{
  "id": 17337,
  "url": "https://arxiv.org/abs/2608.06236v1",
  "title": "Depth-Guided Video Object Counting in Crowded Scenes",
  "summary": "Our primary objective is to advance video object counting in crowded scenes, aiming to robustly count all instances of a target category based on given text or visual prompts. Existing methods rely on RGB information, limiting their discriminative ability in crowded and occluded conditions. To address this, we propose a Depth-Guided Detector (DG-Det) along with a general post-processing pipeline. By integrating depth cues with multi-scale RGB-D cross-attention and explicit occlusion prediction,",
  "authors": "Yuanjing Xu, Xinyan Liu, Weidong Chen, Zixuan Zou, Linhao Zhang, Zhuangzhe Meng, Antoni B. Chan, Weigang Zhang",
  "category": "research",
  "topics": "bias-fairness",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-06T16:24:41.000Z",
  "fetched_at": "2026-08-07T05:10:58.501Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/17337",
  "original_url": "https://arxiv.org/abs/2608.06236v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}