Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding

Documenti analoghi

• Tarsier: Recipes for Training and Evaluating Large Video Description Models
  di: Wang, Jiawei, et al.
  Pubblicazione: (2024)
• Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models
  di: Chen, Shimin, et al.
  Pubblicazione: (2024)
• Boximator: Generating Rich and Controllable Motions for Video Synthesis
  di: Wang, Jiawei, et al.
  Pubblicazione: (2024)
• StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification
  di: He, Yichen, et al.
  Pubblicazione: (2024)
• From Evaluation to Defense: Advancing Safety in Video Large Language Models
  di: Sun, Yiwei, et al.
  Pubblicazione: (2025)