Table of Contents

• Reconstruction with Guided PatchMatch StereoTrevor Gee, Patrice Delmas. 1-6 [doi]
• Domain Adaptation using a Gradient Reversal Layer with Instance WeightingKosuke Osumi, Takayoshi Yamashita, Hironobu Fujiyoshi. 1-5 [doi]
• 3D Object Trajectory Reconstruction using Stereo Matching and Instance Flow based Multiple Object TrackingSebastian Bullinger, Christoph Bodensteiner, Michael Arens. 1-6 [doi]
• Online Targetless End-to-End Camera-LIDAR Self-calibrationBalázs Nagy, Levente Kovács, Csaba Benedek. 1-6 [doi]
• Gait Recognition Based on Constrained Mutual Subspace Method with CNN FeaturesAkinari Sakai, Naoya Sogi, Kazuhiro Fukui. 1-6 [doi]
• UMGAN: Generative adversarial network for image unmosaicing using perceptual lossKamran Javed, Nizam Ud Din, Seho Bae, Rahul S. Maharjan, Donghwan Seo, Juneho Yi. 1-5 [doi]
• Spectral Normalization and Relativistic Adversarial Training for Conditional Pose Generation with Self-AttentionYusuke Horiuchi, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa 0002. 1-5 [doi]
• CNN-based Image Denoising for Outdoor Active StereoChengchao Qu, Maksim Moiseikin, Sascha Voth, Jürgen Beyerer. 1-6 [doi]
• An Evaluation of Recent Local Image Descriptors for Real-World Applications of Image MatchingFabio Bellavia, Carlo Colombo. 1-6 [doi]
• EyeWeS: Weakly Supervised Pre-Trained Convolutional Neural Networks for Diabetic Retinopathy DetectionPedro Costa 0005, Teresa Araújo, Guilherme Aresta, Adrian Galdran, Ana Maria Mendonça, Asim Smailagic, Aurélio Campilho. 1-6 [doi]
• DCNN-GAN: Reconstructing Realistic Image from fMRIYunfeng Lin, Jiangbei Li, Hanjing Wang. 1-6 [doi]
• Cooking Video Summarization Guided By Matching with Step-By-Step Recipe PhotosRyo Sobue, Mitsuru Nakazawa, Yeongnam Chae, Björn Stenger, Takayoshi Yamashita, Hironobu Fujiyoshi. 1-6 [doi]
• Human identification by gait from event-based cameraAnna Sokolova, Anton Konushin 0001. 1-6 [doi]
• Learning Based Character Segmentation Method for Various License PlatesPyong-Kun Kim, Kil-Taek Lim, DooSik Kim. 1-6 [doi]
• Robust Auto-Calibration for Practical Scanning Setups from Epipolar and Trifocal RelationsTorben Fetzer, Gerd Reis, Didier Stricker. 1-6 [doi]
• Heatmapping of People Involved in Group ActivitiesKohei Sendo, Norimichi Ukita. 1-6 [doi]
• Hotspots Integrating of Expert and Beginner Experiences of Machine Operations through Egocentric VisionLongfei Chen, Yuichi Nakamura, Kazuaki Kondo, Dima Damen, Walterio W. Mayol-Cuevas. 1-6 [doi]
• Perspective-Aware Loss Function for Crowd Density EstimationBedir Yilmaz, Ven Jyn Kok, Mei Kuan Lim, Siti Norul Huda Sheikh Abdullah. 1-6 [doi]
• Measuring robustness of Visual SLAMDavid Prokhorov, Dmitry Zhukov, Olga Barinova, Anton Konushin 0001, Anna Vorontsova. 1-6 [doi]
• Super accurate low latency object detection on a surveillance UAVMaarten Vandersteegen, Kristof Van Beeck, Toon Goedemé. 1-6 [doi]
• Kernelized Cross-view Quadratic Discriminant Analysis for Person Re-IdentificationTetsu Matsukawa, Einoshin Suzuki. 1-5 [doi]
• Gradual Sampling Gate for Bidirectional Knowledge DistillationSoma Minami, Takayoshi Yamashita, Hironobu Fujiyoshi. 1-6 [doi]
• SlamCraft: Dense Planar RGB Monocular SLAMJason R. Rambach, Paul Lesur, Alain Pagani, Didier Stricker. 1-6 [doi]
