8 papers
R4DSG: Relative 4D Scene Graph Memory for Object-Centric Question Answering in Long Egocentric Video
Ke Ma, Yamin Mao, Weiming Li +5
Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it wa…
Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction
Yujie Wei, Chenglong Ma, Jianxiong Gao +6
Reconstructing dynamic visual experiences as videos from functional magnetic resonance imaging (fMRI) is pivotal for advancing the understanding of neural processes. However, curre…
SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation
Shuai Tan, Biao Gong, Yujie Wei +8
Diffusion-based video motion customization facilitates the acquisition of human motion representations from a few video samples, while achieving arbitrary subjects transfer through…
CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation
Shuai Tan, Biao Gong, Ke Ma +5
Character image animation is gaining significant importance across various domains, driven by the demand for robust and flexible multi-subject rendering. While existing methods exc…
PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models
Qiyuan Zhang, Biao Gong, Shuai Tan +7
Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation. This gap highlights a critical limitat…
Phys-Liquid: A Physics-Informed Dataset for Estimating 3D Geometry and Volume of Transparent Deformable Liquids
Ke Ma, Yizhou Fang, Jean-Baptiste Weibel +5
Estimating the geometric and volumetric properties of transparent deformable liquids is challenging due to optical complexities and dynamic surface deformations induced by containe…