Login / Signup

X$^{2}$2-VLM: All-in-One Pre-Trained Model for Vision-Language Tasks.

Yan ZengXinsong ZhangHang LiJiawei WangJipeng ZhangWangchunshu Zhou
Published in: IEEE Trans. Pattern Anal. Mach. Intell. (2024)
Keyphrases
  • probabilistic model
  • machine learning
  • computer vision
  • prior knowledge
  • vision system
  • real scenes