MMSP-L4.1
MOMA: MIXTURE-OF-MODALITY-ADAPTATIONS FOR TRANSFERRING KNOWLEDGE FROM IMAGE MODELS TOWARDS EFFICIENT AUDIO-VISUAL ACTION RECOGNITION
Kai Wang, Dimitrios Hatzinakos, University of Toronto, Canada
Session:
MMSP-L4: Pose, Gesture, and Action in Multimedia Lecture
Track:
Multimedia Signal Processing
Location:
Room 205A
Presentation Time:
Thu, 18 Apr, 08:20 - 08:40 (UTC +9)
Session Co-Chairs:
Naveen Kumar, Disney Research, US and Jianquan Liu, Visual Intelligence Research Laboratories, NEC Corporation, Japan
Session MMSP-L4
MMSP-L4.1: MOMA: MIXTURE-OF-MODALITY-ADAPTATIONS FOR TRANSFERRING KNOWLEDGE FROM IMAGE MODELS TOWARDS EFFICIENT AUDIO-VISUAL ACTION RECOGNITION
Kai Wang, Dimitrios Hatzinakos, University of Toronto, Canada
MMSP-L4.2: MUSIC-TO-DANCE POSES: LEARNING TO RETRIEVE DANCE POSES FROM MUSIC
Bo-Wei Tseng, Kenneth Yang, Yu-Hua Hu, Wen-Li Wei, Jen-Chun Lin, Academia Sinica, Taiwan
MMSP-L4.3: GESTURE GENERATION VIA DIFFUSION MODEL WITH ATTENTION MECHANISM
Lingling Li, Weicong Li, Qiyuan Ding, Sun Yat-Sen University, China; Chengpei Tang, Keze Wang, Sun Yat-sen University, China
MMSP-L4.4: Video-language Graph Convolutional Network for Human Action Recognition
Rui Zhang, Xiaoran Yan, Zhejiang Lab, China
MMSP-L4.5: Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework
Junkun Jiang, Jie Chen, Hong Kong Baptist University, Hong Kong
MMSP-L4.6: UNIFIED SPEECH AND GESTURE SYNTHESIS USING FLOW MATCHING
Shivam Mehta, Ruibo Tu, Simon Alexanderson, Jonas Beskow, Éva Székely, Gustav Eje Henter, KTH Royal Institute of Technology, Sweden
Contacts