Table of Contents

• Multi-scale Processing of Noisy Images using Edge Preservation LossesNati Ofir, Yosi Keller. 1-8 [doi]
• Boundary guided image translation for pose estimation from ultra-low resolution thermal sensorKohei Kurihara, Tianren Wang, Teng Zhang, Brian C. Lovell. 9-15 [doi]
• Progressive Learning Algorithm for Efficient Person Re- IdentificationZhen Li, Hanyang Shao, Liang Niu, Nian Xue. 16-23 [doi]
• Image Defocus Analysis for Finger Detection on A Virtual KeyboardMichio Miwa, Kenji Honda, Makoto Sato. 24-30 [doi]
• EM-net: Deep learning for electron microscopy image segmentationAfshin Khadangi, Thomas Boudier, Vijay Rajagopal. 31-38 [doi]
• Incorporating a graph-matching algorithm into a muscle mechanics modelPep Santacruz, Francesc Serratosa. 39-46 [doi]
• SIMCO: SIMilarity-based object COuntingMarco Godi, Christian Joppi, Andrea Giachetti 0001, Marco Cristani. 47-52 [doi]
• Learning Graph Matching Substitution Weights based on a Linear RegressionShaima Algabli, Francesc Serratosa. 53-58 [doi]
• Fast, Accurate and Lightweight Super-Resolution with Neural Architecture SearchXiangxiang Chu, Bo Zhang 0046, Hailong Ma, Ruijun Xu, Qingyuan Li. 59-64 [doi]
• Crack Detection as a Weakly-Supervised Problem: Towards Achieving Less Annotation-Intensive Crack DetectorsYuki Inoue, Hiroto Nagayoshi. 65-72 [doi]
• Probabilistic Latent Factor Model for Collaborative Filtering with Bayesian InferenceJiansheng Fang, Xiaoqing Zhang, Yan Hu, Yanwu Xu, Ming Yang, Jiang Liu. 73-80 [doi]
• Activity Recognition Using First-Person-View Cameras Based on Sparse Optical FlowsPeng Yua Kao, Yan-Jing Lei, Chia-Hao Chang, Chu-Song Chen, Ming-Sui Lee, Yi-Ping Hung. 81-86 [doi]
• Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss ApproachesKalun Ho, Janis Keuper, Franz-Josef Pfreundt, Margret Keuper. 87-94 [doi]
• Local Facial Attribute Transfer through InpaintingRicard Durall, Franz-Josef Pfreundt, Janis Keuper. 95-102 [doi]
• Calibration and Absolute Pose Estimation of Trinocular Linear Camera Array for Smart City ApplicationsMartin Ahrnbom, Mikael G. Nilsson, Håkan Ardö, Kalle Åström, Oksana Yastremska-Kravchenko, Aliaksei Laureshyn. 103-110 [doi]
• Adaptive Remote Sensing Image Attribute Learning for Active Object DetectionNuo Xu, Chunlei Huo, Jiacheng Guo, Yiwei Liu, Jian Wang, Chunhong Pan. 111-118 [doi]
• Efficient Sentence Embedding via Semantic Subspace AnalysisBin Wang, Fenxiao Chen, Yuncheng Wang, C. C. Jay Kuo. 119-125 [doi]
• Md-knn: An Instance-based Approach for Multi-Dimensional ClassificationBin-Bin Jia, Min-Ling Zhang. 126-133 [doi]
• MANet: Multimodal Attention Network based Point-View Fusion for 3D Shape RecognitionYaxin Zhao, Jichao Jiao, Ning Li 0015, Zhongliang Deng. 134-141 [doi]
• Fully Convolutional Neural Networks for Raw Eye Tracking Data Segmentation, Generation, and ReconstructionWolfgang Fuhl, Yao Rong, Enkelejda Kasneci. 142-149 [doi]
• Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?Xiang Deng, Zhongfei (Mark) Zhang. 150-157 [doi]
• Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a SupercomputerEdward Beeching, Jilles Dibangoye, Olivier Simonin 0001, Christian Wolf 0001. 158-165 [doi]
• CT-UNet: An Improved Neural Network Based on U-Net for Building Segmentation in Remote Sensing ImagesHuanran Ye, Sheng Liu, Kun Jin, Haohao Cheng. 166-172 [doi]
• A Joint Super-Resolution and Deformable Registration Network for 3D Brain ImagesSheng Lan, Zhenhua Guo 0001. 173-179 [doi]
• ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel MatchingRishav, René Schuster, Ramy Battrawy, Oliver Wasenmüller, Didier Stricker. 180-187 [doi]
• Visual Oriented Encoder: Integrating Multimodal and Multi-Scale Contexts for Video CaptioningBang Yang, Yuexian Zou. 188-195 [doi]
• Few-Shot Learning Based on Metric Learning Using Class AugmentationSusumu Matsumi, Keiichi Yamada. 196-201 [doi]
• 2D License Plate Recognition based on Automatic Perspective RectificationHui Xu, Zhaohong Guo, Da-Han Wang, Xiang-Dong Zhou, Yu Shi. 202-208 [doi]
• Automatic Classification of Human Granulosa Cells in Assisted Reproductive Technology using vibrational spectroscopy imagingMarina Paolanti, Marco Mameli, Emanuele Frontoni, Giorgia Gioacchini, Elisabetta Giorgini, Valentina Notarstefano, Carlotta Zacà, Oliana Carnevali, Andrea Bonarini. 209-216 [doi]
• Cascade Saliency Attention Network for Object Detection in Remote Sensing ImagesDayang Yu, Rong Zhang, Shan Qin. 217-223 [doi]
• Softer Pruning, Incremental RegularizationLinhang Cai, Zhulin An, Chuanguang Yang, Yongjun Xu. 224-230 [doi]
• A CNN-RNN Framework for Image Annotation from Visual Cues and Social Network MetadataTobia Tesan, Pasquale Coscia, Lamberto Ballan. 231-238 [doi]
• Fast Approximate Modelling of the Next Combination Result for Stopping the Text Recognition in a VideoKonstantin B. Bulatov, Nadezhda Fedotova, Vladimir V. Arlazarov. 239-246 [doi]
• Sparse-Dense Subspace ClusteringShuai Yang, Wenqi Zhu, Yuesheng Zhu. 247-254 [doi]
• HFP: Hardware-Aware Filter Pruning for Deep Convolutional Neural Networks AccelerationFang Yu, Chuanqi Han, Pengcheng Wang, Ruoran Huang, Xi Huang, Li Cui. 255-262 [doi]
• Generating Private Data Surrogates for Vision Related TasksRyan Webster, Julien Rabin, Loïc Simon, Frédéric Jurie. 263-269 [doi]
• Leveraging a weakly adversarial paradigm for joint learning of disparity and confidence estimationMatteo Poggi, Fabio Tosi, Filippo Aleotti, Stefano Mattoccia. 270-277 [doi]
• Cross-Supervised Joint-Event-Extraction with Heterogeneous Information NetworksYue Wang 0014, Zhuo Xu, Lu Bai 0001, Yao Wan, Lixin Cui, Qian Zhao, Edwin R. Hancock, Philip S. Yu. 278-285 [doi]
• Weakly Supervised Body Part Segmentation with Pose based Part PriorsZhengyuan Yang, Yuncheng Li, Linjie Yang, Ning Zhang, Jiebo Luo. 286-293 [doi]
• Pose-based Body Language Recognition for Emotion and Psychiatric Symptom InterpretationZhengyuan Yang, Amanda Kay, Yuncheng Li, Wendi Cross, Jiebo Luo. 294-301 [doi]
• Jointly Learning Multiple Curvature Descriptor for 3D Palmprint RecognitionLunke Fei, Jianyang Qin, Peng Liu, Jie Wen 0001, Chunwei Tian, Bob Zhang, Shuping Zhao. 302-308 [doi]
• Spatial-related and Scale-aware Network for Crowd CountingLei Li, Yuan Dong, Hongliang Bai. 309-315 [doi]
• Hierarchical Mixtures of Generators for Adversarial LearningAlper Ahmetoglu, Ethem Alpaydin. 316-323 [doi]
• A Scalable Deep Neural Network to Detect Low Quality Images Without a ReferenceZongyi Joe Liu, Bruce Ferry, Simon Lacasse. 324-330 [doi]
• CNN-based repetitive self-revised learning for photos' aesthetics imbalanced classificationYing Dai. 331-338 [doi]
• Extracting Action Hierarchies from Action Labels and their Use in Deep Action RecognitionKonstantinos Bacharidis, Antonis A. Argyros. 339-346 [doi]
• The Effect of Multi-step Methods on Overestimation in Deep Reinforcement LearningLingheng Meng, Rob Gorbet, Dana Kulic. 347-353 [doi]
• Cost Volume Refinement for Depth PredictionJoão L. Cardoso, Nuno Gonçalves, Michael Wimmer. 354-361 [doi]
• Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image TranslationTakehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka, Nakamasa Inoue. 362-369 [doi]
• Text Recognition in Real Scenarios with a Few Labeled SamplesJinghuang Lin, Zhanzhan Cheng, Fan Bai, Yi Niu, Shiliang Pu, Shuigeng Zhou. 370-377 [doi]
• A delayed Elastic-Net approach for performing adversarial attacksBrais Cancela, Verónica Bolón-Canedo, Amparo Alonso-Betanzos. 378-384 [doi]
• Improving Explainability of Integrated Gradients with Guided Non-LinearityHyuk Jin Kwon, Hyung il Koo, Nam Ik Cho. 385-391 [doi]
• Can data placement be effective for Neural Networks classification tasks? Introducing the Orthogonal LossBrais Cancela, Verónica Bolón-Canedo, Amparo Alonso-Betanzos. 392-399 [doi]
• Finger Vein Recognition and Intra-Subject Similarity Evaluation of Finger Veins using the CNN Triplet LossGeorg Wimmer, Bernhard Prommegger, Andreas Uhl. 400-406 [doi]
• MetaMix: Improved Meta-Learning with Interpolation-based Consistency RegularizationYangbin Chen, Yun Ma 0001, Tom Ko, Jianping Wang, Qing Li 0001. 407-414 [doi]
• Creating Classifier Ensembles through Meta-heuristic Algorithms for Aerial Scene ClassificationÁlvaro R. Ferreira, Gustavo Henrique de Rosa, João P. Papa, Gustavo Carneiro, Fábio Augusto Faria. 415-422 [doi]
• ACRM: Attention Cascade R-CNN with Mix-NMS for Metallic Surface Defect DetectionJunting Fang, Xiaoyang Tan, Yuhui Wang. 423-430 [doi]
• Nearest Neighbor Classification Based on Activation Space of Convolutional Neural NetworkXinbo Ju, Shuo Shao, Huan Long, Weizhe Wang. 431-437 [doi]
• Graph signal active contoursOlivier Lézoray. 438-445 [doi]
• Video Summarization with a Dual Attention Capsule NetworkHao Fu, Hongxing Wang 0001, Jianyu Yang. 446-451 [doi]
• Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatio-Temporal Graph Convolutional Network for Action RecognitionKonstantinos Papadopoulos 0002, Enjie Ghorbel, Djamila Aouada, Björn E. Ottersten. 452-458 [doi]
• Combined Invariants to Gaussian Blur and Affine TransformationJitka Kostková, Jan Flusser, Matteo Pedone. 459-464 [doi]
• PC-Net: A Deep Network for 3D Point Clouds AnalysisZhuo Chen, Tao Guan, Yawei Luo, Yuesong Wang, Keyang Luo, Luoyuan Xu. 465-472 [doi]
• Automatically Gather Address Specific Dwelling Images Using Google Street ViewSalman Khan, Carl Salvaggio. 473-480 [doi]
• PROPEL: Probabilistic Parametric Regression Loss for Convolutional Neural NetworksMuhammad Asad, Rilwan Remilekun Basaru, S. M. Masudur Rahman Al-Arif, Greg G. Slabaugh. 481-488 [doi]
• Video Analytics Gait Trend Measurement for Fall Prevention and Health MonitoringLawrence O'Gorman, Xinyi Liu, Md Imran Sarker, Mariofanna G. Milanova. 489-496 [doi]
• Deep Next-Best-View Planner for Cross-Season Visual Route ClassificationKurauchi Kanya, Tanaka Kanji. 497-502 [doi]
• EdgeNet: Semantic Scene Completion from a Single RGB- D ImageAloisio Dourado, Teófilo E. de Campos, Hansung Kim, Adrian Hilton. 503-510 [doi]
• Simple Multi-Resolution Representation Learning for Human Pose EstimationTrung Q. Tran, Giang V. Nguyen, Daeyoung Kim 0001. 511-518 [doi]
• Multi - Direction Convolution for Semantic SegmentationDehui Li, Zhiguo Cao, Ke Xian, Xinyuan Qi, Chao Zhang, Hao Lu 0003. 519-525 [doi]
• Image Representation Learning by Transformation RegressionXifeng Guo 0001, Jiyuan Liu 0003, Sihang Zhou, En Zhu, Shihao Dong. 526-533 [doi]
• Temporal Extension Module for Skeleton-Based Action RecognitionYuya Obinata, Takuma Yamamoto. 534-540 [doi]
• F-mixup: Attack CNNs From Fourier PerspectiveXiu-Chuan Li, Xu-Yao Zhang, Fei Yin, Cheng-Lin Liu. 541-548 [doi]
• Efficient correlation filter tracking with adaptive training sample update schemeShan Jiang, Shuxiao Li, Chengfei Zhu, Nan Yan. 549-555 [doi]
