pipixin321 / glancevad Goto Github PK

I am a Master of HUST (Huazhong University of Science and Technology), supervised by Nong Sang.

🔭 Reseach-wise, I mainly focus on:

• Multi-modal Large Language Models
• Video Understanding, more specifically, Weakly-supervised Temporal Action Localization (WSTAL) & Weakly-suervised Video Anomaly Detection (WSVAD).

😄 I am open to:

• A internship/job/PhD offer with computer vision/multimodal LLM research and engineering.

📫 Contact me by:

• Email: [email protected]

💬 News:

• 2024-07-01: We release our code and model of "Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM".[project page]
• 2024-06-10: We release our code and model of "Arcana: Improving Multi-modal Large Language Model through Boosting Vision Capabilities".[project page]
• 2024-01-29: I start my internship in Baidu VIS, to do some research on Multi-modal Large Language Model (MLLM).
• 2023-12-09: One paper about point supervised temporal action localization is accepted on AAAI 2024.