TEC-04: Machine Learning for Image and Video Processing II |
| Interactive Q&A Time: Monday, 26 October, 18:30 - 19:25 |
| Virtual Session: View on Virtual Platform |
| Session Chairs: Anil Kokaram, Trinity College Dublin and Ton Kalker, XPERI |
| TEC-04.1: EXAGGERATED LEARNING FOR CLEAN-AND-SHARP IMAGE RESTORATION |
| Chang Liu; Shanghai Jiao Tong University |
| Qifan Gao; Shanghai Jiao Tong University |
| Xiaolin Wu; McMaster University |
| TEC-04.2: TRADITIONAL METHOD INSPIRED DEEP NEURAL NETWORK FOR EDGE DETECTION |
| Jan Kristanto Wibisono; National Chiao Tung University |
| Hsueh-Ming Hang; National Chiao Tung University |
| TEC-04.3: MULTI-STEP QUANTIZATION OF A MULTI-SCALE NETWORK FOR CROWD COUNTING |
| Kyujin Shim; Korea Advanced Institute of Science and Technology (KAIST) |
| Junyoung Byun; Korea Advanced Institute of Science and Technology (KAIST) |
| Changick Kim; Korea Advanced Institute of Science and Technology (KAIST) |
| TEC-04.4: BOOSTING IMAGE-BASED LOCALIZATION VIA RANDOMLY GEOMETRIC DATA AUGMENTATION |
| Yiming Wan; NLPR, Institute of Automation, Chinese Academy of Sciences |
| Wei Gao; NLPR, Institute of Automation, Chinese Academy of Sciences |
| Sheng Han; NLPR, Institute of Automation, Chinese Academy of Sciences |
| Yihong Wu; NLPR, Institute of Automation, Chinese Academy of Sciences |
| TEC-04.5: A NOVEL CENTROID UPDATE APPROACH FOR CLUSTERING-BASED SUPERPIXEL METHODS AND SUPERPIXEL-BASED EDGE DETECTION |
| Houwang Zhang; China University of Geosciences |
| Chong Wu; City University of Hong Kong |
| Le Zhang; Tongji University |
| Hanying Zheng; China University of Geosciences |
| TEC-04.6: LOSS RESCALING BY UNCERTAINTY INFERENCE FOR SINGLE-STAGE OBJECT DETECTION |
| Yan Li; NEC Laboratories, China |
| Xiaoyi Chen; NEC Laboratories, China |
| Li Quan; NEC Laboratories, China |
| Ni Zhang; NEC Laboratories, China |
| TEC-04.7: GAPNET: GENERIC-ATTRIBUTE-POSE NETWORK FOR FINE-GRAINED VISUAL CATEGORIZATION USING MULTI-ATTRIBUTE ATTENTION MODULE |
| Minjeong Ju; Korea Advanced Institute of Science and Technology (KAIST) |
| Hobin Ryu; Korea Advanced Institute of Science and Technology (KAIST) |
| Sangkeun Moon; Korea Electric Power Corporation (KEPCO) Research Institute |
| Chang D. Yoo; Korea Advanced Institute of Science and Technology (KAIST) |
| TEC-04.8: DESHUFFLEGAN: A SELF-SUPERVISED GAN TO IMPROVE STRUCTURE LEARNING |
| Gulcin Baykal; Istanbul Technical University |
| Gozde Unal; Istanbul Technical University |
| TEC-04.9: SUBSET SAMPLING FOR PROGRESSIVE NEURAL NETWORK LEARNING |
| Dat Thanh Tran; Tampere University |
| Moncef Gabbouj; Tampere University |
| Alexandros Iosifidis; Aarhus University |
| TEC-04.10: EFFICIENT DETECTION OF PIXEL-LEVEL ADVERSARIAL ATTACKS |
| Syed Afaq Ali Shah; Murdoch University |
| Moise Bougre; ENSEA |
| Naveed Akhtar; University of Western Australia |