• Face Style Transfer and Removal with Generative Adversarial NetworkQiang Zhu, Ze-Nian Li. 1-6 [doi]
• Zero-shot Learning of 3D Point Cloud ObjectsAli Cheraghian, Shafin Rahman, Lars Petersson. 1-6 [doi]
• Revisiting Visual Odometry for Real-Time PerformanceGaurav Singh, Meiqing Wu, Siew Kei Lam. 1-6 [doi]
• Performance Evalution of 3D Keypoint Detectors and Descriptors for Plants Health ClassificationShiva Azimi, Brejesh Lall, Tapan K. Gandhi. 1-6 [doi]
• The CASE Dataset of Candidate Spaces for Advert ImplantationSoumyabrata Dev, Murhaf Hossari, Matthew Nicholson, Killian McCabe, Atul Nautiyal, Clare Conran, Jian Tang, Wei Xu, François Pitié. 1-4 [doi]
• A Hierarchical Segmentation Approach with Convolution-Recursive Deep Learning for 3D Multi-Object Recognition under Partial Occlusion ConditionsSomar Boubou, Tatsuo Narikiyo, Michihiro Kawanishi. 1-6 [doi]
• Indexing in k-Nearest Neighbor Graph by Hash-Based Hill-ClimbingMunlika Rattaphun, Amorntip Prayoonwong, Chih-Yi Chiu. 1-4 [doi]
• Automatic Measurement of Visual Attention to Video Content using Deep LearningAttila Schulc, Jeffrey F. Cohn, Jie Shen 0008, Maja Pantic. 1-6 [doi]
• Bullet-time image generation without 3-DYasuyuki Sugaya, Keita Ohseki. 1-6 [doi]
• Residual Squeeze-and-Excitation Network for Battery Cell Surface InspectionZiyang Song, Zejian Yuan, Tie Liu. 1-5 [doi]
• Visual Rhythm Prediction with Feature-Aligning NetworkYutong Xie, Haiyang Wang, Yan Hao, Zihao Xu. 1-6 [doi]
• Pupil Localization for Ophthalmic Diagnosis Using Anchor Ellipse RegressionHorng-Horng Lin, Zheng-Yi Li, Min-Hsiu Shih, Yung-Nien Sun, Ting-Li Shen. 1-5 [doi]
• Invariant Spatial Information for Loop-Closure DetectionRyohei Yamamoto, Kanji Tanaka, Koji Takeda. 1-6 [doi]
• Uncalibrated photometric stereo constrained by intrinsic reflectance image and shape from silhoutteShuhei Hashimoto, Daisuke Miyazaki, Shinsaku Hiura. 1-6 [doi]
• A very concise feature representation for time series classification understandingPattreeya Tanisaro, Gunther Heidemann. 1-6 [doi]
• Autoencoder-Based Fabric Defect Detection with Cross- Patch SimilarityHu Tian, Fei Li. 1-6 [doi]
• Automatic Human Pose Annotation for Loose-fitting ClothesTakuya Matsumoto, Kodai Shimosato, Takahiro Maeda, Tatsuya Murakami, Koji Murakoso, Kazuhiko Mino, Norimichi Ukita. 1-6 [doi]
• A Three-Player GAN: Generating Hard Samples to Improve Classification NetworksSimon Vandenhende, Bert De Brabandere, Davy Neven, Luc Van Gool. 1-6 [doi]
• Re-staining Pathology Images by FCNNMasayuki Fujitani, Yoshihiko Mochizuki, Satoshi Iizuka, Edgar Simo-Serra, Hirokazu Kobayashi, Chika Iwamoto, Kenoki Ohuchida, Makoto Hashizume, Hidekata Hontani, Hiroshi Ishikawa 0002. 1-6 [doi]
• PCB-METAL: A PCB Image Dataset for Advanced Computer Vision Machine Learning Component AnalysisGayathri Mahalingam, Kevin Marshall Gay, Karl Ricanek. 1-5 [doi]
• BallTrack: Football ball tracking for real-time CCTV systemsJacek Komorowski, Grzegorz Kurzejamski, Grzegorz Sarwas. 1-5 [doi]
• Robust 3D Human Pose Estimation Guided by Filtered Subsets of Body KeypointsAlexandros Makris, Antonis A. Argyros. 1-6 [doi]
• Human-Object Maps for Daily Activity RecognitionHaruya Ishikawa, Yuchi Ishikawa, Shuichi Akizuki, Yoshimitsu Aoki. 1-6 [doi]