• Enhanced User Interest and Expertise Modeling for Expert RecommendationTongze He, Caili Guo, Yunfei Chu. 556-562 [doi]
• Translating Adult's Focus of Attention to Elderly'sOnkar Krishna, Go Irie, Takahito Kawanishi, Kunio Kashino, Kiyoharu Aizawa. 563-568 [doi]
• How to define a rejection class based on model learning?Sarah Laroui, Xavier Descombes, Aurélia Vernay, Florent Villiers, François Villalba, Eric Debreuve. 569-576 [doi]
• Exploiting Distilled Learning for Deep Siamese TrackingChengxin Liu, Zhiguo Cao, Wei Li, Yang Xiao, Shuaiyuan Du, Angfan Zhu. 577-583 [doi]
• Open-World Group Retrieval with Ambiguity Removal: A BenchmarkLing Mei, Jianhuang Lai, Zhan-Xiang Feng, Xiaohua Xie. 584-591 [doi]
• RGB-Infrared Person Re-identification via Image Modality ConversionHuangpeng Dai, Qing Xie 0002, Yanchun Ma, Yongjian Liu, Shengwu Xiong. 592-598 [doi]
• Distortion-Adaptive Grape Bunch Counting for Omnidirectional ImagesRyota Akai, Yuzuko Utsumi, Yuka Miwa, Masakazu Iwamura, Koichi Kise. 599-606 [doi]
• Video-based Facial Expression Recognition using Graph Convolutional NetworksDaizong Liu, Hongting Zhang, Pan Zhou. 607-614 [doi]
• Cross-spectrum Face Recognition Using Subspace Projection HashingHanrui Wang 0003, Xingbo Dong, Zhe Jin, Jean-Luc Dugelay, Massimo Tistarelli. 615-622 [doi]
• Object Segmentation Tracking from Generic Video CuesAmirhossein Kardoost, Sabine Müller 0001, Joachim Weickert, Margret Keuper. 623-630 [doi]
• ActionSpotter: Deep Reinforcement Learning Framework for Temporal Action Spotting in VideosGuillaume Vaudaux-Ruth, Adrien Chan-Hon-Tong, Catherine Achard. 631-638 [doi]
• Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric LearningVladislav Sovrasov, Dmitry Sidnev. 639-646 [doi]
• An Efficient Empirical Solver for Localized Multiple Kernel Learning via DNNsZiming Zhang. 647-654 [doi]
• Total Whitening for Online Signature Verification Based on Deep RepresentationXiaomeng Wu, Akisato Kimura, Kunio Kashino, Seiichi Uchida. 655-661 [doi]
• Reducing False Positives in Object Tracking with Siamese NetworkTakuya Ogawa, Takashi Shibata 0001, Shoji Yachida, Toshinori Hosoi. 662-669 [doi]
• TSDM: Tracking by SiamRPN++ with a Depth-refiner and a Mask-generatorPengyao Zhao, Quanli Liu, Wei Wang, Qiang Guo. 670-676 [doi]
• Atmospheric Blocking Pattern Recognition in Global Climate Model Simulation DataGrzegorz Muszynski, Prabhat, Jan Balewski, Karthik Kashinath, Michael F. Wehner, Vitaliy Kurlin. 677-684 [doi]
• MixedFusion: 6D Object Pose Estimation from Decoupled RGB-Depth FeaturesHangtao Feng, Lu Zhang, Xu Yang, Zhiyong Liu 0001. 685-691 [doi]
• An Intransitivity Model for Matchup and Pairwise ComparisonYan Gu, Jiuding Duan, Hisashi Kashima. 692-698 [doi]
• Multimodal End-to-End Learning for Autonomous Steering in Adverse Road and Weather ConditionsJyri Maanpää, Josef Taher, Petri Manninen, Leo Pakola, Iaroslav Melekhov, Juha Hyyppä. 699-706 [doi]
• SiamMT: Real-Time Arbitrary Multi-Object TrackingLorenzo Vaquero, Manuel Mucientes, Víctor M. Brea. 707-714 [doi]
• Vehicle Lane Merge Visual BenchmarkKai Cordes, Hellward Broszio. 715-722 [doi]
• PS2-Net: A Locally and Globally Aware Network for Point-Based Semantic SegmentationNa Zhao, Tat-Seng Chua, Gim Hee Lee. 723-730 [doi]
• Phase Retrieval Using Conditional Generative Adversarial NetworksTobias Uelwer, Alexander Oberstrabeta, Stefan Harmeling. 731-738 [doi]
• Learning to Take Directions One Step at a TimeQiyang Hu, Adrian Wälchli, Tiziano Portenier, Matthias Zwicker, Paolo Favaro. 739-746 [doi]
• Deep Universal Blind Image DenoisingJae Woong Soh, Nam Ik Cho. 747-754 [doi]
• One-shot learning for acoustic identification of bird species in non-stationary environmentsMichelangelo Acconcjaioco, Stavros Ntalampiras. 755-762 [doi]
• Adversarial Encoder-Multi-Task-Decoder for Multi-Stage ProcessesAndre Mendes, Julian Togelius, Leandro dos Santos Coelho. 763-770 [doi]
• What and How? Jointly Forecasting Human Action and PoseYanjun Zhu, David S. Doermann, Yanxia Zhang, Qiong Liu 0003, Andreas Girgensohn. 771-778 [doi]
• Weakly Supervised Attention Rectification for Scene Text RecognitionChengyu Gu, Shilin Wang, Yiwei Zhu, Zheng Huang, Kai Chen 0006. 779-786 [doi]
• A Fast and Accurate Object Detector for Handwritten Digit String RecognitionJun Guo, Wenjing Wei, Yifeng Ma, Cong Peng. 787-794 [doi]
• SFPN: Semantic Feature Pyramid Network for Object DetectionYi Gan, Wei Xu, Jianbo Su. 795-802 [doi]
• Small Object Detection Leveraging on Simultaneous Super-resolutionHong Ji, Zhi Gao, Xiaodong Liu, Yongjun Zhang 0002, Tiancan Mei. 803-810 [doi]
• Class Conditional Alignment for Partial Domain AdaptationMohsen Kheirandishfard, Fariba Zohrizadeh, Farhad Kamangar. 811-818 [doi]
• AdvHat: Real-World Adversarial Attack on ArcFace Face ID SystemStepan Komkov, Aleksandr Petiushko. 819-826 [doi]
• PSDNet: A Balanced Architecture of Accuracy and Parameters for Semantic SegmentationYue Liu, Zhichao Lian. 827-834 [doi]
• Bridging the gap between Natural and Medical Images through Deep ColorizationLia Morra, Luca Piano, Fabrizio Lamberti, Tatiana Tommasi. 835-842 [doi]
• Learning Error-Driven Curriculum for Crowd CountingWenxi Li, Zhuoqun Cao, Qian Wang, Songjian Chen, Rui Feng. 843-849 [doi]
• Self-Training for Domain Adaptive Scene Text DetectionYudi Chen, Wei Wang, Yu Zhou 0015, Fei Yang, Dongbao Yang, Weiping Wang 0005. 850-857 [doi]
• Automatical Enhancement and Denoising of Extremely Low-light ImagesYuda Song, Yunfang Zhu, Xin Du. 858-865 [doi]
• FastCompletion: A Cascade Network with Multiscale Group-Fused Inputs for Real-Time Depth CompletionAng Li, Zejian Yuan, Yonggen Ling, Wanchao Chi, Shenghao Zhang, Chong Zhang. 866-872 [doi]
• LFIEM: Lightweight Filter-based Image Enhancement ModelOktai Tatanov, Aleksei Samarin. 873-878 [doi]
• Improving Visual Question Answering using Active Perception on Static ImagesTheodoros Bozinis, Nikolaos Passalis, Anastasios Tefas. 879-884 [doi]
• Leveraging Quadratic Spherical Mutual Information Hashing for Fast Image RetrievalNikolaos Passalis, Anastasios Tefas. 885-892 [doi]
• DEN: Disentangling and Exchanging Network for Depth CompletionYou-Feng Wu, Vu-Hoang Tran, Ting-Wei Chang, Wei-chen Chiu, Ching-Chun Huang. 893-900 [doi]
• Double Manifolds Regularized Non-negative Matrix Factorization for Data RepresentationJipeng Guo 0001, Shuai Yin, Yanfeng Sun, Yongli Hu. 901-906 [doi]
• Low Rank Representation on Product Grassmann Manifolds for Multi-view Subspace ClusteringJipeng Guo 0001, Yanfeng Sun, Junbin Gao, Yongli Hu, Baocai Yin. 907-914 [doi]
• Coherence and Identity Learning for Arbitrary-length Face Video GenerationShuquan Ye, Chu Han, Jiaying Lin, Guoqiang Han, Shengfeng He. 915-922 [doi]
• Feature-aware unsupervised learning with joint variational attention and automatic clusteringRu Wang, Lin Li, Peipei Wang, Xiaohui Tao, Peiyu Liu. 923-930 [doi]
• Controllable Face AgingHaien Zeng, Hanjiang Lai. 931-938 [doi]
• Learning to Prune in Training via Dynamic Channel PropagationShibo Shen, Rongpeng Li, Zhifeng Zhao, Honggang Zhang 0001, Yugeng Zhou. 939-945 [doi]
• Reinforcement Learning with Dual Attention Guided Graph Convolution for Relation ExtractionZhixin Li, Yaru Sun, Suqin Tang, Canlong Zhang, Huifang Ma. 946-953 [doi]
• Object Detection Model Based on Scene-Level Region Proposal Self-AttentionYu Quan, Zhixin Li, Canlong Zhang, Huifang Ma. 954-961 [doi]
• RWMF: A Real-World Multimodal Foodlog DatabasePengfei Zhou, Cong Bai, Kaining Ying, Jie Xia, Lixin Huang. 962-968 [doi]
• Penalized K-Means Algorithms for Finding the Number of ClustersBehzad Kamgar-Parsi, Behrooz Kamgar-Parsi. 969-974 [doi]
• Learning Recurrent High-order Statistics for Skeleton-based Hand Gesture RecognitionXuan Son Nguyen, Luc Brun, Olivier Lézoray, Sébastien Bougleux. 975-982 [doi]
• Unsupervised Domain Adaptation for Object Detection in Cultural SitesGiovanni Pasqualino, Antonino Furnari, Giovanni Maria Farinella. 983-990 [doi]
• On the Evaluation of Generative Adversarial Networks By Discriminative ModelsAmirsina Torfi, Mohammadreza Beyki, Edward A. Fox. 991-998 [doi]
• Scalable Direction-Search-Based Approach to Subspace ClusteringYicong He, George K. Atia. 999-1006 [doi]
• Efficient Online Subclass Knowledge Distillation for Image ClassificationMaria Tzelepi, Nikolaos Passalis, Anastasios Tefas. 1007-1014 [doi]
• Fourier Domain Pruning of MobileNet-V2 with Application to Video Based Wildfire DetectionHongyi Pan, Diaa Badawi, Ahmet Enis Çetin. 1015-1022 [doi]
• Initialization Using Perlin Noise for Training Networks with a Limited Amount of DataNakamasa Inoue, Eisuke Yamagata, Hirokatsu Kataoka. 1023-1028 [doi]
• MTGAN: Mask and Texture-driven Generative Adversarial Network for Lung Nodule SegmentationWei Chen, Qiuli Wang 0001, Kun Wang, Dan Yang, Xiaohong Zhang, Chen Liu, Yucong Li. 1029-1035 [doi]
• Multiple-step Sampling for Dense Object Detection and CountingZhaoli Deng, Chenhui Yang. 1036-1042 [doi]
• EasiECG: A Novel Inter-Patient Arrhythmia Classification Method using ECG WavesChuanqi Han, Ruoran Huang, Fang Yu, Xi Huang, Li Cui. 1043-1050 [doi]
• q-SNE: Visualizing Data using q-Gaussian Distributed Stochastic Neighbor EmbeddingMotoshi Abe, Jun'ichi Miyao, Takio Kurita. 1051-1058 [doi]
• Semi-Supervised Domain Adaptation via Selective Pseudo Labeling and Progressive Self-TrainingYoonhyung Kim, Changick Kim. 1059-1066 [doi]
• DAPC: Domain Adaptation People Counting via Style-level Transfer Learning and Scene-aware EstimationNa Jiang, Xingsen Wen, Zhiping Shi 0002. 1067-1074 [doi]
• Lane Detection based on Object Detection and Image-to-image TranslationHiroyuki Komori, Kazunori Onoguchi. 1075-1082 [doi]
• TCATD: Text Contour Attention for Scene Text DetectionZiling Hu, Xingjiao Wu, Jing Yang. 1083-1088 [doi]
• Filter Pruning using Hierarchical Group Sparse Regularization for Deep Convolutional Neural NetworksKakeru Mitsuno, Takio Kurita. 1089-1095 [doi]
• JUMPS: Joints Upsampling Method for Pose SequencesLucas Mourot, François Le Clerc, Cédric Thébault, Pierre Hellier. 1096-1103 [doi]
• Fast Multi-Level Foreground EstimationThomas Germer, Tobias Uelwer, Stefan Conrad 0001, Stefan Harmeling. 1104-1111 [doi]
• Local Gradient Difference Features for Classification of 2D-3D Natural Scene Text ImagesLokesh Nandanwar, Palaiahnakote Shivakumara, Ramachandra Raghavendra, Tong Lu, Umapada Pal 0001, Daniel Lopresti, Nor Badrul Anuar. 1112-1119 [doi]
• FOANet: A Focus of Attention Network with Application to Myocardium SegmentationZhou Zhao, Élodie Puybareau, Nicolas Boutry, Thierry Géraud. 1120-1127 [doi]
• Stabilized Calculation of Gaussian Smoothing and Its Differentials Using Attenuated Sliding Fourier TransformYukihiko Yamashita, Toru Wakahara. 1128-1135 [doi]
• Minimal Solvers for Indoor UAV PositioningMarcus Valtonen Örnhag, Patrik Persson, Mårten Wadenbäck, Kalle Åström, Anders Heyden. 1136-1143 [doi]
