Signals 4 · free daily AI digest

Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection

Paper recorded by Signals 4 on 2026-09-15 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-15 on arXiv · recorded by Signals 4 on 2026-09-16

Category: cs.CV · 计算机视觉 · first seen 2026-09-16

Abstract

Video anomaly detection (VAD) aims to localize anomalous events in untrimmed videos. Vision-language models (VLMs) provide rich visual understanding for training-free VAD, but existing approaches impose restrictive interfaces between visual understanding and anomaly scoring. Caption-based pipelines compress visual evidence into text, potentially discarding subtle cues, while direct numerical gener

Read on arXiv →

#42 most recent of 237 cs.CV papers we have recorded · ↑ newer: InfoTaxa: Information-Calibrated Label-Free Clustering for Fine-Graine · ↓ older: EventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction wi
Cite this page: Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection: the #42 most recent of 237 cs.CV papers we have recorded (as of 2026-09-15). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/probe-vad-ordinal-likelihood-probing-for-training-free-video-anomaly-detection.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions