Less is More: Label-Guided Summarization of Procedural and Instructional Videos

Documenti analoghi

• Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models
  di: McLaughlin, Oliver, et al.
  Pubblicazione: (2026)
• Forgotten Polygons: Multimodal Large Language Models are Shape-Blind
  di: Rudman, William, et al.
  Pubblicazione: (2025)
• Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learning
  di: De Min, Thomas, et al.
  Pubblicazione: (2024)
• Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning
  di: Li, Xuchen, et al.
  Pubblicazione: (2025)
• Context-Aware Pseudo-Label Scoring for Zero-Shot Video Summarization
  di: Wu, Yuanli, et al.
  Pubblicazione: (2025)