• Polynomial Universal Adversarial Perturbations for Person Re-IdentificationWenjie Ding, Xing Wei, Rongrong Ji, Xiaopeng Hong, Yihong Gong. 1144-1151 [doi]
• Explore and Explain: Self-supervised Navigation and RecountingRoberto Bigazzi, Federico Landi, Marcella Cornia, Silvia Cascianelli, Lorenzo Baraldi, Rita Cucchiara. 1152-1159 [doi]
• RobusterNet: Improving Copy-Move Forgery Detection with Volterra-based ConvolutionsEfthimia Kafali, Nicholas Vretos, Theodoros Semertzidis, Petros Daras. 1160-1165 [doi]
• Human Segmentation with Dynamic LiDAR DataTao Zhong, Wonjik Kim, Masayuki Tanaka 0001, Masatoshi Okutomi. 1166-1172 [doi]
• Answer-checking in Context: A Multi-modal Fully Attention Network for Visual Question AnsweringHantao Huang, Tao Han, Wei Han, Deep Yap, Cheng-Ming Chiang. 1173-1180 [doi]
• Exploring the ability of CNN s to generalise to previously unseen scales over wide scale rangesYlva Jansson, Tony Lindeberg. 1181-1188 [doi]
• SCA Net: Sparse Channel Attention Module for Action RecognitionHang Song, Yonghong Song, Yuanlin Zhang 0001. 1189-1196 [doi]
• HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving ObjectsSuihanjin Yu, Youmin Zhang 0005, Chen Wang 0026, Xiao Bai 0001, Liang Zhang, Edwin R. Hancock. 1197-1204 [doi]
• PowerHC: non linear normalization of distances for advanced nearest neighbor classificationManuele Bicego, Mauricio Orozco-Alzate. 1205-1211 [doi]
• A Novel Attention-based Aggregation Function to Combine Vision and LanguageMatteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara. 1212-1219 [doi]
• Rethinking deep active learning: Using unlabeled data at model trainingOriane Siméoni, Mateusz Budnik, Yannis Avrithis, Guillaume Gravier. 1220-1227 [doi]
• Pose-aware Multi-feature Fusion Network for Driver Distraction RecognitionMingyan Wu, Xi Zhang, LinLin Shen, Hang Yu. 1228-1235 [doi]
• SA-UNet: Spatial Attention U-Net for Retinal Vessel SegmentationChanglu Guo, Márton Szemenyei, Yugen Yi, Wenle Wang, Buer Chen, Changqi Fan. 1236-1242 [doi]
• Delving in the loss landscape to embed robust watermarks into neural networksEnzo Tartaglione, Marco Grangetto, Davide Cavagnino, Marco Botta. 1243-1250 [doi]
• PEAN: 3D Hand Pose Estimation Adversarial NetworkLinhui Sun, Yifan Zhang 0001, Jian Cheng 0001, Hanqing Lu. 1251-1258 [doi]
• ILS-SUMM: Iterated Local Search for Unsupervised Video SummarizationYair Shemer, Daniel Rotman, Nahum Shimkin. 1259-1266 [doi]
• Snapshot Hyperspectral Imaging Based on Weighted High-order Singular Value RegularizationNiankai Cheng, Hua Huang, Lei Zhang, Lizhi Wang. 1267-1274 [doi]
• Multi-Task Learning Based Traditional Mongolian Words RecognitionHongxi Wei, Hui Zhang, Jing Zhang, Kexin Liu. 1275-1281 [doi]
• Seasonal Inhomogeneous Nonconsecutive Arrival Process Search and EvaluationKimberly Holmgren, Paul Gibby, Joseph R. Zipkin. 1282-1289 [doi]
• Cross-media Hash Retrieval Using Multi-head Attention NetworkZhixin Li, Feng Ling, Chuansheng Xu, Canlong Zhang, Huifang Ma. 1290-1297 [doi]
• Confidence Calibration for Deep Renal Biopsy Immunofluorescence Image ClassificationFederico Pollastri, Juan Maroñas, Federico Bolelli, Giulia Ligabue, Roberto Paredes, Riccardo Magistroni, Costantino Grana. 1298-1305 [doi]
• Color Texture Description Based on Holistic and Hierarchical Order-Encoding PatternsTiecheng Song, Jie Feng, Yuanlin Wang, Chenqiang Gao. 1306-1312 [doi]
• Porting A Convolutional Neural Network For Stereo Vision In HardwareDionisios G. Sotiropoulos, George-Peter K. Economou. 1313-1320 [doi]
• Learning with Multiplicative PerturbationsXiulong Yang, Shihao Ji. 1321-1328 [doi]
• GCNs-Based Context-Aware Short Text Similarity ModelXiaoqi Sun, Shaochun Wu, Yue Liu. 1329-1335 [doi]
• Cascade Attention Guided Residue Learning GAN for Cross-Modal TranslationBin Duan, Wei Wang, Hao Tang, Hugo Latapie, Yan Yan 0002. 1336-1343 [doi]
• A Novel Random Forest Dissimilarity Measure for Multi-View LearningHongliu Cao, Simon Bernard, Robert Sabourin, Laurent Heutte. 1344-1351 [doi]
• Recurrent Graph Convolutional Networks for Skeleton-based Action RecognitionGuangming Zhu 0001, Lu Yang, Liang Zhang, Peiyi Shen, Juan Song. 1352-1359 [doi]
• Watermelon: a Novel Feature Selection Method Based on Bayes Error Rate Estimation and a New Interpretation of Feature Relevance and RedundancyXiang Xie, Wilhelm Stork. 1360-1367 [doi]
• SATGAN: Augmenting Age Biased Dataset for Cross-Age Face RecognitionWenshuang Liu, Wenting Chen, Yuanlue Zhu, LinLin Shen. 1368-1375 [doi]
• MFPP: Morphological Fragmental Perturbation Pyramid for Black-Box Model ExplanationsQing Yang, Xia Zhu, Jong-Kae Fwu, Yun Ye, Ganmei You, Yuan Zhu. 1376-1383 [doi]
• Semantics to Space(S2S): Embedding semantics into spatial space for zero-shot verb-object query inferencingSungmin Eum, Heesung Kwon. 1384-1391 [doi]
• Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient DescentRiccardo Barbano, Chen Zhang, Simon R. Arridge, Bangti Jin. 1392-1399 [doi]
• Meta Generalized Network for Few-Shot ClassificationWei Wu, Shanmin Pang, Zhiqiang Tian, Yaochen Li. 1400-1405 [doi]
• Arbitrary Style Transfer with Parallel Self-AttentionTiange Zhang, Ying Gao, Feng Gao, Lin Qi, Junyu Dong. 1406-1413 [doi]
• An Adaptive Fusion Model Based on Kalman Filtering and LSTM for Fast Tracking of Road SignsChengliang Wang, Xin Xie, Chao Liao. 1414-1421 [doi]
• Exploring and Exploiting the Hierarchical Structure of a Scene for Scene Graph GenerationIkuto Kurosawa, Tetsunori Kobayashi, Yoshihiko Hayashi. 1422-1429 [doi]
• Self-paced Bottom-up Clustering Network with Side Information for Person Re-IdentificationMingkun Li, Chun-Guang Li, Ruo-Pei Guo, Jun Guo 0002. 1430-1437 [doi]
• The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual ResidualsTakumi Kawashima, Qing Yu, Akari Asai, Daiki Ikami, Kiyoharu Aizawa. 1438-1445 [doi]
• NAS-EOD: an end-to-end Neural Architecture Search method for Efficient Object DetectionHuigang Zhang, Liuan Wang, Jun Sun, Li Sun 0007, Hiromichi Kobashi, Nobutaka Imamura. 1446-1451 [doi]
• Triplet-path Dilated Network for Detection and Segmentation of General Pathological ImagesJiaqi Luo, Zhicheng Zhao, Fei Su, Limei Guo. 1452-1459 [doi]
• UHRSNet: A Semantic Segmentation Network Specifically for Ultra-High-Resolution ImagesLianlei Shan, Minglong Li, Xiaobin Li 0006, Yang Bai, Ke Lv, Bin Luo, Si-Bao Chen, Weiqiang Wang. 1460-1466 [doi]
• Revisiting ImprovedGAN with Metric Learning for Semi-Supervised LearningJaewoo Park, Yoon Gyo Jung, Andrew Beng Jin Teoh. 1467-1474 [doi]
• VGG-Embedded Adaptive Layer-Normalized Crowd Counting Net with Scale-Shuffling ModulesDewen Guo, Jie Feng 0001, Bingfeng Zhou. 1475-1482 [doi]
• MagnifierNet: Learning Efficient Small-scale Pedestrian Detector towards Multiple Dense RegionsQi Cheng, Mingqin Chen, Yingjie Wu, Fei Chen, Shiping Lin. 1483-1490 [doi]
• Coarse to Fine: Progressive and Multi-Task Learning for Salient Object DetectionDonggoo Kang, Sangwoo Park, Joonki Paik. 1491-1498 [doi]
• Residual Learning of Video Frame Interpolation Using Convolutional LSTMKeito Suzuki, Masaaki Ikehara. 1499-1504 [doi]
• Camera Calibration Using Parallel Line SegmentsGaku Nakano. 1505-1512 [doi]
• The Role of Cycle Consistency for Generating Better Human Action Videos from a Single FrameRunze Li, Bir Bhanu. 1513-1520 [doi]
• RLST: A Reinforcement Learning Approach to Scene Text Detection RefinementXuan Peng, Zheng Huang, Kai Chen, Jie Guo, Weidong Qiu. 1521-1528 [doi]
• Multi-Scale and Attention based ResNet for Heartbeat ClassificationHaojie Zhang, Gongping Yang, Yuwen Huang, Feng Yuan, Yilong Yin. 1529-1535 [doi]
• Improving reliability of attention branch network by introducing uncertaintyTakuya Tsukahara, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi. 1536-1542 [doi]
• Motion Complementary Network for Efficient Action RecognitionKe Cheng, Yifan Zhang 0001, Chenghua Li, Jian Cheng, Hanqing Lu. 1543-1549 [doi]
• Discrete Semantic Matrix Factorization Hashing for Cross-Modal RetrievalJianyang Qin, Lunke Fei, Shaohua Teng, Wei Zhang, Dongning Liu, Genping Zhao, Haoliang Yuan. 1550-1557 [doi]
• Fast Subspace Clustering Based on the Kronecker ProductLei Zhou 0008, Xiao Bai 0001, Liang Zhang, Jun Zhou, Edwin R. Hancock. 1558-1565 [doi]
• Learning sparse deep neural networks using efficient structured projections on convex constraints for green AIMichel Barlaud, Frédéric Guyard. 1566-1573 [doi]
• You Ought to Look Around: Precise, Large Span Action DetectionGe Pan, Han Zhang, Fan Yu, Yonghong Song, Yuanlin Zhang 0001, Han Yuan. 1574-1581 [doi]
• UCCTGAN: Unsupervised Clothing Color Transformation Generative Adversarial NetworkShuming Sun, Xiaoqiang Li, Jide Li. 1582-1589 [doi]
• Accurate Cell Segmentation in Digital Pathology Images via Attention Enforced NetworksZeyi Yao, Kaiqi Li, Yiwen Luo, Xiaoguang Zhou, Muyi Sun, Guanhong Zhang. 1590-1595 [doi]
• Residual Fractal Network for Single Image Super Resolution by Widening and DeepeningJiahang Gu, Zhaowei Qu, Xiaoru Wang, Jiawang Dan, Junwei Sun. 1596-1603 [doi]
• Video Object Detection Using Object's Motion Context and Spatio-Temporal Feature AggregationJaekyum Kim, Junho Koh, Byeongwon Lee, Seungji Yang, Jun Won Choi. 1604-1610 [doi]
• Learning Stereo Matchability in Disparity Regression NetworksJingyang Zhang, Yao Yao 0008, Zixin Luo, Shiwei Li, Tianwei Shen, Tian Fang, Long Quan. 1611-1618 [doi]
• Self-supervised learning of Dynamic Representations for Static ImagesSiyang Song, Enrique Sanchez, LinLin Shen, Michel F. Valstar. 1619-1626 [doi]
• Wasserstein k-means with sparse simplex projectionTakumi Fukunaga, Hiroyuki Kasai. 1627-1634 [doi]
• Cross-layer Information Refining Network for Single Image Super-ResolutionHongyi Zhang, Wen Lu, Xiaopeng Sun. 1635-1640 [doi]
• Thermal Characterisation of Unweighted and Weighted NetworksJianjia Wang, Hui Wu, Edwin R. Hancock. 1641-1648 [doi]
• ReADS: A Rectified Attentional Double Supervised Network for Scene Text RecognitionQi Song, Qianyi Jiang, Nan Li, Rui Zhang, Xiaolin Wei. 1649-1656 [doi]
• Attributes Aware Face Generation with Generative Adversarial NetworksZheng Yuan, Jie Zhang 0071, Shiguang Shan, Xilin Chen. 1657-1664 [doi]
• Saliency Prediction on Omnidirectional Images with Brain-Like Shallow Neural NetworkDandan Zhu, Yongqing Chen, Xiongkuo Min, Defang Zhao, Yucheng Zhu, Qiangqiang Zhou, Xiaokang Yang, Tian Han 0001. 1665-1671 [doi]
• G-FAN: Graph-Based Feature Aggregation Network for Video Face RecognitionHe Zhao, Yongjie Shi, Xin Tong, Jingsi Wen, Xianghua Ying, Hongbin Zha. 1672-1678 [doi]
• Unsupervised Multi-Task Domain AdaptationShih-Min Yang, Mei-Chen Yeh. 1679-1685 [doi]
• Embedding shared low-rank and feature correlation for multi-view data analysisZhan Wang, Lizhi Wang, Lei Zhang, Hua Huang. 1686-1693 [doi]
