by mbzuai-oryx · Agent Tool · ★ 97
VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos [CVPR 2025🔥] Shehan Munasinghe , Hanan Gani , Wenqi Zhu , Jiale Cao, Eric Xing, Fahad Shahbaz Khan. Salman Khan, Mohamed bin Zayed University of Artificial Intelligence, Tianjin University, Linköping University, Australian National University, Carnegie Mellon University 📢 Latest Updates Feb-2025: Video-GLaMM is accepted at CVPR 2025! 🎊🎊 Overview VideoGLaMM is a large video multimodal video model capable of pixel-level visual grounding.
| Stars | 97 |
| Forks | 5 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 63.3247097709818/100 |
| Open Issues | 8 |
| Last Updated | 2025-04-14 |
| Created | 2024-10-31 |
| Platforms | python |
| Est. Tokens | ~2718k |
Explore other popular agent tool tools:
VideoGLaMM is [CVPR 2025 🔥]A Large Multimodal Model for Pixel-Level Visual Grounding in Videos. It is categorized as a Agent Tool with 97 GitHub stars.
VideoGLaMM is primarily written in Python. It covers topics such as cvpr2025, foundation-models, llm-agent.
You can find installation instructions and usage details in the VideoGLaMM GitHub repository at github.com/mbzuai-oryx/VideoGLaMM. The project has 97 stars and 5 forks, indicating an active community.