| Mohammed Bennamoun; University of Western Australia |
| Liang Zhang; Xidian University |
| TEC-04.11: HIERARCHICAL MODEL FOR LONG-LENGTH VIDEO SUMMARIZATION WITH ADVERSARIALLY ENHANCED AUDIO/VISUAL FEATURES |
| Hansol Lee; Seoul National University of Science and Technology |
| Gyemin Lee; Seoul National University of Science and Technology |
| TEC-04.12: ROBUST ADVERSARIAL LEARNING FOR SEMI-SUPERVISED SEMANTIC SEGMENTATION |
| Jia Zhang; Guangxi Normal University |
| Zhixin Li; Guangxi Normal University |
| Canlong Zhang; Guangxi Normal University |
| Huifang Ma; Northwest Normal University |
| TEC-04.13: INPUT DROPOUT FOR SPATIALLY ALIGNED MODALITIES |
| Sébastien de Blois; Université Laval |
| Mathieu Garon; Université Laval |
| Christian Gagné; Université Laval |
| Jean-François Lalonde; Université Laval |
| TEC-04.14: SELF-SUPERVISED LEARNING OF DEPTH AND POSE USING CYCLE GENERATIVE ADVERSARIAL NETWORK |
| Yunhe Tong; Peking University |
| Anjie Wang; Peking University |
| Songchao Tan; Peking University |
| Shanshe Wang; Peking University |
| Siwei Ma; Peking University |
| Wen Gao; Peking University |
| TEC-04.15: WEAKLY-SUPERVISED DEFECT SEGMENTATION WITHIN VISUAL INSPECTION IMAGES OF LIQUID CRYSTAL DISPLAYS IN ARRAY PROCESS |
| Fan Li; IBM |
| Guoqiang Hu; IBM |
| Shengnan Zhu; IBM |
| TEC-04.16: ATTENTION SELECTIVE NETWORK FOR FACE SYNTHESIS AND POSE-INVARIANT FACE RECOGNITION |
| Jiashu Liao; University of Warwick |
| Alex Kot; Nanyang Technological University |
| Tanaya Guha; University of Warwick |
| Victor Sanchez; University of Warwick |
| TEC-04.17: CONTINUAL LEARNING OF PREDICTIVE MODELS IN VIDEO SEQUENCES VIA VARIATIONAL AUTOENCODERS |
| Damian Campo; University of Genova |
| Giulia Slavic; University of Genova |
| Mohamad Baydoun; University of Genova |
| Lucio Marcenaro; University of Genova |
| Carlo Regazzoni; University of Genova |
| TEC-04.18: CHANNEL--SPATIAL FUSION AWARE NET FOR ACCURATE AND FAST OBJECT DETECTION |
| Linhuang Wu; Fuzhou University |
| Xiujun Yang; Fuzhou University |
| Zhenjia Fan; Fuzhou University |
| Chunjun Wang; University of Chicago |
| Zhifeng Chen; Fuzhou University |
| TEC-04.19: UNPRIORTIZED AUTOENCODER FOR IMAGE GENERATION |
| Jaeyoung Yoo; Seoul National University |
| Hojun Lee; Seoul National University |
| Nojun Kwak; Seoul National University |
| TEC-04.20: FEATURE ENHANCEMENT AND FUSION FOR IMAGE-BASED PARTICLE MATTER ESTIMATION WITH F-MSE LOSS |
| Xiaoyu Wang; Northwest University |
| Lei Zhang; Northwest University |
| Qirong Bo; Northwest University |
| Jun Feng; Northwest University |
| Jingzhao Hu; Northwest University |
| Yuxin Kang; Northwest University |
| Jing Zhang; Lamar University |
| TEC-04.21: DEEP MULTIMODAL SPARSE REPRESENTATION-BASED CLASSIFICATION |
| Mahdi Abavisani; Rutgers University |
| Vishal M. Patel; Johns Hopkins University |