• fMRI Brain Networks as Statistical Mechanical EnsemblesHui Wu, Jianjia Wang, Edwin R. Hancock. 1694-1700 [doi]
• Position-aware and Symmetry Enhanced GAN for Radial Distortion CorrectionYongjie Shi, Xin Tong, Jingsi Wen, He Zhao, Xianghua Ying, Hongbin Zha. 1701-1708 [doi]
• Feature Embedding Based Text Instance Grouping for Largely Spaced and Occluded Text DetectionPan Gao, Qi Wan, Renwu Gao, LinLin Shen. 1709-1716 [doi]
• Deeply-fused Attentive Network for Stereo MatchingZuliu Yang, Xindong Ai, Weida Yang, Yong Zhao 0010, Qifei Dai, Fuchi Li. 1717-1724 [doi]
• HP2IFS: Head Pose estimation exploiting Partitioned Iterated Function SystemsCarmen Bisogni, Michele Nappi, Chiara Pero, Stefano Ricciardi. 1725-1730 [doi]
• Detail Fusion GAN: High-Quality Translation for Unpaired Images with GAN-based Data AugmentationLing Li, Yaochen Li, Chuan Wu, Hang Dong, Peilin Jiang, Fei Wang. 1731-1736 [doi]
• Content-Sensitive Superpixels Based on Adaptive RegrowthXiaopeng Li, Junlin Xiong. 1737-1743 [doi]
• CAggNet: Crossing Aggregation Network for Medical Image SegmentationXu Cao, Yanghao Lin. 1744-1750 [doi]
• MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action RecognitionKaiyu Shan, Yongtao Wang, Zhi Tang, Ying Chen, Yangyan Li. 1751-1756 [doi]
• 3D Facial Matching by Spiral Convolutional Metric Learning and a Biometric Fusion-Net of Demographic PropertiesSoha Sadat Mahdi, Nele Nauwelaers, Philip Joris, Giorgos Bouritsas, Shunwang Gong, Sergiy Bokhnyak, Susan Walsh, Mark D. Shriver, Michael M. Bronstein, Peter Claes. 1757-1764 [doi]
• Reducing-Over-Time Tree for Event-based DataShane Harrigan, Sonya Coleman, Dermot Kerr, Pratheepan Yogarajah, Zheng Fang, Chengdong Wu. 1765-1772 [doi]
• 3CS Algorithm for Efficient Gaussian Process Model RetrievalFabian Berns, Kjeld Schmidt, Ingolf Bracht, Christian Beecks. 1773-1780 [doi]
• Clusterface: Joint Clustering and Classification for Set-Based Face RecognitionSamadhi Wickrama Arachchilage, Ebroul Izquierdo. 1781-1787 [doi]
• Sensor-independent Pedestrian Detection for Personal Mobility Vehicles in Walking Space Using Dataset Generated by SimulationTakahiro Shimizu, Kenji Koide, Shuji Oishi, Masashi Yokozuka, Atsuhiko Banno, Motoki Shino. 1788-1795 [doi]
• A Unified Framework for Distance-Aware Domain AdaptationFei Wang, Youdong Ding, Huan Liang, Yuzhen Gao, Wenqi Che. 1796-1803 [doi]
• DCT/IDCT Filter Design for Ultrasound Image FilteringBarmak Honarvar Shakibaei Asli, Jan Flusser, Yifan Zhao, John Ahmet Erkoyuncu, Rajkumar Roy. 1804-1811 [doi]
• Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain AdaptationHai H. Tran, Sumyeong Ahn, Taeyoung Lee, Yung Yi. 1812-1819 [doi]
• Road Network Metric Learning for Estimated Time of ArrivalYiwen Sun, Kun Fu, Zheng Wang, Changshui Zhang, Jieping Ye. 1820-1827 [doi]
• Boundary-aware Graph Convolution for Semantic SegmentationHanzhe Hu, Jinshi Cui, Hongbin Zha. 1828-1835 [doi]
• VSB2-Net: Visual-Semantic Bi-Branch Network for Zero-Shot HashingXin Li, Xiangfeng Wang, Bo Jin, Wenjie Zhang, Jun Wang, Hongyuan Zha. 1836-1843 [doi]
• MRP-Net: A Light Multiple Region Perception Neural Network for Multi-label AU DetectionYang Tang, Shuang Chen, Honggang Zhang, Gang Wang, Rui Yang. 1844-1851 [doi]
• Deep Iterative Residual Convolutional Network for Single Image Super-ResolutionRao Muhammad Umer, Gian Luca Foresti, Christian Micheloni. 1852-1858 [doi]
• Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot LearningJunjie Wang, Xiangfeng Wang, Bo Jin, Junchi Yan, Wenjie Zhang, Hongyuan Zha. 1859-1866 [doi]
• Visual Saliency Oriented Vehicle Scale EstimationJiali Ding, Tie Liu, Qixin Chen, Zejian Yuan, Yuanyuan Shang. 1867-1873 [doi]
• Hierarchical Classification with Confidence using Generalized LogitsJim Davis, Tong Liang, James Enouen, Roman Ilin. 1874-1881 [doi]
• P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference DistributionsWei Hu, QiHao Zhao, Yangyu Huang, Fan Zhang. 1882-1889 [doi]
• RSAN: Residual Subtraction and Attention Network for Single Image Super-ResolutionShuo Wei, Xin Sun 0007, Haoran Zhao, Junyu Dong. 1890-1895 [doi]
• Audio-Visual Speech Recognition Using A Two-Step Feature Fusion StrategyHong Liu, Wanlu Xu, Bing Yang. 1896-1903 [doi]
• Rethinking ReID: Multi-Feature Fusion Person Re-identification Based on Orientation ConstraintsMingjing Ai, Guozhi Shan, Bo Liu, Tianyang Liu. 1904-1911 [doi]
• Cross-Domain Semantic Segmentation of Urban Scenes via Multi-Level Feature AlignmentBin Zhang, Shengjie Zhao, Rongqing Zhang 0001. 1912-1917 [doi]
• DA-RefineNet: Dual-inputs Attention RefineNet for Whole Slide Image SegmentationZiqiang Li, Rentuo Tao, Qianrun Wu, Bin Li. 1918-1925 [doi]
• Small Object Detection by Generative and Discriminative LearningYi Gu, Jie Li, Chentao Wu, Weijia Jia 0001, Jianping Chen. 1926-1933 [doi]
• Fused 3-Stage Image Segmentation for Pleural Effusion Cell ClustersSike Ma, Meng Zhao, Hao Wang 0003, Fan Shi, Xuguo Sun, Shengyong Chen, Hong-Ning Dai. 1934-1941 [doi]
• Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept ManipulationZiqiang Li, Rentuo Tao, Hongjing Niu, Mingdao Yue, Bin Li. 1942-1948 [doi]
• One-stage Multi-task Detector for 3D Cardiac MR ImagingWeizeng Lu, Xi Jia, Wei Chen, Nicoló Savioli, Antonio de Marvao, LinLin Shen, Declan P. O'Regan, Jinming Duan 0001. 1949-1955 [doi]
• PHNet: Parasite-Host Network for Video Crowd CountingShiqiao Meng, Jiajie Li, Weiwei Guo, Lai Ye, Jinfeng Jiang. 1956-1963 [doi]
• Semantic Object Segmentation in Cultural Sites using Real and Synthetic DataFrancesco Ragusa, Daniele Di Mauro, Alfio Palermo, Antonino Furnari, Giovanni Maria Farinella. 1964-1971 [doi]
• Improving Low-Resolution Image Classification by Super-Resolution with Enhancing High-Frequency ContentLiguo Zhou, Guang Chen, Mingyue Feng, Alois Knoll. 1972-1978 [doi]
• Correlation-based ConvNet for Small Object Detection in VideosBrais Bosquet, Manuel Mucientes, Víctor M. Brea. 1979-1984 [doi]
• Stage-Wise Neural Architecture SearchArtur Jordao, Fernando Akio, Maiko M. I. Lie, William Robson Schwartz. 1985-1992 [doi]
• User-Independent Gaze Estimation by Extracting Pupil Parameter and Its Mapping to the Gaze AngleSang Yoon Han, Nam Ik Cho. 1993-2000 [doi]
• Regularized Flexible Activation Function Combination for Deep Neural NetworksRenlong Jie, Junbin Gao, Andrey Vasnev, Minh-Ngoc Tran. 2001-2008 [doi]
• Vacant Parking Space Detection based on Task Consistency and Reinforcement LearningManh-Hung Nguyen, Tzu-Yin Chao, Ching-Chun Huang. 2009-2016 [doi]
• Disentangled Representation based Face Anti-SpoofingZhao Liu, Zunlei Feng, Zeyu Zou, Rong Zhang, Mingli Song, Jianping Shen. 2017-2024 [doi]
• Online Object Recognition Using CNN-based Algorithm on High-speed Camera Imaging: Framework for fast and robust high-speed camera object recognition based on population data cleansing and data ensembleShigeaki Namiki, Keiko Yokoyama, Shoji Yachida, Takashi Shibata 0001, Hiroyoshi Miyano, Masatoshi Ishikawa. 2025-2032 [doi]
• Stylized-Colorization for Line ArtsTzu-Ting Fang, Duc Minh Vo, Akihiro Sugimoto, Shang-Hong Lai. 2033-2040 [doi]
• Integrating Historical States and Co-attention Mechanism for Visual DialogTianling Jiang, Yi Ji 0001, Chunping Liu. 2041-2048 [doi]
• Video Episode Boundary Detection with Joint Episode-Topic ModelShunyao Wang, Ye Tian, Ruidong Wang, Yang Du, Han Yan, Ruilin Yang, Jian Ma 0001. 2049-2056 [doi]
• Part-based Collaborative Spatio-temporal Feature Learning for Cloth-changing Gait RecognitionLingxiang Yao, Worapan Kusakunniran, Qiang Wu, Jian Zhang, Jingsong Xu. 2057-2064 [doi]
• Disentangle, Assemble, and Synthesize: Unsupervised Learning to Disentangle Appearance and LocationHiroaki Aizawa, Hirokatsu Kataoka, Yutaka Satoh, Kunihito Kato. 2065-2072 [doi]
• PCANet: Pyramid Context-aware Network for Retinal Vessel SegmentationYi Zhang, Yixuan Chen 0007, Kai Zhang 0012. 2073-2080 [doi]
• Removing Raindrops from a Single Image using Synthetic DataYoshihito Kokubo, Shusaku Asada, Hirotaka Maruyama, Masaru Koide, Kohei Yamamoto, Yoshihisa Suetsugu. 2081-2088 [doi]
• ACCLVOS: Atrous Convolution with Spatial-Temporal ConvLSTM for Video Object SegmentationMuzhou Xu, Shan Zhong, Chunping Liu, Shengrong Gong, Zhaohui Wang, Yu Xia. 2089-2096 [doi]
• DualBox: Generating BBox Pair with Strong Correspondence via Occlusion Pattern Clustering and Proposal RefinementZheng Ge, Chuyu Hu, Xin Huang, Baiqiao Qiu, Osamu Yoshie. 2097-2102 [doi]
• Adaptive Word Embedding Module for Semantic Reasoning in Large-scale DetectionYu Zhang, Xiaoyu Wu, Ruolin Zhu. 2103-2109 [doi]
• A Comparison of Neural Network Approaches for Melanoma ClassificationMaria Frasca, Michele Nappi, Michele Risi, Genoveffa Tortora, Alessia Auriemma Citarella. 2110-2117 [doi]
• AdaFilter: Adaptive Filter Design with Local Image Basis Decomposition for Optimizing Image Recognition PreprocessingAiga Suzuki, Keiichi Ito, Takahide Ibe, Nobuyuki Otsu. 2118-2125 [doi]
• Face Anti-Spoofing Using Spatial Pyramid PoolingLei Shi, Zhuo Zhou, Zhenhua Guo. 2126-2133 [doi]
• Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural NetworksMélodie Boillet, Christopher Kermorvant, Thierry Paquet. 2134-2141 [doi]
• Ballroom Dance Recognition from Audio RecordingsTomás Pavlín, Jan Cech, Jiri Matas. 2142-2149 [doi]
• Low-Cost Lipschitz-Independent Adaptive Importance Sampling of Stochastic GradientsHuikang Liu, Xiaolu Wang, Jiajin Li, Anthony Man-Cho So. 2150-2157 [doi]
• Feature Pyramid Hierarchies for Multi-scale Temporal Action DetectionJiayu He, Guohui Li, Jun Lei. 2158-2165 [doi]
• Dual Loss for Manga Character Recognition with Imbalanced Training DataYonggang Li, Yafeng Zhou, Yongtao Wang, Xiaoran Qin, Zhi Tang. 2166-2171 [doi]
• Parallel Network to Learn Novelty from the KnownShuaiyuan Du, Chaoyi Hong, Zhiyu Pan, Chen Feng, Zhiguo Cao. 2172-2179 [doi]
• Rethinking Experience Replay: a Bag of Tricks for Continual LearningPietro Buzzega, Matteo Boschini, Angelo Porrello, Simone Calderara. 2180-2187 [doi]
• Person Recognition with HGR Maximal Correlation on Multimodal DataYihua Liang, Fei Ma, Yang Li, Shao-Lun Huang. 2188-2195 [doi]
• Variational Deep Embedding Clustering by Augmented Mutual Information MaximizationQiang Ji, Yanfeng Sun, Yongli Hu, Baocai Yin. 2196-2202 [doi]
• A Novel Region of Interest Extraction Layer for Instance SegmentationLeonardo Rossi, Akbar Karimi, Andrea Prati 0001. 2203-2209 [doi]
• Detection and Correspondence Matching of Corneal Reflections for Eye Tracking Using Deep LearningSoumil Chugh, Braiden Brousseau, Jonathan Rose, Moshe Eizenman. 2210-2217 [doi]
• Siamese Fully Convolutional Tracker with Motion CorrectionMathew Francis, Prithwijit Guha. 2218-2225 [doi]
• S2I-Bird: Sound-to-Image Generation of Bird Species using Generative Adversarial NetworksJooyong Shim, Joongheon Kim, Jong-Kook Kim. 2226-2232 [doi]
