{
  "id": 4402,
  "url": "https://arxiv.org/abs/2605.13202v1",
  "title": "STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition",
  "summary": "Few-shot action recognition (FSAR) requires models to generalize to novel action categories from only a handful of annotated samples. Despite progress with vision-language models, existing approaches still suffer from semantic-temporal misalignment, where static textual prompts fail to capture decisive visual cues that appear sparsely across sequences, and from inadequate modeling of multi-scale temporal dynamics, as short-term discriminative cues and long-range dependencies are often either ove",
  "authors": "Hongli Liu, Yu Wang, Shengjie Zhao",
  "category": "research",
  "topics": "bias-fairness,safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-13T08:54:38.000Z",
  "fetched_at": "2026-07-14T16:30:59.236Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4402",
  "original_url": "https://arxiv.org/abs/2605.13202v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}