{
  "id": 18014,
  "url": "https://arxiv.org/abs/2608.09369v1",
  "title": "FeedbackTrack: Visual-Cortex-Inspired Cross-Frame Feedback for Transformer Tracking",
  "summary": "Visual object tracking requires effective temporal integration, yet most Transformer trackers still rely on predominantly feed-forward feature extraction. Existing temporal mechanisms typically update templates, prompts, queries, or prediction states, while intermediate representations are rarely reused to modulate corresponding processing stages. We propose \\textbf{FeedbackTrack}, a visual-cortex-inspired framework that introduces sparse, group-level layer-aligned cross-frame feedback into pret",
  "authors": "Yueyang Cang, Xiaoteng Zhang, Zhiyuan Ning, Yuchen He, Li Shi",
  "category": "research",
  "topics": "privacy-surveillance",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-10T09:48:11.000Z",
  "fetched_at": "2026-08-11T05:10:37.351Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/18014",
  "original_url": "https://arxiv.org/abs/2608.09369v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}