• Modulation Pattern Detection Using Complex Convolutions in Deep LearningJakob Krzyston, Rajib Bhattacharjea, Andrew Stark. 2233-2239 [doi]
• Responsive Social Smile: A Machine Learning based Multimodal Behavior Assessment Framework towards Early Stage Autism ScreeningYueran Pan, Kunjing Cai, Ming Cheng, Xiaobing Zou, Ming Li. 2240-2247 [doi]
• Hierarchically Aggregated Residual Transformation for Single Image Super ResolutionZejiang Hou, Sun-Yuan Kung. 2248-2255 [doi]
• Label Self-Adaption Hashing for Image RetrievalJianglin Lu, Zhihui Lai, Jingxu Lin, Qinghong Lin, Jie Zhou 0009. 2256-2263 [doi]
• Fast and Accurate Real-Time Semantic Segmentation with Dilated Asymmetric ConvolutionsLeonel Rosas-Arias, Gibran Benitez-Garcia, José Portillo-Portillo, Gabriel Sánchez-Pérez, Keiji Yanai. 2264-2271 [doi]
• Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged NetworksYoshitomo Matsubara, Marco Levorato. 2272-2279 [doi]
• Self-Selective Context for Interaction RecognitionMert Kilickaya, Noureldien Hussein, Efstratios Gavves, Arnold W. M. Smeulders. 2280-2287 [doi]
• Teacher-Student Training and Triplet Loss for Facial Expression Recognition under OcclusionMariana-Iuliana Georgescu, Radu-Tudor Ionescu. 2288-2295 [doi]
• Map-Based Temporally Consistent Geolocalization through Learning Motion TrajectoriesBing Zha, Alper Yilmaz. 2296-2303 [doi]
• Unsupervised deep learning for text line segmentationBerat Kurar Barakat, Ahmad Droby, Reem Alaasam, Boraq Madi, Irina Rabaev, Raed Shammes, Jihad El-Sana. 2304-2311 [doi]
• The eXPose Approach to Crosslier DetectionAntónio Pereira Barata, Frank W. Takes, H. Jaap van den Herik, Cor J. Veenman. 2312-2319 [doi]
• RefiNet: 3D Human Pose Refinement with Depth MapsAndrea D'Eusanio, Stefano Pini, Guido Borghi, Roberto Vezzani, Rita Cucchiara. 2320-2327 [doi]
• Fall Detection by Human Pose Estimation and Kinematic TheoryVincenzo Dentamaro, Donato Impedovo, Giuseppe Pirlo. 2328-2335 [doi]
• Aerial Road Segmentation in the Presence of Topological Label NoiseCorentin Henry, Friedrich Fraundorfer, Eleonora Vig. 2336-2343 [doi]
• Generic Document Image Dewarping by Probabilistic Discretization of Vanishing PointsGilles Simon, Salvatore Tabbone. 2344-2351 [doi]
• Hybrid Network For End-To-End Text-Independent Speaker IdentificationWajdi Ghezaiel, Luc Brun, Olivier Lézoray. 2352-2359 [doi]
• Cycle-Consistent Adversarial Networks and Fast Adaptive Bi-dimensional Empirical Mode Decomposition for Style TransferElissavet Batziou, Petros Alvanitopoulos, Konstantinos Ioannidis, Ioannis Patras, Stefanos Vrochidis, Ioannis Kompatsiaris. 2360-2367 [doi]
• Cost-Effective Adversarial Attacks against Scene Text RecognitionMingkun Yang, Haitian Zheng, Xiang Bai, Jiebo Luo. 2368-2374 [doi]
• Adversarially Constrained Interpolation for Unsupervised Domain AdaptationMohamed Azzam, Aurele Tohokantche Gnanha, Hau-San Wong, Si Wu 0002. 2375-2381 [doi]
• Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd CountingPongpisit Thanasutives, Ken-ichi Fukui, Masayuki Numao, Boonserm Kijsirikul. 2382-2389 [doi]
• Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-ResolutionXiaoyu Xiang, Qian Lin, Jan P. Allebach. 2390-2397 [doi]
• 3D Pots Configuration System by Optimizing over Geometric ConstraintsJae Eun Kim, Muhammad Zeeshan Arshad, Yoo Seong Jong, Je-Hyung Hong, Jinwook Kim, Young-Min Kim. 2398-2405 [doi]
• Unsupervised Face Manipulation via HallucinationKeerthy Kusumam, Enrique Sanchez, Georgios Tzimiropoulos. 2406-2413 [doi]
• Classifier Pool Generation based on a Two-level Diversity ApproachMarcos Monteiro, Alceu S. Britto Jr., Jean Paul Barddal, Luiz S. Oliveira, Robert Sabourin. 2414-2421 [doi]
• A Novel Deep-learning Pipeline for Light Field Image Based Material RecognitionYunlong Wang 0003, Kunbo Zhang, Zhenan Sun. 2422-2429 [doi]
• Complex-Object Visual Inspection: Empirical Studies on A Multiple Lighting SolutionMaya Aghaei, Matteo Bustreo, Pietro Morerio, Nicolò Carissimi, Alessio Del Bue, Vittorio Murino. 2430-2437 [doi]
• ISP4ML: The Role of Image Signal Processing in Efficient Deep Learning Vision SystemsPatrick Hansen, Alexey Vilkin, Yury Krustalev, James Imber, Dumidu Talagala, David Hanwell, Matthew Mattina, Paul N. Whatmough. 2438-2445 [doi]
• Automatic Student Network Search for Knowledge DistillationZhexi Zhang, Wei Zhu, Junchi Yan, Peng Gao, Guotong Xie. 2446-2453 [doi]
• AerialMPTNet: Multi-Pedestrian Tracking in Aerial Imagery Using Temporal and Graphical FeaturesMaximilian Kraus, Seyed Majid Azimi, Emec Ercelik, Reza Bahmanyar, Peter Reinartz, Alois C. Knoll. 2454-2461 [doi]
• STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow EstimationPierre Godet, Alexandre Boulch, Aurélien Plyer, Guy Le Besnerais. 2462-2469 [doi]
• Deep Topic Modeling by Multilayer Bootstrap Network and LassoJianyu Wang, Xiao-lei Zhang. 2470-2475 [doi]
• Deep transformation models: Tackling complex regression problems with neural network based transformation modelsBeate Sick, Torsten Hothorn, Oliver Dürr. 2476-2481 [doi]
• FC-DCNN: A densely connected neural network for stereo estimationDominik Hirner, Friedrich Fraundorfer. 2482-2489 [doi]
• A Close Look at Deep Learning with Small DataLorenzo Brigato, Luca Iocchi. 2490-2497 [doi]
• Adaptive Matching of Kernel MeansMiao Cheng, Xinge You. 2498-2505 [doi]
• From Certain to Uncertain: Toward Optimal Solution for Offline Multiple Object TrackingKaikai Zhao, Takashi Imaseki, Hiroshi Mouri, Einoshin Suzuki, Tetsu Matsukawa. 2506-2513 [doi]
• Adaptive Context-Aware Discriminative Correlation Filters for Robust Visual Object TrackingTianyang Xu, Zhen-Hua Feng, Xiao-jun Wu, Josef Kittler. 2514-2520 [doi]
• Accurate Background Subtraction Using Dynamic Object Presence Probability in Sports ScenesRyosuke Watanabe, Jun Chen 0017, Tomoaki Konno, Sei Naito. 2521-2528 [doi]
• Variational Information Bottleneck Model for Accurate Indoor Position RecognitionWeizhu Qian, Franck Gechter. 2529-2535 [doi]
• Audio-Video detection of the active speaker in meetingsFrancisco Madrigal, Frédéric Lerasle, Lionel Pibre, Isabelle Ferrané. 2536-2543 [doi]
• Automatic Estimation of Self-Reported Pain by Interpretable Representations of Motion DynamicsBenjamin Szczapa, Mohamed Daoudi, Stefano Berretti, Pietro Pala, Alberto Del Bimbo, Zakia Hammal. 2544-2550 [doi]
• DAG-Net: Double Attentive Graph Neural Network for Trajectory ForecastingAlessio Monti, Alessia Bertugli, Simone Calderara, Rita Cucchiara. 2551-2558 [doi]
• Active Sampling for Pairwise Comparisons via Approximate Message Passing and Information Gain MaximizationAliaksei Mikhailiuk, Clifford Wilmot, María Pérez-Ortiz 0001, Dingcheng Yue, Rafal K. Mantiuk. 2559-2566 [doi]
• Recursive Convolutional Neural Networks for EpigenomicsAikaterini Symeonidi, Anguelos Nicolaou, Frank Johannes, Vincent Christlein. 2567-2574 [doi]
• DE-Net: Dilated Encoder Network for Automated Tongue SegmentationHui Tang, Bin Wang 0041, Jun Zhou 0001, Yongsheng Gao. 2575-2581 [doi]
• DID: A Nested Dense in Dense Structure with Variable Local Dense Blocks for Super-Resolution Image ReconstructionLongxi Li, Hesen Feng, Bing Zheng, Lihong Ma 0002, Jing Tian 0002. 2582-2589 [doi]
• An Adaptive Video-to-Video Face Identification System Based on Self-TrainingEric López-López, Carlos V. Regueiro, Xosé M. Pardo. 2590-2596 [doi]
• LFIR2Pose: Pose Estimation from an Extremely Low-resolution FIR image SequenceSaki Iwata, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Tomoyoshi Aizawa. 2597-2603 [doi]
• Using Meta Labels for the Training of Weighting Models in a Sample-Specific Late Fusion Classification ArchitecturePeter Bellmann, Patrick Thiam, Friedhelm Schwenker. 2604-2611 [doi]
• Human or Machine? It Is Not What You Write, But How You Write ItLuis A. Leiva, Moisés Díaz, Miguel A. Ferrer, Réjean Plamondon. 2612-2619 [doi]
• Image Sequence Based Cyclist Action Recognition Using Multi-Stream 3D ConvolutionStefan Zernetsch, Steven Schreck, Viktor Kress, Konrad Doll, Bernhard Sick. 2620-2626 [doi]
• Object Detection in the DCT Domain: is Luminance the Solution?Benjamin Deguerre, Clément Chatelain 0001, Gilles Gasso. 2627-2634 [doi]
• Estimation of Abundance and Distribution of Salt Marsh Plants from Images Using Deep LearningJ. Parashar, Suchendra M. Bhandarkar, J. Simon, Brian M. Hopkinson, S. C. Pennings. 2635-2642 [doi]
• Fusion of Global-Local Features for Image Quality Inspection of Shipping LabelSungho Suh, Paul Lukowicz, Yong Oh Lee. 2643-2649 [doi]
• Generalized Shortest Path-based Superpixels for Accurate Segmentation of Spherical ImagesRémi Giraud, Rodrigo Borba Pinheiro, Yannick Berthoumieu. 2650-2656 [doi]
• OmniFlowNet: a Perspective Neural Network Adaptation for Optical Flow Estimation in Omnidirectional ImagesCharles-Olivier Artizzu, Haozhou Zhang, Guillaume Allibert, Cédric Demonceaux. 2657-2662 [doi]
• Emerging Relation Network and Task Embedding for Multi-Task Regression ProblemsJens Schreiber, Bernhard Sick. 2663-2670 [doi]
• MaxDropout: Deep Neural Network Regularization Based on Maximum Output ValuesClaudio Filipi Goncalves dos Santos, Danilo Colombo, Mateus Roder, João Paulo Papa. 2671-2676 [doi]
• Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning ApproachXian Zhong, Cheng Gu, Wenxin Huang, Lin Li, Shuqin Chen, Chia-Wen Lin. 2677-2684 [doi]
• Model Decay in Long-Term TrackingEfstratios Gavves, Ran Tao 0004, Deepak K. Gupta, Arnold W. M. Smeulders. 2685-2692 [doi]
• Few-Shot Few-Shot Learning and the role of Spatial AttentionYann Lifchitz, Yannis Avrithis, Sylvaine Picard. 2693-2700 [doi]
• Countering Anti-forensics of SIFT-based Copy-Move DetectionMuhammad Salman, Andreas Uhl. 2701-2707 [doi]
• Deep Convolutional Embedding for Digitized Painting ClusteringGiovanna Castellano, Gennaro Vessio. 2708-2715 [doi]
• Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card GamePablo V. A. Barros, Ana Tanevska, Alessandra Sciutti. 2716-2723 [doi]
• Revisiting the Training of Very Deep Neural Networks without Skip ConnectionsOyebade K. Oyedotun, Abd El Rahman Shabayek, Djamila Aouada, Björn E. Ottersten. 2724-2731 [doi]
• Deep Top-rank Counter Metric for Person Re-identificationChen Chen 0036, Hao Dou, Xiyuan Hu, Silong Peng. 2732-2739 [doi]
• Deep Ordinal Regression with Label DiversityAxel Berg, Magnus Oskarsson, Mark O'Connor. 2740-2747 [doi]
• P ≈ NP, at least in Visual Question AnsweringShailza Jolly, Sebastian Palacio, Joachim Folz, Federico Raue, Jörn Hees, Andreas Dengel 0001. 2748-2754 [doi]
• Light3DPose: Real-time Multi-Person 3D Pose Estimation from Multiple ViewsAlessio Elmi, Davide Mazzini, Pietro Tortella. 2755-2762 [doi]
• Ground-truthing Large Human Behavior Monitoring DatasetsTehreem Qasim, Robert B. Fisher, Naeem Bhatti. 2763-2770 [doi]
• A Two-Stream Recurrent Network for Skeleton-based Human Interaction RecognitionQianhui Men, Edmond S. L. Ho, Hubert P. H. Shum, Howard Leung. 2771-2778 [doi]
