Video-ChatGPT’s IT

• Paper: Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
• GitHub Link
• Publisher: Arxiv
• Author Affiliation: Mohamed bin Zayed University of AI
• 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)
  • V+T $\rightarrow$ T
• Source
  • ActivityNet
• Method
  • Inherit
• I/V/A Scale
  • I
    • Not report
  • V
    • 100K
  • A
    • Not report
• Dialog Turn
  • 1
• Instance Scale
  • 100K