{
  "id": 19190,
  "url": "https://arxiv.org/abs/2608.12843v1",
  "title": "Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval",
  "summary": "Text-based person anomaly retrieval aims to retrieve pedestrians exhibiting anomalous behaviors from a large image gallery using natural language descriptions. Compared with conventional text-based person retrieval, this task requires fine-grained reasoning over pedestrian appearance, behaviors, object interactions, and scene context, making robust cross-modal matching significantly more challenging. This paper presents the GENAI4E team's solution to AI City Challenge 2026 Track 4. Our framework",
  "authors": "Huu-An Vu, Cam Tu Tran Thi, Thanh Toan Le Ngo, Hoang Vo, Do Trung Hieu, Hieu Dinh Trung Pham et al.",
  "category": "research",
  "topics": null,
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T05:28:50.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/19190",
  "original_url": "https://arxiv.org/abs/2608.12843v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}