{
  "id": 204410,
  "title": "VQ-VAD: Vector-quantized Motion Representation Learning for Human-centric Video Anomaly Detection",
  "url": "https://urgent.news/2026/08/05/vq-vad-vector-quantized-motion-representation-learning-for-human",
  "topic": "finance",
  "section": "Finance & Markets",
  "published": "2026-08-05T17:12:39.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.05069v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Video Anomaly Detection (VAD) is inherently challenging due to the scarcity of anomalies and the large visual variability in surveillance footage, including changes in lighting, viewpoint, and human appearance. To mitigate visual noise and address privacy concerns, recent work has shifted to pose-based VAD, which focuses on motion dynamics rather than raw video data. However, existing pose-based…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}