• Learning To Find Good Correspondences Of Multiple ObjectsYouye Xie, Yingheng Tang, Gongguo Tang, William A. Hoff. 2779-2786 [doi]
• A cheaper Rectified-Nearest-Feature-Line-Segment classifier based on safe pointsMauricio Orozco-Alzate, Manuele Bicego. 2787-2794 [doi]
• Progressive Gradient Pruning for Classification, Detection and Domain AdaptationLe Thanh Nguyen-Meidine, Eric Granger, Madhu Kiran, Marco Pedersoli, Louis-Antoine Blais-Morin. 2795-2802 [doi]
• An Empirical Bayes Approach to Topic ModelingAnirban Gangopadhyay. 2803-2808 [doi]
• Global Feature Aggregation for Accident AnticipationMishal Fatima, Muhammad Umar Karim Khan, Chong-Min Kyung. 2809-2816 [doi]
• Detecting Manipulated Facial Videos: A Time Series SolutionZhewei Zhang, Can Mal, Bowen Ding, Meilin Gao. 2817-2823 [doi]
• Task-based Focal Loss for Adversarially Robust Meta-LearningYufan Hou, Lixin Zou, Weidong Liu 0001. 2824-2829 [doi]
• On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network ArchitecturesMatt Poyser, Amir Atapour Abarghouei, Toby P. Breckon. 2830-2837 [doi]
• Aggregating Object Features Based on Attention Weights for Fine-Grained Image RetrievalHongli Lin, Yongqi Song, Zixuan Zeng, Weisheng Wang, Jiayi Wang. 2838-2844 [doi]
• Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-TrainingTeo Spadotto, Marco Toldo, Umberto Michieli, Pietro Zanuttigh. 2845-2852 [doi]
• Electroencephalography signal processing based on textural features for monitoring the driver's state by a Brain-Computer InterfaceGiulia Orrù, Marco Micheletto, Fabio Terranova, Gian Luca Marcialis. 2853-2860 [doi]
• Constrained Spectral Clustering Network with Self-TrainingXinyue Liu, Shichong Yang, Linlin Zong. 2861-2866 [doi]
• A General Model for Learning Node and Graph Representations JointlyChaofan Chen. 2867-2873 [doi]
• MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM)Omniah H. Nagoor, J. Whittle, J. Deng, Benjamin Mora, Mark W. Jones. 2874-2881 [doi]
• Moto: Enhancing Embedding with Multiple Joint Factors for Chinese Text ClassificationXunzhu Tang, Rujie Zhu, Tiezhu Sun, Shi Wang. 2882-2888 [doi]
• CKG: Dynamic Representation Based on Context and Knowledge GraphXunzhu Tang, Tiezhu Sun, Rujie Zhu, Shi Wang. 2889-2895 [doi]
• Motion Segmentation with Pairwise Matches and Unknown Number of MotionsFederica Arrigoni, Luca Magri, Tomás Pajdla. 2896-2903 [doi]
• Breast Anatomy Enriched Tumor Saliency EstimationFei Xu, Yingtao Zhang, Heng-Da Cheng, Jianrui Ding, Boyu Zhang, Chunping Ning, Ying Wang. 2904-2911 [doi]
• Automatic Detection of Stationary Waves in the Venus Atmosphere Using Deep Generative ModelsMinori Narita, Daiki Kimura, Takeshi Imamura. 2912-2919 [doi]
• Fast and Efficient Neural Network for Light Field Disparity EstimationDizhi Ma, Andrew Lumsdaine. 2920-2926 [doi]
• PoseCVAE: Anomalous Human Activity DetectionYashswi Jain, Ashvini Kumar Sharma, Rajbabu Velmurugan, Biplab Banerjee. 2927-2934 [doi]
• Edge-Aware Monocular Dense Depth Estimation with MorphologyZhi Li, Xiaoyang Zhu, Haitao Yu 0012, Qi Zhang, Yongshi Jiang. 2935-2942 [doi]
• Stroke Based Posterior Attention for Online Handwritten Mathematical Expression RecognitionChangjie Wu, Qing Wang, Jianshu Zhang, Jun Du, Jia-Ming Wang, Jiajia Wu, Jin-Shui Hu. 2943-2949 [doi]
• PIN: A Novel Parallel Interactive Network for Spoken Language UnderstandingPeilin Zhou, Zhiqi Huang, Fenglin Liu, Yuexian Zou. 2950-2957 [doi]
• SIDGAN: Single Image Dehazing without Paired SupervisionPan Wei, Xin Wang, Lei Wang, Ji Xiang. 2958-2965 [doi]
• An Adaptive Model for Face Distortion CorrectionDuong Hai Nguyen, Tien D. Bui. 2966-2971 [doi]
• Feature Extraction by Joint Robust Discriminant Analysis and Inter-class SparsityFadi Dornaika, A. Khoder. 2972-2979 [doi]
• Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-IdentificationRodolfo Quispe, Hélio Pedrini. 2980-2987 [doi]
• 6D Pose Estimation with Correlation FusionYi Cheng, Hongyuan Zhu, Ying Sun, Cihan Acar, Wei Jing, Yan Wu, Liyuan Li, Cheston Tan, Joo-Hwee Lim. 2988-2994 [doi]
• Predicting Online Video Advertising Effects with Multimodal Deep LearningJun Ikeda, Hiroyuki Seshime, Xueting Wang, Toshihiko Yamasaki. 2995-3002 [doi]
• Face Image Quality Assessment for Model and Human PerceptionKen Chen, Yichao Wu, Zhenmao Li, Yudong Wu, Ding Liang. 3003-3010 [doi]
• An Accurate Threshold Insensitive Kernel Detector for Arbitrary Shaped TextXijun Qian, Yifan Liu, Yubin Yang. 3011-3018 [doi]
• Smart Inference for Multidigit Convolutional Neural Network based Barcode DecodingThao Do, Yalew Tolcha, Tae Joon Jun, Daeyoung Kim 0001. 3019-3026 [doi]
• Cross-People Mobile-Phone Based Airwriting Character RecognitionYunzhe Li, Hui Zheng, He Zhu, Haojun Ai, XiaoWei Dong. 3027-3033 [doi]
• The color out of space: learning self-supervised representations for Earth Observation imageryStefano Vincenzi, Angelo Porrello, Pietro Buzzega, Marco Cipriano, Pietro Fronte, Roberto Cuccu, Carla Ippoliti, Annamaria Conte, Simone Calderara. 3034-3041 [doi]
• Fixed simplex coordinates for angular margin loss in CapsNetRita Pucci, Christian Micheloni, Gian Luca Foresti, Niki Martinel. 3042-3049 [doi]
• Digit Recognition Applied to Reconstructed Audio Signals Using Deep LearningAnastasia-Sotiria Toufa, Constantine Kotropoulos. 3050-3057 [doi]
• A Globally Optimal Method for the PnP Problem with MRP Rotation ParameterizationManolis I. A. Lourakis, George Terzakis. 3058-3063 [doi]
• Hybrid Decomposition Convolution Neural Network and Vocabulary Forest for Image RetrievalYoucef Djenouri, Jon M. Hjelmervik. 3064-3070 [doi]
• Second-order Attention Guided Convolutional Activations for Visual RecognitionShannan Chen, Qian Wang, Qiule Sun, Bin Liu, Jianxin Zhang, Qiang Zhang. 3071-3076 [doi]
• Attentional Wavelet Network for Traditional Chinese Painting TransferRui Wang, Huaibo Huang, Aihua Zheng, Ran He. 3077-3083 [doi]
• The effect of image enhancement algorithms on convolutional neural networksJosé A. Rodríguez-Rodríguez, Miguel A. Molina-Cabello, Rafaela Benítez-Rochel, Ezequiel López-Rubio. 3084-3089 [doi]
• Neuron-based Network Pruning Based on Majority VotingAli Alqahtani, Xianghua Xie, Ehab Essa, Mark W. Jones. 3090-3097 [doi]
• Machine-learned Regularization and Polygonization of Building Segmentation MasksStefano Zorzi, Ksenia Bittner, Friedrich Fraundorfer. 3098-3105 [doi]
• Adaptive estimation of optimal color transformations for deep convolutional network based homography estimationMiguel A. Molina-Cabello, Jorge García-González, Rafael Marcos Luque Baena, Karl Thurnhofer-Hemsi, Ezequiel López-Rubio. 3106-3113 [doi]
• On Identification and Retrieval of Near-Duplicate Biological Images: a New Dataset and ProtocolT. E. Koker, S. S. Chintapalli, S. Wang, B. A. Talbot, D. Wainstock, Marcelo Cicconet, M. C. Walsh. 3114-3121 [doi]
• Cross-Lingual Text Image Recognition via Multi-Task Sequence to Sequence LearningZhuo Chen, Fei Yin, Xu-Yao Zhang, Qing Yang, Chena-Lin Liu. 3122-3129 [doi]
• Stratified Multi-Task Learning for Robust Spotting of Scene TextsKinjal Dasgupta, Sudip Das, Ujjwal Bhattacharya. 3130-3137 [doi]
• Recursive Recognition of Offline Handwritten Mathematical ExpressionsMarco Cotogni, Claudio Cusano, Antonino Nocera. 3138-3145 [doi]
• Predicting Chemical Properties using Self-Attention Multi-task Learning based on SMILES RepresentationSangrak Lim, Yong Oh Lee. 3146-3153 [doi]
• Anime Sketch Colorization by Component-based Matching using Deep Appearance Features and Graph RepresentationThien Do, Van Pham, Anh Nguyen, Trung D. Q. Dang, Quoc Nguyen, Bach Hoang, Giao Nguyen. 3154-3161 [doi]
• Textual-Content-Based Classification of Bundles of Untranscribed Manuscript ImagesJosé Ramón Prieto, Vicente Bosch, Enrique Vidal 0001, Carlos Alonso, M. Carmen Orcero, Lourdes Márquez. 3162-3169 [doi]
• Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City MazeDongfang Liu, Yiming Cui, Xiaolei Guo, Wei Ding, Baijian Yang, Yingjie Chen. 3170-3177 [doi]
• A GAN-based Blind Inpainting Method for Masonry Wall ImagesYahya Ibrahim, Balázs Nagy, Csaba Benedek. 3178-3185 [doi]
• Do We Really Need Scene-specific Pose Encoders?Yoli Shavit, Ron Ferens. 3186-3192 [doi]
• CardioGAN: An Attention-based Generative Adversarial Network for Generation of ElectrocardiogramsSubhrajyoti Dasgupta, Sudip Das, Ujjwal Bhattacharya. 3193-3200 [doi]
• Unsupervised Moving Object Detection through Background Models for PTZ CameraKimin Yun, Hyungil Kim, Kangmin Bae, Jongyoul Park. 3201-3208 [doi]
• Enhanced Feature Pyramid Network for Semantic SegmentationMucong Ye, Jingpeng Ouyang, Ge Chen, Jing Zhang, Xiaogang Yu. 3209-3216 [doi]
• Extracting and Interpreting Unknown Factors with Classifier for Foot Strike Types in RunningChanjin Seo, Masato Sabanai, Yuta Goto, Koji Tagami, Hiroyuki Ogata, Kazuyuki Kanosue, Jun Ohya. 3217-3224 [doi]
• A Self-supervised GAN for Unsupervised Few-shot Object RecognitionKhoi Nguyen, Sinisa Todorovic. 3225-3231 [doi]
• Robust Lexicon-Free Confidence Prediction for Text RecognitionQi Song, Qianyi Jiang, Rui Zhang, Xiaolin Wei. 3232-3239 [doi]
• Single Image Super-Resolution with Dynamic Residual ConnectionKaram Park, Jae Woong Soh, Nam Ik Cho. 3240-3247 [doi]
• Efficient-Receptive Field Block with Group Spatial Attention Mechanism for Object DetectionJiacheng Zhang, Zhicheng Zhao, Fei Su. 3248-3255 [doi]
• A Deep Learning-Based Method for Predicting Volumes of Nasopharyngeal Carcinoma for Adaptive Radiation Therapy TreatmentBilel Daoud, Ken'ichi Morooka, Shoko Miyauchi, Ryo Kurazume, Wafa Mnejja, Leila Farhat, Jamel Daoud. 3256-3263 [doi]
• Learning Sign-Constrained Support Vector MachinesKenya Tajima, Kohei Tsuchida, Esmeraldo Ronnie Rey Zara, Naoya Ohta, Tsuyoshi Kato. 3264-3271 [doi]
• Manual-Label Free 3D Detection via An Open-Source SimulatorZhen Yang, Chi Zhang, Huiming Guo, Zhaoxiang Zhang. 3272-3279 [doi]
• Object Detection Using Dual Graph NetworkShengjia Chen, Zhixin Li, Feicheng Huang, Canlong Zhang, Huifang Ma. 3280-3287 [doi]
• Factor Screening using Bayesian Active Learning and Gaussian Process Meta-ModellingCheng Li 0003, Santu Rana, Andrew Gill, Dang Nguyen, Sunil Gupta 0001, Svetha Venkatesh. 3288-3295 [doi]
• Late Fusion of Bayesian and Convolutional Models for Action RecognitionCamille Maurice, Francisco Madrigal, Frédéric Lerasle. 3296-3303 [doi]
• Explainable Online Validation of Machine Learning Models for Practical ApplicationsWolfgang Fuhl, Yao Rong, Thomas Motz, Michael Scheidt, Andreas Hartel, Andreas Koch, Enkelejda Kasneci. 3304-3311 [doi]
• Knowledge Distillation for Action Anticipation via Label SmoothingGuglielmo Camporese, Pasquale Coscia, Antonino Furnari, Giovanni Maria Farinella, Lamberto Ballan. 3312-3319 [doi]
