VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning

Documenti analoghi

• DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO
  di: Park, Jinyoung, et al.
  Pubblicazione: (2025)
• Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization
  di: Lee, Ji Soo, et al.
  Pubblicazione: (2025)
• Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection
  di: Kim, Jongha, et al.
  Pubblicazione: (2024)
• Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering
  di: Kim, Jongha, et al.
  Pubblicazione: (2026)
• Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning
  di: Jeon, MinJu, et al.
  Pubblicazione: (2025)