MMSP-9.6
BI-DIRECTIONAL MODALITY FUSION NETWORK FOR AUDIO-VISUAL EVENT LOCALIZATION
Shuo Liu, Weize Quan, University of Chinese Academy of Sciences; NLPR, Institute of Automation, Chinese Academy of Sciences, China; Yuan Liu, Speech Lab, Alibaba Group, China; Dong-Ming Yan, NLPR, Institute of Automation, Chinese Academy of Sciences, China
Session:
Human Centric Multimedia
Track:
Multimedia Signal Processing
Location:
Gather Area O
Presentation Time:
Thu, 12 May, 22:00 - 22:45 China Time (UTC +8)
Thu, 12 May, 14:00 - 14:45 UTC
Thu, 12 May, 14:00 - 14:45 UTC
Session Chair:
Ivan Bajic, Simon Fraser University
Session MMSP-9
MMSP-9.1: FROM BOTTOM-UP TO TOP-DOWN: CHARACTERIZATION OF TRAINING PROCESS IN GAZE MODELING
Ron Hecht, Ke Liu, Noa Garnett, Ariel Telpaz, Omer Tsimhoni, General Motors, Israel
MMSP-9.2: META TALK: LEARNING TO DATA-EFFICIENTLY GENERATE AUDIO-DRIVEN LIP-SYNCHRONIZED TALKING FACE WITH HIGH DEFINITION
Yuhan Zhang, Weihua He, Minglei Li, Kun Tian, Ziyang Zhang, Jie Cheng, Yaoyuan Wang, Jianxing Liao, Huawei Technologies Co., Ltd., China
MMSP-9.3: MAP: MULTISPECTRAL ADVERSARIAL PATCH TO ATTACK PERSON DETECTION
Taeheon Kim, Hong Joo Lee, Yong Man Ro, KAIST, Korea, Republic of
MMSP-9.4: Genre-Conditioned Long-Term 3D Dance Generation Driven by Music
Yuhang Huang, Junjie Zhang, Dan Zeng, Shanghai University, China; Shuyan Liu, University of Chinese Academy of Sciences, China; Qian Bao, Wu Liu, JD AI Research, China; Zhineng Chen, Fudan University, China
MMSP-9.5: LEARNING SOUND LOCALIZATION BETTER FROM SEMANTICALLY SIMILAR SAMPLES
Arda Senocak, Hyeonggon Ryu, In So Kweon, KAIST, Korea, Republic of; Junsik Kim, Harvard University, Korea, Republic of
MMSP-9.6: BI-DIRECTIONAL MODALITY FUSION NETWORK FOR AUDIO-VISUAL EVENT LOCALIZATION
Shuo Liu, Weize Quan, University of Chinese Academy of Sciences; NLPR, Institute of Automation, Chinese Academy of Sciences, China; Yuan Liu, Speech Lab, Alibaba Group, China; Dong-Ming Yan, NLPR, Institute of Automation, Chinese Academy of Sciences, China