Video-LLaMA’s IT

• Paper: Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding
• GitHub Link
• Publisher: EMNLP 2023
• Author Affiliation: Alibaba Group
• Type
  • SFT
  • RLHF
• Multi-turn
  • ✔
  • ✖
• Input Modalities $\rightarrow$ Output Modalities
  (I: Image, V: Video, A: Audio, 3D: Point Cloud, T: Text, B: Bounding box, Tab: Table, Web: Web page)
  • I/V+T $\rightarrow$ T
• Source
  • MiniGPT-4, LLaVA, and VideoChat’s IT
• Method
  • Auto.
• I/V/A Scale
  • I
    • 81K
  • V
    • 8K
  • A
    • Not report
• Dialog Turn
  • 2.22
• Instance Scale
  • 171K