14 papers
AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
Yiheng Li, Zhuo Li, Ruibing Hou +4
Conditional human motion generation remains a fundamental challenge in computer vision and robotics. Despite significant progress, current methods are often constrained by fixed mo…
Revisiting Multimodal Positional Encoding in Vision-Language Models
Jie Huang, Xuejing Liu, Sibo Song +4
Multimodal position encoding is essential for vision-language models, yet there has been little systematic investigation into multimodal position encoding. We conduct a comprehensi…
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen +3
The dense, temporal nature of video presents a profound challenge for automated analysis. Despite the use of powerful Vision-Language Models, prevailing methods for video understan…
Morph: A Motion-free Physics Optimization Framework for Human Motion Generation
Zhuo Li, Mingshuang Luo, Ruibing Hou +5
Human motion generation has been widely studied due to its crucial role in areas such as digital humans and humanoid robot control. However, many current motion generation approach…
DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning
Mingshuang Luo, Shuang Liang, Zhengkun Rong +7
Character image animation aims to synthesize high-fidelity videos by transferring motion from a driving sequence to a static reference image. Despite recent advancements, existing…
CLIP-Guided Adaptable Self-Supervised Learning for Human-Centric Visual Tasks
Mingshuang Luo, Ruibing Hou, Bo Chao +4
Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale un…