From the 1 of 6 linked papers with an AI index.
6 papers
UniVR: Thinking in Visual Space for Unified Visual Reasoning
Zhongwei Ren, Yunchao Wei, Yao Zhao +5
The paper presents UniVR, a system that learns complex visual reasoning, fine-grained physical dynamics, and long-term planning directly from raw video demonstrations using a novel…
MotionAtlas: Detailed Region Captioning for Motion-Centric Videos
Weisong Liu, Haochen Wang, Kuan Gao +8
We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to co…
VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification
Jiahao Meng, Tan Yue, Qi Xu +7
Recent video multimodal large language models achieve impressive results across various benchmarks. However, current evaluations suffer from two critical limitations: (1) inflated…
VideoWorld 2: Learning Transferable Knowledge from Real-world Videos
Zhongwei Ren, Yunchao Wei, Xiao Yu +5
Learning transferable knowledge from unlabeled video data and applying it in new environments is a fundamental capability of intelligent agents. This work presents VideoWorld 2, wh…
Can a Second-View Image Be a Language? Geometric and Semantic Cross-Modal Reasoning for X-ray Prohibited Item Detection
Chuang Peng, Renshuai Tao, Zhongwei Ren +2
Automatic X-ray prohibited items detection is vital for security inspection and has been widely studied. Traditional methods rely on visual modality, often struggling with complex…
VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
Zhongwei Ren, Yunchao Wei, Xun Guo +4
This work explores whether a deep generative model can learn complex knowledge solely from visual input, in contrast to the prevalent focus on text-based models like large language…