Table of Contents

• Integrating Domain Knowledge: Using Hierarchies to Improve Deep ClassifiersClemens-Alexander Brust, Joachim Denzler. 3-16 [doi]
• Label-Smooth Learning for Fine-Grained Visual CategorizationXianjie Mo, Tingting Wei, Hengmin Zhang, Qiong Huang, Wei Luo. 17-31 [doi]
• ForestNet - Automatic Design of Sparse Multilayer Perceptron Network Architectures Using Ensembles of Randomized TreesDalia Rodríguez-Salas, Nishant Ravikumar, Mathias Seuret, Andreas Maier 0001. 32-45 [doi]
• Clustering-Based Adaptive Dropout for CNN-Based ClassificationZhiwei Wen, Zhiwei Ke, Weicheng Xie, LinLin Shen. 46-58 [doi]
• Real-Time Detection and Tracking Using Hybrid DNNs and Space-Aware Color Feature: From Algorithm to SystemLiang Feng, Hiroaki Igarashi, Seiya Shibata, Yuki Kobayashi, Takashi Takenaka, Wei Zhang. 61-75 [doi]
• Continuous Motion Numeral Recognition Using RNN Architecture in Air-Writing EnvironmentAdil Rahman, Prasun Roy, Umapada Pal 0001. 76-90 [doi]
• Using Motion Compensation and Matrix Completion Algorithm to Remove Rain Streaks and Snow for Video SequencesYutong Zhou, Nobutaka Shimada. 91-104 [doi]
• Assessing the Impact of Video Compression on Background SubtractionPoonam Beniwal, Pranav Mantini, Shishir K. Shah. 105-118 [doi]
• Learning Motion Regularity for Temporal Video Segmentation and Anomaly DetectionFatima Zohra Daha, Shishir K. Shah. 121-135 [doi]
• A New Forged Handwriting Detection Method Based on Fourier Spectral Density and VariationSayani Kundu, Palaiahnakote Shivakumara, Anaica Grouver, Umapada Pal 0001, Tong Lu, Michael Blumenstein. 136-150 [doi]
• Robust Pedestrian Detection: Faster Deployments with Fusion of ModelsChan-Tong Lam, José Gaspar, Wei Ke, Xu Yang, Sio Kei Im. 151-163 [doi]
• Perceptual Image Anomaly DetectionNina Tuluptceva, Bart Bakker, Irina Fedulova, Anton Konushin 0001. 164-178 [doi]
• Deep Similarity Fusion Networks for One-Shot Semantic SegmentationShuchang Lyu, Guangliang Cheng, Qimin Ding. 181-194 [doi]
• Seeing Things in Random-Dot VideosThomas Dagès, Michael Lindenbaum, Alfred M. Bruckstein. 195-208 [doi]
• Boundary Extraction of Planar Segments from Clouds of Unorganised PointsZezhong Xu, Cheng Qian, Xianju Fei, Yanbin Zhuang, Shibo Xu, Reinhard Klette. 209-222 [doi]
• Real-Time Multi-class Instance Segmentation with One-Time Deep Embedding ClusteringYu-Chi Chen, Chia-Yuan Chang, Pei-Yung Hsiao, Li-Chen Fu. 223-235 [doi]
• Multi-person Pose Estimation with Mid-Points for Human Detection under Real-World SurveillanceYadong Pan, Shoji Nishimura. 239-253 [doi]
• Gaze from Head: Gaze Estimation Without Observing EyeJun'ichi Murakami, Ikuhisa Mitsugami. 254-267 [doi]
• Interaction Recognition Through Body Parts Relation ReasoningMauricio Perez, Jun Liu 0036, Alex C. Kot. 268-280 [doi]
• DeepHuMS: Deep Human Motion Signature for 3D Skeletal SequencesNeeraj Battan, Abbhinav Venkat, Avinash Sharma. 281-294 [doi]
• Towards a Universal Appearance for Domain Generalization via Adversarial LearningYujui Chen, Tse-Wei Lin, Chiou-Ting Hsu. 297-311 [doi]
• Pre-trained and Shared Encoder in Cycle-Consistent Adversarial Networks to Improve Image QualityRuntong Zhang, Yuchen Wu, Keiji Yanai. 312-325 [doi]
