ARS-17: Machine Learning for Recognition in Images and Videos I |
| Interactive Q&A Time: Wednesday, 28 October, 09:00 - 09:55 |
| Virtual Session: View on Virtual Platform |
| Session Chairs: A. Aydin Alatan, Middle East Technical University (METU) and Yue (Rex) Wu, Amazon |
| ARS-17.1: DISCRIMINATIVE CLIP MINING FOR VIDEO ANOMALY DETECTION |
| Li Sun; Shanghai Jiao Tong University |
| Yanjun Chen; Shanghai Jiao Tong University |
| Wu Luo; Shanghai Jiao Tong University |
| Haiyan Wu; Railway Police College |
| Chongyang Zhang; Shanghai Jiao Tong University |
| ARS-17.2: PROPOSAL-BASED INSTANCE SEGMENTATION WITH POINT SUPERVISION |
| Issam Laradji; University of British Columbia |
| Negar Rostamzadeh; Element AI |
| Pedro Pinheiro; Element AI |
| David Vazquez; Element AI |
| Mark Schmidt; Element AI |
| ARS-17.3: CAM-UNET: CLASS ACTIVATION MAP GUIDED UNET WITH FEEDBACK REFINEMENT FOR DEFECT SEGMENTATION |
| Dongyun Lin; Institute for Infocomm Research(I2R) |
| Yiqun Li; Institute for Infocomm Research(I2R) |
| Shitala Prasad; Institute for Infocomm Research(I2R) |
| Tin Lay Nwe; Institute for Infocomm Research(I2R) |
| Sheng Dong; Institute for Infocomm Research(I2R) |
| Zaw Min Oo; Institute for Infocomm Research(I2R) |
| ARS-17.4: ATTENTION-ENHANCED AND MORE BALANCED R-CNN FOR OBJECT DETECTION |
| Ruohong Mei; Beijing University of Posts and Telecommunications |
| Haiying Wang; Beijing University of Posts and Telecommunications |
| Aidong Men; Beijing University of Posts and Telecommunications |
| ARS-17.5: QAMFACE: QUADRATIC ADDITIVE ANGULAR MARGIN LOSS FOR FACE RECOGNITION |
| He Zhao; Peking University |
| Yongjie Shi; Peking University |
| Tong Xin; Peking University |
| Xianghua Ying; Peking University |
| Hongbin Zha; Peking University |
| ARS-17.6: IMPROVING DETECTION AND RECOGNITION OF DEGRADED FACES BY DISCRIMINATIVE FEATURE RESTORATION USING GAN |
| Soumya Shubhra Ghosh; Queen's University Belfast |
| Yang Hua; Queen's University Belfast |
| Sankha Subhra Mukherjee; Anyvision |
| Neil Robertson; Queen's University Belfast |
| ARS-17.7: A GENERATIVE SELF-ENSEMBLE APPROACH TO SIMULATED+UNSUPERVISED LEARNING |
| Yu Mitsuzumi; NTT / Kyoto University |
| Go Irie; NTT |
| Akisato Kimura; NTT |
| Atsushi Nakazawa; Kyoto University |
| ARS-17.8: LEARNING DISENTANGLED FEATURE REPRESENTATIONS FOR ANOMALY DETECTION |
| Wei-Yu Lee; MOXA Inc. |
| Yu-Chiang Frank Wang; National Taiwan University |
| ARS-17.9: FACE RECOGNITION UNDER LOW ILLUMINATION VIA DEEP FEATURE RECONSTRUCTION NETWORK |
| Yu-Hsuan Huang; National Taiwan University |
| Homer H. Chen; National Taiwan University |
| ARS-17.10: PAIRWISE ADJACENCY MATRIX ON SPATIAL TEMPORAL GRAPH CONVOLUTION NETWORK FOR SKELETON-BASED TWO-PERSON INTERACTION RECOGNITION |
| Chao-Lung Yang; National Taiwan University of Science and Technology |
| Aji Setyoko; National Taiwan University of Science and Technology |
| Hendrik Tampubolon; National Taiwan University of Science and Technology |
| Kai-Lung Hua; National Taiwan University of Science and Technology |
| ARS-17.11: JUST NOTICEABLE DIFFERENCE FOR MACHINES TO GENERATE ADVERSARIAL IMAGES |
| Adil Kaan Akan; Middle East Technical University |
| Mehmet Ali Genc; Middle East Technical University |
| Fatos Tunay Yarman Vural; Middle East Technical University |
| ARS-17.12: EFFICIENT TEMPORAL-SPATIAL FEATURE GROUPING FOR VIDEO ACTION RECOGNITION |
| Zhikang Qiu; Shanghai Jiao Tong University |
| Xu Zhao; Shanghai Jiao Tong University |
| Zhilan Hu; Huawei |
| ARS-17.13: SPEAKER-INDEPENDENT LIPREADING WITH LIMITED DATA |
| Chenzhao Yang; Shanghai Jiao Tong University |
| Shilin Wang; Shanghai Jiao Tong University |
| Xingxuan Zhang; Shanghai Jiao Tong University |
| Yun Zhu; Shanghai Jiao Tong University |
| ARS-17.14: POINT SET ATTENTION NETWORK FOR SEMANTIC SEGMENTATION |
| Jie Jiang; Institute of Automation, Chinese Academy of Sciences |
| Jing Liu; Institute of Automation, Chinese Academy of Sciences |
| Jun Fu; Institute of Automation, Chinese Academy of Sciences |
| Xinxin Zhu; Institute of Automation, Chinese Academy of Sciences |
| Hanqing Lu; Institute of Automation, Chinese Academy of Sciences |
| ARS-17.15: MT-UNET: A NOVEL U-NET BASED MULTI-TASK ARCHITECTURE FOR VISUAL SCENE UNDERSTANDING |
| Ankit Jha; Indian Institute of Technology Bombay |
| Awanish Kumar; Indian Institute of Technology Bombay |
| Shivam Pande; Indian Institute of Technology Bombay |
| Biplab Banerjee; Indian Institute of Technology Bombay |
| Subhasis Chaudhuri; Indian Institute of Technology Bombay |
| ARS-17.16: ADVERSARIAL DEFENSE VIA LOCAL FLATNESS REGULARIZATION |
| Jia Xu; Tsinghua University |
| Yiming Li; Tsinghua University |
| Yong Jiang; Tsinghua University |
| Shutao Xia; Tsinghua University |