Mix-DANN and dynamic-modal-distillation for video domain adaptation

• Main Authors: YIN, Yuehao, ZHU, Bin, CHEN, Jingjing, CHENG, Lechao, JIANG, Yu-Gang
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Dynamic-Modal-Distillation; Video Domain Adaptation; Adversarial Learning; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/9015; https://ink.library.smu.edu.sg/context/sis_research/article/10018/viewcontent/_ACM_MM_2022__MD_DMD.pdf
• Institution: Singapore Management University

Video domain adaptation is non-trivial due to video is inherently involved with multi-dimensional and multi-modal information. Existing works mainly adopt adversarial learning and self-supervised tasks to align features. Nevertheless, the explicit interaction between source and target in the tempora...