TP-V1.V3.10
RESIDUAL GRAPH ATTENTION NETWORK AND EXPRESSION-RESPECT DATA AUGMENTATION AIDED VISUAL GROUNDING
Jia Wang, Hung-Yi Wu, Hong-Han Shuai, Wen-Huang Cheng, National Yang Ming Chiao Tung University, Taiwan; Jun-Cheng Chen, Academia Sinica, Taiwan; , ,
Session:
Computational and Electronic Imaging Methods
Track:
Computational Imaging Methods and Models
Location:
Gather.Town 3
Presentation Time:
Tue, 4 Oct, 21:00 - 22:00 China Standard Time (UTC +8)
Tue, 4 Oct, 15:00 - 16:00 Central European Time (UTC +1)
Tue, 4 Oct, 13:00 - 14:00 UTC
Tue, 4 Oct, 09:00 - 10:00 Eastern Time (UTC -5)
Tue, 4 Oct, 15:00 - 16:00 Central European Time (UTC +1)
Tue, 4 Oct, 13:00 - 14:00 UTC
Tue, 4 Oct, 09:00 - 10:00 Eastern Time (UTC -5)
Session Co-Chairs:
Andrea Cavallaro, Queen Mary University of London and Jean-Christophe Pesquet, CentraleSupélec and Rebecca Willett, University of Chicago
Presentation
Discussion
Resources
No resources available.
Session TP-V1.V3
TP-V1.V3.1: ADVERSARIAL EXAMPLES FOR GOOD: ADVERSARIAL EXAMPLES GUIDED IMBALANCED LEARNING
Jie Zhang, Lei Zhang, Gang Li, Chao Wu, Zhejiang University, China
TP-V1.V3.2: MONOTONICALLY CONVERGENT REGULARIZATION BY DENOISING
Yuyang Hu, Jiaming Liu, Xiaojian Xu, Ulugbek Kamilov, Washington University in St. Louis, United States of America
TP-V1.V3.3: DARTS-PD: DIFFERENTIABLE ARCHITECTURE SEARCH WITH PATH-WISE WEIGHT SHARING DERIVATION
He Cai, Zhaokai Zhang, Tianpeng Feng, Yandong Guo, OPPO Research Institute, China
TP-V1.V3.4: DUAL-DOMAIN UPDATE AND DOUBLE-GROUP OPTIMIZATION NETWORK FOR IMAGE COMPRESSIVE SENSING
Hanru Zhang, Chunling Yang, South China University of Technology, China
TP-V1.V3.5: RELATION-GUIDED NETWORK FOR IMAGE-TEXT RETRIEVAL
Yulou Yang, Hao Shen, Ming Yang, Nanjing Normal University, China
TP-V1.V3.7: A DATABASE OF VISUAL COLOR DIFFERENCES OF MODERN SMARTPHONE PHOTOGRAPHY
Keshuo Xu, Yuming Fang, Jiangxi University of Finance and Economics, China; Zhihua Wang, Kede Ma, City University of Hong Kong, China; Yang Yang, Jianlei Dong, Guangdong OPPO Mobile Telecommunications Corp., Ltd, China; Lihao Xu, Hangzhou Dianzi University, China
TP-V1.V3.8: NONLINEAR ORTHOGONAL NMF ON THE STIEFEL MANIFOLD WITH GRAPH-BASED TOTAL VARIATION REGULARIZATION
Abderrahmane Rahiche, Mohamed Cheriet, Synchromedia lab, Ecole de Technologie Supérieure (ETS), Canada
TP-V1.V3.9: BREGMAN PLUG-AND-PLAY PRIORS
Abdullah Al-Shabili, Ivan Selesnick, Tandon School of Engineering, New York University, United States of America; Xiaojian Xu, Washington University in St. Louis, United States of America; Ulugbek Kamilov, Washington University in St. Louis, United States of America
TP-V1.V3.10: RESIDUAL GRAPH ATTENTION NETWORK AND EXPRESSION-RESPECT DATA AUGMENTATION AIDED VISUAL GROUNDING
Jia Wang, Hung-Yi Wu, Hong-Han Shuai, Wen-Huang Cheng, National Yang Ming Chiao Tung University, Taiwan; Jun-Cheng Chen, Academia Sinica, Taiwan; , ,
TP-V1.V3.11: DISCRIMINATE CLEARER TO RANK BETTER: IMAGE CROPPING BY AMPLIFYING VIEW-WISE DIFFERENCES
Zhiyu Pan, Zhiguo Cao, Ke Xian, Hao Lu, Huazhong University of Science and Technology, China; Weicai Zhong, Huawei, China
TP-V1.V3.12: TWO-STEP COLOR-POLARIZATION DEMOSAICKING NETWORK
Vy Nguyen, Masayuki Tanaka, Yusuke Monno, Masatoshi Okutomi, Tokyo Institute of Technology, Japan
TP-V1.V3.13: OPTIMAL NOISE-AWARE IMAGING WITH SWITCHABLE PREFILTERS
Zilai Gong, Masayuki Tanaka, Yusuke Monno, Masatoshi Okutomi, Tokyo Institute of Technology, China
TP-V1.V3.14: HALFTONING WITH MULTI-AGENT DEEP REINFORCEMENT LEARNING
Haitian Jiang, Dongliang Xiong, Xiaowen Jiang, Kai Huang, Zhejiang University, China; Aiguo Yin, Zhuhai Pantum Electronics Company Limited, China; Li Ding, Zhuhai Apex Microelectronics Company Limited, China
TP-V1.V3.15: ON ADVERSARIAL ROBUSTNESS OF DEEP IMAGE DEBLURRING
Kanchana Vaishnavi Gandikota, Paramanand Chandramouli, Michael Moeller, University of Siegen, Germany