14:00–14:10
Welcome and Opening
14:10–14:50
Human-Centered Interaction Detection and Applications
Prof. Xiao Wu, Southwest Jiaotong University
15:05–15:45
Building Brain-Inspired World Models for Embodied Navigation and Tracking
Prof. Junyu Gao, Institute of Automation, Chinese Academy of Sciences
15:45–16:25
Generate More with Less: Efficient Generation from Images to Video to 4D
Prof. Yicong Li, University of Science and Technology of China
16:25–16:32
Tomatoes, Potatoes, and Onions: Questioning the Need for Faces in Face Presentation Attack Detection
Guray Ozgur, Fadi Boutros, Naser Damer
16:32–16:40
TSRNet: Two Stream Attention and Retentive Network for Temporal Action Detection
Wei Runchen, Ke Lu, Kun Dong, Jian Xue
16:40–16:47
Preserve or Repair? Selective Boundary Policy for a World Action Model
Hui Xue, Gang Wen, Liqian Liang, Congyan Lang
16:47–16:55
Understanding Retailer-Assigned Recipe Segments: Multimodal Prediction, Attribution, and Popularity Analysis
Mehrdad Rostami, Mourad Oussalah
16:55–17:02
CausalPatch: Count-Constrained Causal Repair for User-Edited Multi-Shot Narratives
Zhihang Liu, Wenxuan Liu, Xin Wang, Wenwu Zhu
17:02–17:10
Internal and Observable Correlates of Perceived Dominance: A Multimodal Study of Audio and Physiology in Small-Group Interaction
Anna Obara, Meisam Jamshidi Seikavandi, Karim Haddad, Daniel Overholt, Alice Modica, Shan Ahmed Shaffi, Fabricio Batista Narcizo
17:10–17:30
Ref-SALT: Identity-Preserving Cross-Identity Reference Control for Portrait Relighting
Yunfei He, Xin Jin, Huirong Zhu
Provenance-Aware Detection of Recontextualized Multimodal Disinformation
Ivan Malashin, Vadim Tynchenko, Aleksei Borodulin
Human-Centric Multilingual Visual Question Answering for Second-Language Learning in Resource-Constrained Communities
Zheng Liu, Kunyu Yang, Yu Weng, Hanning Zhang, Chang Liu
PC-YOLO: A Small-target Detection Framework for Face Detection with P2 Detection Head and Gradient Re-balanced Scale-aware CIoU Loss
Shan Jiang, Junting Liu, Chaomurilige, Xuan Liu
One Sensor, Whole Body — 3D Body Pose from a Single Consumer Earbud IMU
Zhilin Guo, Boqiao Zhang, Oszkár Urbán, Josef Bengtson, Hakan Aktas, Wenzhao Li, Siyu Hong, Kyle Thomas Fogarty, Chenliang Zhou, Ali Senguel, Cengiz Oztireli
MATHDance: Mamba-Transformer Architecture with Uniform Tokenization for High-Quality 3D Dance Generation
Kaixing Yang, Xulong Tang, Ziqiao Peng, Yuxuan Hu, Xiangyue Zhang, Ke Qiu, Puwei Wang, Hongyan Liu, Zhaoxin Fan, Jun He
Relation-Aware Human Activity Graphs for Insider-Risk Attribution from Heterogeneous Non-Visual Streams
Lijuan Sun, Rongkai Zhang, Xu Wu
SENS: Stage-wise Endpoint Noise Steering for Endpoint Control in Text-to-Motion Generation
Xinyue Gao, Xiaokang Wang, Yidian Liu, Yutong Gao
17:10–17:30
Discussion and Closing