• Conditional Multi-Task learning for Plant Disease IdentificationSue Han Lee, Hervé Goëau, Pierre Bonnet, Alexis Joly. 3320-3327 [doi]
• Gaussian Constrained Attention Network for Scene Text RecognitionZhi Qiao, Xugong Qin, Yu Zhou 0015, Fei Yang, Weiping Wang 0005. 3328-3335 [doi]
• Unconstrained Facial Expression Recogniton Based on Cascade Decision and Gabor FiltersYanhong Wu, Lijie Zhang, Guannan Chen, Pablo Navarrete Michelini. 3336-3341 [doi]
• How Does DCNN Make Decisions ?Yi Lin, Namin Wang, Xiaoqing Ma, Ziwei Li, Gang Bai. 3342-3349 [doi]
• Augmentation of Small Training Data Using GANs for Enhancing the Performance of Image ClassificationShih-Kai Hung, John Q. Gan. 3350-3356 [doi]
• Semantic Segmentation of Breast Ultrasound Image with Pyramid Fuzzy Uncertainty Reduction and Direction Connectedness FeatureKuan Huang, Yingtao Zhang, H. D. Cheng, Ping Xing, Boyu Zhang. 3357-3364 [doi]
• Sample-Dependent Distance for 1: N Identification via Discriminative Feature SelectionNaoki Kawamura, Susumu Kubota. 3365-3371 [doi]
• Evaluating Initialization of Nelder-Mead Method for Hyperparameter Optimization in Deep LearningShintaro Takenaga, Shuhei Watanabe, Masahiro Nomura, Yoshihiko Ozaki, Masaki Onishi, Hitoshi Habe. 3372-3379 [doi]
• Three-Dimensional Lip Motion Network for Text-Independent Speaker RecognitionJianrong Wang, Tong Wu, Shanyu Wang, Mei Yu, Qiang Fang, Ju Zhang 0001, Li Liu. 3380-3387 [doi]
• Context-Aware Residual Module for Image ClassificationJing Bai, Ran Chen. 3388-3395 [doi]
• Comparison of deep learning and hand crafted features for mining simulation dataTheodoros Georgiou 0001, Sebastian Schmitt, Thomas Bäck, Nan Pu, Wei Chen 0072, Michael S. Lew. 3396-3403 [doi]
• Adaptive Sampling of Pareto Frontiers with Binary Constraints Using Regression and ClassificationRaoul Heese, Michael Bortz. 3404-3411 [doi]
• Are spoofs from latent fingerprints a real threat for the best state-of-art liveness detectors?Roberto Casula, Giulia Orrù, Daniele Angioni, Xiaoyi Feng, Gian Luca Marcialis, Fabio Roli. 3412-3418 [doi]
• Anomaly Detection, Localization and Classification for Railway InspectionRiccardo Gasparini, Andrea D'Eusanio, Guido Borghi, Stefano Pini, Giuseppe Scaglione, Simone Calderara, Eugenio Fedeli, Rita Cucchiara. 3419-3426 [doi]
• Understanding when spatial transformer networks do not support invariance, and what to do about itLukas Finnveden, Ylva Jansson, Tony Lindeberg. 3427-3434 [doi]
• A Prototype-Based Generalized Zero-Shot Learning Framework for Hand Gesture RecognitionJinting Wu, Yujia Zhang, Xiaoguang Zhao. 3435-3442 [doi]
• Detection of Makeup Presentation Attacks based on Deep Face RepresentationsChristian Rathgeb, Pawel Drozdowski, Christoph Busch 0001. 3443-3450 [doi]
• On learning Random Forests for Random Forest-clusteringManuele Bicego, Francisco Escolano. 3451-3458 [doi]
• Expectation-Maximization for Scheduling Problems in Satellite CommunicationWerner Bailer, Martin Winter, Johannes Ebert, Joel Flavio, Karin Plimon. 3459-3466 [doi]
• GAN-based Gaussian Mixture Model Responsibility LearningWanming Huang, Richard Yida Xu, Shuai Jiang, Xuan Liang, Ian Oppermann. 3467-3474 [doi]
• DSPNet: Deep Learning-Enabled Blind Reduction of Speckle NoiseYuxu Lu, Meifang Yang, Ryan Wen Liu. 3475-3482 [doi]
• Constructing Geographic and Long-term Temporal Graph for Traffic ForecastingYiwen Sun, Yulu Wang, Kun Fu, Zheng Wang, Changshui Zhang, Jieping Ye. 3483-3490 [doi]
• Multi-modal Contextual Graph Neural Network for Text Visual Question AnsweringYaoyuan Liang, Xin Wang, Xuguang Duan, Wenwu Zhu 0001. 3491-3498 [doi]
• Defense Mechanism Against Adversarial Attacks Using Density-based Representation of ImagesYen-Ting Huang, Wen-Hung Liao, Chen-Wei Huang. 3499-3504 [doi]
• Multi-Laplacian GAN with Edge Enhancement for Face Super ResolutionShanlei Ko, Bi-Ru Dai. 3505-3512 [doi]
• 2D Deep Video Capsule Network with Temporal Shift for Action RecognitionThéo Voillemin, Hazem Wannous, Jean-Philippe Vandeborre. 3513-3519 [doi]
• Interactive Style Space of Deep Features and Style InnovationBingqing Guo, Pengwei Hao. 3520-3527 [doi]
• Vesselness Filters: A Survey with Benchmarks Applied to Liver ImagingJonas Lamy, Odyssée Merveille, Bertrand Kerautret, Nicolas Passat, Antoine Vacavant. 3528-3535 [doi]
• Attention Based Multi-Instance Thyroid Cytopathological Diagnosis with Multi-Scale Feature FusionShuhao Qiu, Yao Guo, Chuang Zhu, Wenli Zhou, Huang Chen. 3536-3541 [doi]
• Question-Agnostic Attention for Visual Question AnsweringMoshiur R. Farazi, Salman Khan, Nick Barnes. 3542-3549 [doi]
• 3D Semantic Labeling of Photogrammetry Meshes Based on Active LearningMengqi Rong, Shuhan Shen, Zhanyi Hu. 3550-3557 [doi]
• Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative TeacherBrian Kenji Iwana, Seiichi Uchida. 3558-3565 [doi]
• Learning Emotional-Blinded Face RepresentationsAlejandro Peña, Julian Fiérrez, Aythami Morales, Àgata Lapedriza. 3566-3573 [doi]
• Let's Play Music: Audio-Driven Performance Video GenerationHao Zhu, Yi Li, Feixia Zhu, Aihua Zheng, Ran He. 3574-3581 [doi]
• Incorporating Depth Information into Few-Shot Semantic SegmentationYifei Zhang 0004, Désiré Sidibé, Olivier Morel, Fabrice Mériaudeau. 3582-3588 [doi]
• Cut and Compare: End-to-end Offline Signature Verification NetworkXi Lu, LinLin Huang, Fei Yin. 3589-3596 [doi]
• Improving Visual Relation Detection using Depth MapsSahand Sharifzadeh, Sina Moayed Baharlou, Max Berrendorf, Rajat Koner, Volker Tresp. 3597-3604 [doi]
• MA-LSTM: A Multi-Attention Based LSTM for Complex Pattern ExtractionJingjie Guo, Kelang Tian, Kejiang Ye, Cheng-Zhong Xu 0001. 3605-3611 [doi]
• Inception-based Deep Learning Architecture for Tuberculosis Screening using Chest X-raysDipayan Das 0004, K. C. Santosh, Umapada Pal 0001. 3612-3619 [doi]
• Ordinal Depth Classification Using Region-based Self-attentionMinh-Hieu Phan, Son Lam Phung, Abdesselam Bouzerdoum. 3620-3627 [doi]
• Movement-induced Priors for Deep StereoYuxin Hou, Muhammad Kamran Janjua, Juho Kannala, Arno Solin. 3628-3635 [doi]
• Classification of Intestinal Gland Cell-Graphs Using Graph Neural NetworksLinda Studer, Jannis Wallau, Heather Dawson, Inti Zlobec, Andreas Fischer. 3636-3643 [doi]
• ID documents matching and localization with multi-hypothesis constraintsGuillaume Chiron, Nabil Ghanmi, Ahmad-Montaser Awal. 3644-3651 [doi]
• Attentive Part-aware Networks for Partial Person Re- identificationLijuan Huo, Chunfeng Song, Zhengyi Liu, Zhaoxiang Zhang. 3652-3659 [doi]
• Semantic Bilinear Pooling for Fine-Grained RecognitionXinjie Li, Chun Yang, Song-Lu Chen, Chao Zhu 0003, Xu-Cheng Yin. 3660-3666 [doi]
• Domain Siamese CNNs for Sparse Multispectral Disparity EstimationDavid-Alexandre Beaupré, Guillaume-Alexandre Bilodeau. 3667-3674 [doi]
• GAN-Based Image Deblurring Using DCT DiscriminatorHiroki Tomosada, Takahiro Kudo, Takanori Fujisawa, Masaaki Ikehara. 3675-3681 [doi]
• Talking Face Generation via Learning Semantic and Temporal Synchronous LandmarksAihua Zheng, Feixia Zhu, Hao Zhu, Mandi Luo, Ran He. 3682-3689 [doi]
• Single View Learning in Action RecognitionGaurvi Goyal, Nicoletta Noceti, Francesca Odone. 3690-3697 [doi]
• Local Binary Quaternion Rotation Pattern for colour texture retrievalHela Jebali, Noël Richard, Mohamed Naouai. 3698-3705 [doi]
• First- and Second-Order Sorted Local Binary Pattern Features for Grayscale-Inversion and Rotation Invariant Texture ClassificationTiecheng Song, Yuanjing Han, Jie Feng, Yuanlin Wang, Chenqiang Gao. 3706-3713 [doi]
• A Transformer-based Radical Analysis Network for Chinese Character RecognitionChen Yang, Qing Wang, Jun Du, Jianshu Zhang, Changjie Wu, Jiaming Wang. 3714-3719 [doi]
• InsideBias: Measuring Bias in Deep Networks and Application to Face Gender BiometricsIgnacio Serna, Alejandro Peña, Aythami Morales, Julian Fiérrez. 3720-3727 [doi]
• VSR++: Improving Visual Semantic Reasoning for Fine-Grained Image-Text MatchingHui Yuan, Yan Huang, Dongbo Zhang, Zerui Chen, Wenlong Cheng, Liang Wang. 3728-3735 [doi]
• Low Dimensional State Representation Learning with Reward-shaped PriorsNicolò Botteghi, Ruben Obbink, Daan Geijs, Mannes Poel, Beril Sirmaçek, Christoph Brune, Abeje Y. Mersha, Stefano Stramigioli. 3736-3743 [doi]
• Towards Practical Compressed Video Action Recognition: A Temporal Enhanced Multi-Stream NetworkBing Li, Longteng Kong, Dongming Zhang, Xiuguo Bao, Di Huang 0001, Yunhong Wang. 3744-3750 [doi]
• Feature-Supervised Action Modality TransferFida Mohammad Thoker, Cees G. M. Snoek. 3751-3758 [doi]
• Feature Point Matching in Cross-Spectral Images with Cycle Consistency LearningRyosuke Furuta, Naoaki Noguchi, Xueting Wang, Toshihiko Yamasaki. 3759-3766 [doi]
• Group-wise Feature Orthogonalization and Suppression for GAN based Facial Attribute TranslationZhiwei Wen, Haoqian Wu, Weicheng Xie 0001, LinLin Shen. 3767-3774 [doi]
• A Weak Coupling of Semi-Supervised Learning with Generative Adversarial Networks for Malware ClassificationShuwei Wang, Qiuyun Wang, Zhengwei Jiang, Xuren Wang, Rongqi Jing. 3775-3782 [doi]
• Graph-based image decoding for multiplexed in situ RNA detectionGabriele Partel, Carolina Wählby. 3783-3790 [doi]
• Tiny Object Detection in Aerial ImagesJinwang Wang, Wen Yang, Haowen Guo, Ruixiang Zhang, Gui-Song Xia. 3791-3798 [doi]
• Channel-Wise Dense Connection Graph Convolutional Network for Skeleton-Based Action RecognitionMichael Lao BanTeng, Zhiyong Wu 0001. 3799-3806 [doi]
• Coarse-to-fine Foreground Segmentation based on Co-occurrence Pixel-Block and Spatio-Temporal Attention ModelDong Liang, Xinyu Liu. 3807-3813 [doi]
• Uncertainty-sensitive Activity Recognition: A Reliability Benchmark and the CARING ModelsAlina Roitberg, Monica Haurilet, Manuel Martínez 0001, Rainer Stiefelhagen. 3814-3821 [doi]
• A new geodesic-based feature for characterization of 3D shapes: application to soft tissue organ temporal deformationsKarim Makki, Amine Bohi, Augustin C. Ogier, Marc-Emmanuel Bellemare. 3822-3828 [doi]
• Online Domain Adaptation for Person Re-Identification with a Human in the LoopRita Delussu, Lorenzo Putzu, Giorgio Fumera, Fabio Roli. 3829-3836 [doi]
• Hierarchical Deep Hashing for Fast Large Scale Image RetrievalYongfei Zhang, Cheng Peng, Jingtao Zhang, Xianglong Liu, Shiliang Pu, Changhuai Chen. 3837-3844 [doi]
• Learning to segment clustered amoeboid cells from brightfield microscopy via multi-task learning with adaptive weight selectionRituparna Sarkar, Suvadip Mukherjee, Elisabeth Labruyère, Jean-Christophe Olivo-Marin. 3845-3852 [doi]
• Learning Metric Features for Writer-Independent Signature Verification using Dual Triplet LossQian Wan 0004, Qin Zou 0001. 3853-3859 [doi]
• Recovery of 2D and 3D Layout Information through an Advanced Image Stitching Algorithm using Scanning Electron Microscope ImagesAayush Singla, Bernhard Lippmann, Helmut Graeb. 3860-3867 [doi]