• MobileGAN: Compact Network Architecture for Generative Adversarial NetworkTomoyuki Shimizu, Jianfeng Xu, Kazuyuki Tasaka. 326-338 [doi]
• Denoising and Inpainting of Sea Surface Temperature Image with Adversarial Physical Model LossNobuyuki Hirahara, Motoharu Sonogashira, Hidekazu Kasahara, Masaaki Iiyama. 339-352 [doi]
• Confidence Map Based 3D Cost Aggregation with Multiple Minimum Spanning Trees for Stereo MatchingYuhao Xiao, Dingding Xu, Guijin Wang, Xiaowei Hu, Yongbing Zhang, Xiangyang Ji, Li Zhang. 355-365 [doi]
• Optical Flow Assisted Monocular Visual OdometryYiming Wan, Wei Gao 0014, Yihong Wu 0002. 366-377 [doi]
• Coarse-to-Fine Deep Orientation Estimator for Local Image MatchingYasuaki Mori, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi. 378-390 [doi]
• Geometric Total Variation for Image Vectorization, Zooming and Pixel Art DepixelizingBertrand Kerautret, Jacques-Olivier Lachaud. 391-405 [doi]
• Information Theory-Based Curriculum Learning Factory to Optimize TrainingHenok Ghebrechristos, Gita Alaghband. 409-423 [doi]
• A Factorization Strategy for Tensor Robust PCAAndong Wang, Zhong Jin, Jingyu Yang. 424-437 [doi]
• Speeding up of the Nelder-Mead Method by Data-Driven Speculative ExecutionShuhei Watanabe, Yoshihiko Ozaki, Yoshiaki Bando, Masaki Onishi. 438-452 [doi]
• Efficient Bayesian Optimization Based on Parallel Sequential Random EmbeddingsNoriko Yokoyama, Masahiro Kohjima, Tatsushi Matsubayashi, Hiroyuki Toda. 453-466 [doi]
• Fundus Image Classification and Retinal Disease Localization with Limited SupervisionQier Meng, Yohei Hashimoto, Shin'ichi Satoh. 469-482 [doi]
• OSTER: An Orientation Sensitive Scene Text Recognizer with CenterLine RectificationZipeng Feng, Chen Du, Yanna Wang, Baihua Xiao. 483-497 [doi]
• On Fast Point Cloud Matching with Key Points and Parameter TuningDániel Varga, Sándor Laki, János M. Szalai-Gindl, László Dobos, Péter Vaderna, Bence Formanek. 498-511 [doi]
• Detection of Critical Camera Configurations for Structure from Motion Using Random ForestMario Michelini, Helmut Mayer 0001. 512-526 [doi]
• Visual Counting of Traffic Flow from a Car via Vehicle Detection and Motion AnalysisKevin Kolcheck, Zheyuan Wang, Haiyan Xu, Jiang Yu Zheng. 529-543 [doi]
• Directly Optimizing IoU for Bounding Box LocalizationMofassir ul Islam Arif, Mohsan Jameel, Lars Schmidt-Thieme. 544-556 [doi]
• Double Refinement Network for Room Layout EstimationIvan Kruzhilov, Mikhail Romanov, Dmitriy Babichev, Anton Konushin 0001. 557-568 [doi]
• Finger Tracking Based Tabla Syllable TranscriptionRaghavendra H. Bhalerao, Varsha Kshirsagar, Mitesh Raval. 569-579 [doi]
• Dual Templates Siamese TrackingZhiqiang Hou, Lilin Chen, Lei Pu. 580-593 [doi]
• Structure Function Based Transform Features for Behavior-Oriented Social Media Image ClassificationDivya Krishnani, Palaiahnakote Shivakumara, Tong Lu, Umapada Pal 0001, Raghavendra Ramachandra. 594-608 [doi]
• Single Image Reflection Removal Based on GAN with Gradient ConstraintRyo Abiko, Masaaki Ikehara. 609-624 [doi]
• SSA-GAN: End-to-End Time-Lapse Video Generation with Spatial Self-AttentionDaichi Horita, Keiji Yanai. 625-638 [doi]
