MMSP-10.3
DAM-GAN : IMAGE INPAINTING USING DYNAMIC ATTENTION MAP BASED ON FAKE TEXTURE DETECTION
Dongmin Cha, Daijin Kim, Pohang University of Science and Technology, Korea, Republic of
Session:
Image/Graphics Processing, Analysis, and Coding
Track:
Multimedia Signal Processing
Location:
Gather Area O
Presentation Time:
Thu, 12 May, 23:00 - 23:45 China Time (UTC +8)
Thu, 12 May, 15:00 - 15:45 UTC
Thu, 12 May, 15:00 - 15:45 UTC
Session Co-Chairs:
Federica Battisti, University of Padova and Jibin Wu, National University of Singapore
Session MMSP-10
MMSP-10.1: DYNAMIC MULTI-SCALE LOSS BALANCE FOR OBJECT DETECTION
Yihao Luo, Xiang Cao, Juntao Zhang, Tianjiang Wang, Qi Feng, Huazhong University of Science and Technology, China; Peng Cheng, Coolanyp Limited Liability Company, Kirkland, State of Washington, USA, United States of America
MMSP-10.2: LATENT SPACE SLICING FOR ENHANCED ENTROPY MODELING IN LEARNING-BASED POINT CLOUD GEOMETRY COMPRESSION
Nicolas Frank, Davi Lazzarotto, Touradj Ebrahimi, École Polytechnique Fédérale de Lausanne (EPFL), Switzerland
MMSP-10.3: DAM-GAN : IMAGE INPAINTING USING DYNAMIC ATTENTION MAP BASED ON FAKE TEXTURE DETECTION
Dongmin Cha, Daijin Kim, Pohang University of Science and Technology, Korea, Republic of
MMSP-10.4: IMPROVING REFERENCE-BASED IMAGE COLORIZATION FOR LINE ARTS VIA FEATURE AGGREGATION AND CONTRASTIVE LEARNING
Shukai Wu, Qingqin Wang, Sanyuan Zhang, Zhejiang University, China; Shuchang Xu, Zhejiang University & Hangzhou Normal University & Wenzhou University, China
MMSP-10.5: FEW-SHOT GAZE ESTIMATION WITH MODEL OFFSET PREDICTORS
Jiawei Ma, Shih-Fu Chang, Columbia University, United States of America; Xu Zhang, Yue Wu, Varsha Hedau, Amazon Alexa AI, United States of America
MMSP-10.6: ADVERSARIAL EXAMPLES FOR IMAGE CROPPING IN SOCIAL MEDIA
Masatomo Yoshida, Masahiro Okuda, Doshisha University, Japan