5 papers
Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning
Shibo Gao, Peipei Yang, Xu-Yao Zhang +1
Video Anomaly Detection (VAD) aims to identify anomalous events and localize their temporal intervals. Existing approaches exhibit a "when-what" dissociation: traditional DNN-based…
I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning
Shibo Gao, Chongxiao Wang, Chenglong Huang +10
Real-world video reasoning often involves multimodal, multi-source inputs, whereas existing video reasoning tasks typically assume a simplified video-text setting, limiting identit…
Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients
Ziwei Xiang, Fanhu Zeng, Hongjian Fang +6
Large Vision Language Models (LVLMs) have achieved remarkable success in a range of downstream tasks that require multimodal interaction, but their capabilities come with substanti…
The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM
Shibo Gao, Peipei Yang, Haiyang Guo +7
Video anomaly detection (VAD) aims to identify and ground anomalous behaviors or events in videos, serving as a core technology in the fields of intelligent surveillance and public…
VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding
Shibo Gao, Peipei Yang, Yangyang Liu +4
Video Anomaly Detection (VAD) aims to identify anomalous events in videos and accurately determine their time intervals. Current VAD methods mainly fall into two categories: tradit…