• Semantic Segmentation of Railway Images Considering Temporal ContinuityYuki Furitsu, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Hiroki Mukojima, Nozomi Nagamine. 639-652 [doi]
• Real Full Binary Neural Network for Image Classification and Object DetectionYoungbin Kim, Wonjun Hwang. 653-662 [doi]
• Progressive Scale Expansion Network with Octave Convolution for Arbitrary Shape Scene Text DetectionShi Yan, Wei Feng, Peng Zhao, Cheng-Lin Liu. 663-676 [doi]
• SFLNet: Direct Sports Field Localization via CNN-Based RegressionShuhei Tarashima. 677-690 [doi]
• Trained Model Fusion for Object Detection Using Gating NetworkTetsuo Inoshita, Yuichi Nakatani, Katsuhiko Takahashi, Asuka Ishii, Gaku Nakano. 691-704 [doi]
• Category Independent Object Transfiguration with Domain Aware GANKaori Kumagai, Yukito Watanabe, Takashi Hosono, Jun Shimamura, Atsushi Sagata. 705-719 [doi]
• New Moments Based Fuzzy Similarity Measure for Text Detection in Distorted Social Media ImagesSoumyadip Roy, Palaiahnakote Shivakumara, Umapada Pal 0001, Tong Lu, Michael Blumenstein. 720-734 [doi]
• Fish Detection Using Convolutional Neural Networks with Limited Training DataShih-Lun Tseng, Huei-Yung Lin. 735-748 [doi]
• A New U-Net Based License Plate Enhancement Model in Night and Day ImagesPinaki Nath Chowdhury, Palaiahnakote Shivakumara, Ramachandra Raghavendra, Umapada Pal 0001, Tong Lu, Michael Blumenstein. 749-763 [doi]
• Integration of Biologically Inspired Pixel Saliency Estimation and IPDA Filters for Multi-target TrackingDaniel Griffiths, Laleh Badriasl, Tony Scoleri, Russell S. A. Brinkworth, Sanjeev Arulampalam, Anthony Finn. 764-778 [doi]
• The Effectiveness of Noise in Data Augmentation for Fine-Grained Image ClassificationNanyu Sun, Xianjie Mo, Tingting Wei, Dabin Zhang, Wei Luo. 779-792 [doi]
• Attention Recurrent Neural Networks for Image-Based Sequence Text RecognitionGuoqiang Zhong 0001, Guohua Yue. 793-806 [doi]
• Nighttime Haze Removal with Glow Decomposition Using GANBeomhyuk Koo, Gyeonghwan Kim. 807-820 [doi]
• Finding Logo and Seal in Historical Document Images - An Object Detection Based ApproachSukalpa Chanda, Prashant Kumar Prasad, Anders Hast, Anders Brun, Lasse Mårtensson, Umapada Pal 0001. 821-834 [doi]
• KIL: Knowledge Interactiveness Learning for Joint Depth Estimation and Semantic SegmentationLing Zhou, Chunyan Xu, Zhen Cui, Jian Yang 0003. 835-848 [doi]
• Road Scene Risk Perception for Intelligent Vehicles Using End-to-End Affordance Learning and Visual ReasoningJayani Withanawasam, Ehsan Javanmardi, Kelvin Wong, Mahdi Javanmardi, Shunsuke Kamijo. 849-862 [doi]
• Image2Height: Self-height Estimation from a Single-Shot ImageKei Shimonishi, Tyler Fisher, Hiroaki Kawashima, Kotaro Funakoshi. 863-877 [doi]
• Segmentation of Foreground in Image Sequence with Foveated Vision ConceptKwok-Leung Chan. 878-888 [doi]
• Bi-direction Feature Pyramid Temporal Action Detection NetworkJiang He, Yan Song, Haiyu Jiang. 889-901 [doi]
• Hand Segmentation for Contactless Palmprint RecognitionYusei Suzuki, Hiroya Kawai, Koichi Ito, Takafumi Aoki, Masakazu Fujio, Yosuke Kaga, Kenta Takahashi. 902-912 [doi]
• Selecting Discriminative Features for Fine-Grained Visual ClassificationQin Xu, Linyang Li, Qian Chen, Bin Luo. 913-926 [doi]