• Speeding-up pruning for Artificial Neural Networks: Introducing Accelerated Iterative Magnitude PruningMarco Zullich, Eric Medvet, Felice Andrea Pellegrino, Alessio Ansuini. 3868-3875 [doi]
• Two-Stage Adaptive Object Scene Flow Using Hybrid CNN-CRF ModelCongcong Li, Haoyu Ma, Qingmin Liao. 3876-3883 [doi]
• Localization and Transformation Reconstruction of Image Regions: An Extended Congruent Triangles ApproachAfra'a Ahmad Alyosef, Christian Elias, Andreas Nürnberger. 3884-3891 [doi]
• Subspace Clustering via Joint Unsupervised Feature SelectionWenhua Dong, Xiao-jun Wu, Hui Li, Zhen-Hua Feng, Josef Kittler. 3892-3898 [doi]
• A Multi-Task Neural Network for Action Recognition with 3D Key-PointsRongxiao Tang, Luyang Wang, Zhenhua Guo 0001. 3899-3906 [doi]
• Signal Generation using 1d Deep Convolutional Generative Adversarial Networks for Fault Diagnosis of Electrical MachinesRussell Sabir, Daniele Rosato, Sven Hartmann, Clemens Gühmann. 3907-3914 [doi]
• Documents Counterfeit Detection Through a Deep Learning ApproachDarwin Saire, Salvatore Tabbone. 3915-3922 [doi]
• GarmentGAN: Photo-realistic Adversarial Fashion TransferAmir Hossein Raffiee, Michael Sollami. 3923-3930 [doi]
• Semantic Segmentation Refinement Using Entropy and Boundary-guided Monte Carlo Sampling and Directed Regional SearchZitang Sun, Sei-ichiro Kamata, Ruojing Wang. 3931-3938 [doi]
• Combining GANs and AutoEncoders for efficient anomaly detectionFabio Carrara, Giuseppe Amato, Luca Brombin, Fabrizio Falchi, Claudio Gennaro. 3939-3946 [doi]
• A Bayesian Approach to Reinforcement Learning of Vision-Based Vehicular ControlZahra Gharaee, Karl Holmquist, Linbo He, Michael Felsberg. 3947-3954 [doi]
• Quantified Facial Temporal-Expressiveness Dynamics for Affect AnalysisMd Taufeeq Uddin, Shaun J. Canavan. 3955-3962 [doi]
• A Simple Domain Shifting Network for Generating Low Quality ImagesGuruprasad M. Hegde, Avinash Nittur Ramesh, Kanchana Vaishnavi Gandikota, Roman Obermaisser, Michael Moeller 0001. 3963-3968 [doi]
• A Multi-head Self-relation Network for Scene Text RecognitionJunwei Zhou, Hongchao Gao, Jiao Dai, Dongqin Liu, Jizhong Han. 3969-3976 [doi]
• A modified Single-Shot multibox Detector for beyond Real-Time Object DetectionGeorgios Orfanidis, Konstantinos Ioannidis, Stefanos Vrochidis, Anastasios Tefas, Ioannis Kompatsiaris. 3977-3984 [doi]
• Progressive Scene Segmentation Based on Self-Attention MechanismYunyi Pan, Yuan Gan, Kun Liu, Yan Zhang. 3985-3992 [doi]
• Walk the Lines: Object Contour Tracing CNN for Contour Completion of ShipsAndré Peter Kelm, Udo Zölzer. 3993-4000 [doi]
• Multi-Task Learning for Calorie Prediction on a Novel Large-Scale Recipe Dataset Enriched with Nutritional InformationRobin Ruede, Verena Heusser, Lukas Frank, Alina Roitberg, Monica Haurilet, Rainer Stiefelhagen. 4001-4008 [doi]
• A Versatile Crack Inspection Portable System based on Classifier Ensemble and Controlled IlluminationMilind G. Padalkar, Carlos Beltrán-González, Matteo Bustreo, Alessio Del Bue, Vittorio Murino. 4009-4016 [doi]
• Uncertainty-Aware Data Augmentation for Food RecognitionEduardo Aguilar 0001, Bhalaji Nagarajan, Rupali Khatun, Marc Bolaños, Petia Radeva. 4017-4024 [doi]
• Self and Channel Attention Network for Person Re-IdentificationAsad Munir, Niki Martinel, Christian Micheloni. 4025-4031 [doi]
• Feature-Dependent Cross-Connections in Multi-Path Neural NetworksDumindu Tissera, Kasun Vithanage, Rukshan Wijesinghe, Kumara Kahatapitiya, Subha Fernando, Ranga Rodrigo. 4032-4039 [doi]
• Iterative Bounding Box Annotation for Object DetectionBishwo Adhikari, Heikki Huttunen. 4040-4046 [doi]
• Investigating and Exploiting Image Resolution for Transfer Learning-based Skin Lesion ClassificationAmirreza Mahbod, Gerald Schaefer, Chunliang Wang, Rupert Ecker, Georg Dorffner, Isabella Ellinger. 4047-4053 [doi]
• Attention Based Pruning for Shift NetworksGhouthi Boukli Hacene, Carlos Lassance, Vincent Gripon, Matthieu Courbariaux, Yoshua Bengio. 4054-4061 [doi]
• An Integrated Approach of Deep Learning and Symbolic Analysis for Digital PDF Table ExtractionMengshi Zhang, Daniel Perelman, Vu Le, Sumit Gulwani. 4062-4069 [doi]
• Relatable Clothing: Detecting Visual Relationships between People and ClothingThomas Truong, Svetlana N. Yanushkevich. 4070-4076 [doi]
• Unsupervised Learning of Facial Landmarks based on Inter-Intra Subject ConsistenciesWeijian Li, Haofu Liao, Shun Miao, Le Lu 0001, Jiebo Luo. 4077-4082 [doi]
• Sparse Network Inversion for Key Instance Detection in Multiple Instance LearningBeomjo Shin, Junsu Cho, Hwanjo Yu, Seungjin Choi. 4083-4090 [doi]
• Inferring Functional Properties from Fluid Dynamics FeaturesAndrea Schillaci, Maurizio Quadrio, Carlotta Pipolo, Marcello Restelli, Giacomo Boracchi. 4091-4098 [doi]
• A generalizable saliency map-based interpretation of model outcomeShailja Thakur, Sebastian Fischmeister. 4099-4106 [doi]
• EEG-Based Cognitive State Assessment Using Deep Ensemble Model and Filter Bank Common Spatial PatternDebashis Das Chakladar, Shubhashis Dey, Partha Pratim Roy 0001, Masakazu Iwamura. 4107-4114 [doi]
• Dynamically Mitigating Data Discrepancy with Balanced Focal Loss for Replay Attack DetectionYongqiang Dou, Haocheng Yang, Maolin Yang, Yanyan Xu, Dengfeng Ke. 4115-4122 [doi]
• Robust Visual Object Tracking with Two-Stream Residual Convolutional NetworksNing Zhang, Jingen Liu, Ke Wang, Dan Zeng 0001, Tao Mei 0001. 4123-4130 [doi]
• Feature Representation Learning for Calving Detection of Cows Using Video FramesRyosuke Hyodo, Teppei Nakano, Tetsuji Ogawa. 4131-4136 [doi]
• Dynamic Multi-path Neural NetworkYingcheng Su, Yichao Wu, Ken Chen, Ding Liang, Xiaolin Hu. 4137-4144 [doi]
• Learning Neural Textual Representations for Citation RecommendationBinh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi. 4145-4152 [doi]
• RSINet: Rotation-Scale Invariant Network for Online Visual TrackingYang Fang, Geun Sik Jo, Chang Hee Lee. 4153-4160 [doi]
• Meta Learning via Learned LossSarah Bechtle, Artem Molchanov, Yevgen Chebotar, Edward Grefenstette, Ludovic Righetti, Gaurav S. Sukhatme, Franziska Meier. 4161-4168 [doi]
• Angus Cattle Recognition Using Deep LearningShunnan Chen, Sen Wang, Xinxin Zuo, Ruigang Yang. 4169-4175 [doi]
• Self-supervised Learning for Astronomical Image ClassificationAna Martinazzo, Mateus Espadoto, Nina S. T. Hirata. 4176-4182 [doi]
• RWF-2000: An Open Large Scale Video Database for Violence DetectionMing Cheng, Kunjing Cai, Ming Li. 4183-4190 [doi]
• Radical Counter Network for Robust Chinese Character RecognitionYunqing Li, Yixing Zhu, Jun Du, Changjie Wu, Jianshu Zhang. 4191-4197 [doi]
• Graph Convolutional Neural Networks for Power Line Outage IdentificationJia He, Maggie X. Cheng. 4198-4205 [doi]
• Exemplar Guided Cross-Spectral Face Hallucination via Mutual Information DisentanglementHaoxue Wu, Huaibo Huang, Aijing Yu, Jie Cao 0002, Zhen Lei, Ran He. 4206-4212 [doi]
• Efficient Game-Theoretic Hypergraph MatchingJian Hou 0012, Nai-Ming Qi. 4213-4220 [doi]
• Face Anti-Spoofing Based on Dynamic Color Texture Analysis Using Local Directional Number PatternJunwei Zhou, Ke Shu, Peng Liu, Jianwen Xiang, Shengwu Xiong. 4221-4228 [doi]
• Dual-attention Guided Dropblock Module for Weakly Supervised Object LocalizationJunhui Yin, Siqing Zhang, Dongliang Chang, Zhanyu Ma, Jun Guo 0002. 4229-4236 [doi]
• Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security VideosMamshad Nayeem Rizve, Ugur Demir, Praveen Tirupattur, Aayush Jung Rana, Kevin Duarte, Ishan R. Dave, Yogesh Singh Rawat, Mubarak Shah. 4237-4244 [doi]
• Privacy Attributes-aware Message Passing Neural Network for Visual Privacy Attributes ClassificationHanbin Hong, Wentao Bao, Yuan Hong, Yu Kong. 4245-4251 [doi]
• Text Synopsis Generation for Egocentric VideosAidean Sharghi, Niels da Vitoria Lobo, Mubarak Shah. 4252-4259 [doi]
• Decision Snippet FeaturesPascal Welke, Fouad Alkhoury, Christian Bauckhage, Stefan Wrobel. 4260-4267 [doi]
• Semi-Supervised Outdoor Image Generation Conditioned on Weather SignalsSota Kawakami, Kei Okada, Naoko Nitta, Kazuaki Nakamura, Noboru Babaguchi. 4268-4275 [doi]
• Recurrent Deep Attention Network for Person Re-IdentificationChanghao Wang, Jun Zhou, Xianfei Duan, Guanwen Zhang, Wei Zhou. 4276-4281 [doi]
• Continuous Learning of Face Attribute SynthesisXin-ning, Weijun Li, Xiaoli Dong, Shaohui Xu, Fangzhe Nan, Yuanzhou Yao. 4282-4289 [doi]
• Scientific Document Summarization using Citation Context and Multi-objective OptimizationNaveen Saini, Sushil Kumar, Sriparna Saha 0001, Pushpak Bhattacharyya. 4290-4295 [doi]
• Applying (3+2+1)D Residual Neural Network with Frame Selection for Hong Kong Sign Language RecognitionZhenxing Zhou, King-Shan Lui, Vincent W. L. Tam, Edmund Y. Lam. 4296-4302 [doi]
• Flow-guided Spatial Attention Tracking for Egocentric Activity RecognitionTianshan Liu, Kin-Man Lam. 4303-4308 [doi]
• A Cross Domain Multi-modal Dataset for Robust Face Anti-spoofingQiaobin Ji, Shugong Xu, Xudong Chen, Shunqing Zhang, Shan Cao. 4309-4316 [doi]
• Multi-focus Image Fusion for Confocal Microscopy Using U-Net Regression MapMd Maruf Hossain Shuvo, Yasmin M. Kassim, Filiz Bunyak, Olga V. Glinskii, Leike Xie, Vladislav V. Glinsky, Virginia H. Huxley, Mahesh M. Thakkar, Kannappan Palaniappan. 4317-4323 [doi]
• Dual Path Multi-Modal High-Order Features for Textual Content based Visual Question AnsweringYanan Li 0002, Yuetan Lin, Honghui Zhao, Donghui Wang. 4324-4331 [doi]
• Neural Machine Registration for Motion Correction in Breast DCE-MRIFederica Aprea, Stefano Marrone 0002, Carlo Sansone. 4332-4339 [doi]
• IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture RecognitionGibran Benitez-Garcia, Jesus Olivares-Mercado, Gabriel Sanchez-Perez, Keiji Yanai. 4340-4347 [doi]
• Nonlinear Ranking Loss on Riemannian Potato EmbeddingByung Hyung Kim, Yoon-Je Suh, Honggu Lee, Sungho Jo. 4348-4355 [doi]
• Crowdsourced Verification for Operating Calving Surveillance Systems at an Early StageYusuke Okimoto, Soshi Kawata, Susumu Saito, Teppei Nakano, Tetsuji Ogawa. 4356-4362 [doi]
• PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional NetworksWenwen Yu, Ning Lu, Xianbiao Qi, Ping Gong, Rong Xiao 0003. 4363-4370 [doi]
• TSMSAN: A Three-Stream Multi-Scale Attentive Network for Video Saliency DetectionJingwen Yang, Guanwen Zhang, Jiaming Yan, Wei Zhou. 4371-4376 [doi]
• Towards Low-Bit Quantization of Deep Neural Networks with Limited DataYong Yuan, Chen Chen 0036, Xiyuan Hu, Silong Peng. 4377-4384 [doi]
• Generic Merging of Structure from Motion Maps with a Low Memory FootprintGabrielle Flood, David Gillsjö, Patrik Persson, Anders Heyden, Kalle Åström. 4385-4392 [doi]
• Investigation of DNN Model Robustness Using Heterogeneous DatasetsWen-Hung Liao, Yen-Ting Huang. 4393-4397 [doi]