Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detection
Wei-Chih Yin, Yun-Ching Kao, Cheng-Kuan Lin +1
Training-free zero-shot video anomaly detection (ZS-VAD) leverages vision-language models (VLMs) to localize anomaly instances from a predefined anomaly vocabulary, without providi…
cs.CV2024
MP-PolarMask: A Faster and Finer Instance Segmentation for Concave Images
Ke-Lei Wang, Pin-Hsuan Chou, Young-Ching Chou +3
While there are a lot of models for instance segmentation, PolarMask stands out as a unique one that represents an object by a Polar coordinate system. With an anchor-box-free desi…