All times are in Alaska local time (AKDT/UTC−08:00)
MLR-APPL-IVASR-6: Machine learning for image and video analysis, synthesis, and retrieval 6 |
Interactive Q&A Time: Wednesday, September 22, 08:00 - 09:30 |
Session Chair: Ngai-Man Cheung, Singapore University of Technology and Design |
MLR-APPL-IVASR-6.1: LIFELONG TWIN GENERATIVE ADVERSARIAL NETWORKS |
Fei Ye; University of York |
Adrian Bors; University of York |
MLR-APPL-IVASR-6.2: A NOVEL SENSITIVITY METRIC FOR MIXED-PRECISION QUANTIZATION WITH SYNTHETIC DATA GENERATION |
Donghyun Lee; Samsung Electronics |
Minkyoung Cho; Samsung Electronics |
Seungwon Lee; Samsung Electronics |
Joonho Song; Samsung Electronics |
Changkyu Choi; Samsung Electronics |
MLR-APPL-IVASR-6.3: K-HAIRSTYLE: A LARGE-SCALE KOREAN HAIRSTYLE DATASET FOR VIRTUAL HAIR EDITING AND HAIRSTYLE CLASSIFICATION |
Taewoo Kim; Korea Advanced Institute of Science and Technology |
Chaeyeon Chung; Korea Advanced Institute of Science and Technology |
Sunghyun Park; Korea Advanced Institute of Science and Technology |
Gyojung Gu; Nestyle |
Keonmin Nam; Nestyle |
Wonzo Choe; Brandi |
Jaesung Lee; Brandi |
Jaegul Choo; Korea Advanced Institute of Science and Technology |
MLR-APPL-IVASR-6.4: SILHOUETTE-BASED SYNTHETIC DATA GENERATION FOR 3D HUMAN POSE ESTIMATION WITH A SINGLE WRIST-MOUNTED 360° CAMERA |
Ryosuke Hori; Keio University |
Ryo Hachiuma; Keio University |
Hideo Saito; Keio University |
Mariko Isogawa; NTT |
Dan Mikami; NTT |
MLR-APPL-IVASR-6.5: TWO-STAGE SEAMLESS TEXT ERASING ON REAL-WORLD SCENE IMAGES |
Benjamin Conrad; University of Amsterdam |
Pei-I Chen; Jumio AI Labs |
MLR-APPL-IVASR-6.6: OPENING DEEP NEURAL NETWORKS WITH GENERATIVE MODELS |
Marcos Vendramini; Universidade Federal de Minas Gerais |
Hugo Oliveira; University of São Paulo |
Alexei Machado; Universidade Federal de Minas Gerais |
Jefersson dos Santos; Universidade Federal de Minas Gerais |
MLR-APPL-IVASR-6.7: GENERATING THERMAL HUMAN FACES FOR PHYSIOLOGICAL ASSESSMENT USING THERMAL SENSOR AUXILIARY LABELS |
Catherine Ordun; University of Maryland Baltimore County |
Edward Raff; Booz Allen Hamilton |
Sanjay Purushotham; University Maryland Baltimore County |
MLR-APPL-IVASR-6.8: HSEGAN: HAIR SYNTHESIS AND EDITING USING STRUCTURE-ADAPTIVE NORMALIZATION ON GENERATIVE ADVERSARIAL NETWORK |
Wanling Fan; Fudan University |
Jiayuan Fan; Fudan University |
Gang Yu; Tencent |
Bin Fu; Tencent |
Tao Chen; Fudan University |
MLR-APPL-IVASR-6.9: ENHANCE VIA DECOUPLING: IMPROVING MULTI-LABEL CLASSIFIERS WITH VARIATIONAL FEATURE AUGMENTATION |
Ming Chen; Tsinghua University |
Guijin Wang; Tsinghua University |
Jing-Hao Xue; University College London |
Zijian Ding; Tsinghua University |
Li Sun; Tsinghua University |
MLR-APPL-IVASR-6.10: ON DATA AUGMENTATION FOR GAN TRAINING |
Ngoc-Trung Tran; Singapore University of Technology and Design (SUTD) |
Viet-Hung Tran; Singapore University of Technology and Design (SUTD) |
Ngoc-Bao Nguyen; Singapore University of Technology and Design (SUTD) |
Trung-Kien Nguyen; Singapore University of Technology and Design (SUTD) |
Ngai-Man Cheung; Singapore University of Technology and Design (SUTD) |
MLR-APPL-IVASR-6.11: SEMANTIC ROLE AWARE CORRELATION TRANSFORMER FOR TEXT TO VIDEO RETRIEVAL |
Burak Satar; Agency for Science, Technology and Research (A*STAR) |
Hongyuan Zhu; Agency for Science, Technology and Research (A*STAR) |
Xavier Bresson; Nanyang Technological University (NTU) |
Joo-Hwee Lim; Agency for Science, Technology and Research (A*STAR) |
MLR-APPL-IVASR-6.12: SOFT RANKING THRESHOLD LOSSES FOR IMAGE RETRIEVAL |
Chiao-An Yang; National Taiwan University |
Zhixiang Wang; National Taiwan University |
Yen-Yu Lin; National Chiao Tung University |
Yung-Yu Chuang; National Taiwan University |