5 papers
ContextTom: Training-Free Video VLM Acceleration with Early Spatial Context
Yuqi Li, Neil Rodrigues, Xianglong Wang +8
Video vision-language models process thousands of visual tokens before producing an answer. Reducing these tokens early saves computation, but also determines which evidence reache…
TeQCo: Temporal Quota Consistency for Training-Free Video Token Compression
Yuqi Li, Xianglong Wang, Neil Rodrigues +8
Video token compression must control both temporal coverage and task relevance, but sequential stages can conflict: a content-driven allocation stage may be overwritten by a global…
IIR-VLM: In-Context Instance-level Recognition for Large Vision-Language Models
Liang Shi, Wei Li, Kevin M Beussman +2
Instance-level recognition (ILR) concerns distinguishing individual instances from one another, with person re-identification as a prominent example. Despite the impressive visual…
ALARM: Automated MLLM-Based Anomaly Detection in Complex-EnviRonment Monitoring with Uncertainty Quantification
Congjing Zhang, Feng Lin, Xinyi Zhao +5
The advance of Large Language Models (LLMs) has greatly stimulated research interest in developing multi-modal LLM (MLLM)-based visual anomaly detection (VAD) algorithms that can b…
SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models
Xinyi Zhao, Congjing Zhang, Pei Guo +4
Video anomaly detection (VAD) is essential for enhancing safety and security by identifying unusual events across different environments. Existing VAD benchmarks, however, are prim…