{
  "id": 6076,
  "url": "https://arxiv.org/abs/2604.09063v3",
  "title": "Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition",
  "summary": "Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiveness of supervised skeleton-based methods, their reliance on exhaustive annotation limits generalization to novel actions. Zero-Shot Skeleton Action Recognition (ZSAR) emerges as a promising paradigm, yet it faces challenges due to the spectral bias of diffusion models, which oversmooth high-frequency dynamics. Here, we propose Frequency-Aware Diffu",
  "authors": "Yuxi Zhou, Zhengbo Zhang, Jingyu Pan, Zhiyu Lin, Zhigang Tu",
  "category": "research",
  "topics": "bias-fairness,safety-alignment,privacy-surveillance,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-10T07:42:47.000Z",
  "fetched_at": "2026-07-14T16:32:15.634Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6076",
  "original_url": "https://arxiv.org/abs/2604.09063v3",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}