• Consolidating Segmentwise Non-Rigid Structure from MotionVladislav Golyanik, André Jonas, Didier Stricker. 1-6 [doi]
• Skip-Pose Vectors: Pose-based motion embedding using Encoder-Decoder modelsYuta Shirakawa, Tatsuo Kozakaya. 1-6 [doi]
• Welding Joints Inspection via Residual Attention NetworkJinguo Zhu, Zejian Yuan, Tie Liu. 1-5 [doi]
• Recognition and 6D Pose Estimation of Large-scale Objects using 3D Semi-Global DescriptorsDavid Nospes, Kirill Safronov, Sarah Gillet, Klaus Brillowski, Uwe E. Zimmermann. 1-6 [doi]
• Auto-Retoucher(ART) - A Framework for Background Replacement and Foreground AdjustmentYunxuan Xiao, Yikai Li, Yuwei Wu, Lizhen Zhu. 1-5 [doi]
• Improving image classifiers for small datasets by learning rate adaptationsSourav Mishra, Toshihiko Yamasaki, Hideaki Imaizumi. 1-6 [doi]
• Spatio-temporal eye contact detection combining CNN and LSTMYuki Watanabe, Atsushi Nakazawa, Yu Mitsuzumi, Toyoaki Nishida. 1-7 [doi]
• Temporally Forward Nonlinear Scale Space with Octave Prediction for High Frame Rate and Ultra-Low Delay A-KAZE Matching SystemYuan Li, Songlin Du, Takeshi Ikenaga. 1-4 [doi]
• Uncertainty based model selection for fast semantic segmentationYu-Hui Huang, Marc Proesmans, Stamatios Georgoulis, Luc Van Gool. 1-6 [doi]
• Sparse and Noisy LiDAR Completion with RGB Guidance and UncertaintyWouter Van Gansbeke, Davy Neven, Bert De Brabandere, Luc Van Gool. 1-6 [doi]
• Region-wise Modeling of Facial Skin Age using Deep CNNsMatthew Shreve, Raja Bala, Wencheng Wu, Beilei Xu, Ankur Purwar, Paul Matts. 1-6 [doi]
• End-to-End Feature Pyramid Network for Real-Time Multi-Person Pose EstimationDingli Luo, Songlin Du, Takeshi Ikenaga. 1-4 [doi]
• Team Formation Mapping and Sequential Ball Motion State Based Event Recognition for Automatic Data VolleyLinzi Liang, Xina Cheng, Takeshi Ikenaga. 1-4 [doi]
• News2meme: An Automatic Content Generator from News Based on Word Subspaces from Text and ImageErica K. Shimomoto, Lincon Sales de Souza, Bernardo B. Gatto, Kazuhiro Fukui. 1-6 [doi]
• A Photo Booth That Finds Your Sports Player LookalikeMitsuru Nakazawa, Tomoyuki Mukasa, Björn Stenger. 1-4 [doi]
• Phenotypic Profiling of High Throughput Imaging Screens with Generic Deep Convolutional FeaturesPhilip T. G. Jackson, Yinhai Wang, Sinead Knight, Hongming Chen, Thierry Dorval, Martin Brown, Claus Bendtsen, Boguslaw Obara. 1-4 [doi]
• Single-wavelength and multi-parallel dotted- and solid-lines for dense and robust active 3D reconstructionGenki Nagamatsu, Ryo Furukawa, Ryusuke Sagawa, Hiroshi Kawasaki. 1-6 [doi]
• Similar Finger Gesture Recognition using Triplet-loss NetworksGibran Benitez-Garcia, Muhammad Haris, Yoshiyuki Tsuda, Norimichi Ukita. 1-6 [doi]
• Integrating Visual and Geometric Consistency for Pose EstimationHuiqin Chen, Emanuel Aldea, Sylvie Le Hégarat-Mascle. 1-5 [doi]
• Exploring Better Food Detection via Transfer LearningJianing Sun, Katarzyna Radecka, Zeljko Zilic. 1-6 [doi]
• Accurate Ellipse Extraction in Low-Quality ImagesZezhong Xu, Shibo Xu, Cheng Qian, Reinhard Klette. 1-5 [doi]
• Accurate Hand Keypoint Localization on Mobile DevicesFilippos Gouidis, Paschalis Panteleris, Iason Oikonomidis, Antonis A. Argyros. 1-6 [doi]