7 papers · 1 filter
Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation
Xinshun Wang, Peiming Li, Ziyi Wang +5
Human motion analysis tasks, such as temporal 3D pose estimation, motion prediction, and motion in-betweening, play an essential role in computer vision. However, current paradigms…
Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognition
Mengyuan Liu, Ziyi Wang, Peiming Li +1
RGB camera-based surveillance systems enable human action recognition for public safety and healthcare, yet raise serious privacy concerns. Existing methods rely on post-capture al…
Universal Skeleton Understanding via Differentiable Rendering and MLLMs
Ziyi Wang, Peiming Li, Xinshun Wang +3
Multimodal large language models (MLLMs) exhibit strong visual-language reasoning, yet cannot process structured, non-visual data such as human skeletons. Existing methods either c…
GenVideoLens: Where LVLMs Fall Short in AI-Generated Video Detection?
Yueying Zou, Pei Pei Li, Zekun Li +4
In recent years, AI-generated videos have become increasingly realistic and sophisticated. Meanwhile, Large Vision-Language Models (LVLMs) have shown strong potential for detecting…
UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling
Peiming Li, Ziyi Wang, Yulin Yuan +4
Point cloud videos capture dynamic 3D motion while reducing the effects of lighting and viewpoint variations, making them highly effective for recognizing subtle and continuous hum…
Recognizing Actions from Robotic View for Natural Human-Robot Interaction
Ziyi Wang, Peiming Li, Hong Liu +5
Natural Human-Robot Interaction (N-HRI) requires robots to recognize human actions at varying distances and states, regardless of whether the robot itself is in motion or stationar…