Login / Signup

Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment.

Xiaoxu XuYitian YuanQiudan ZhangWenhui WuZequn JieLin MaXu Wang
Published in: CoRR (2023)
Keyphrases
  • weakly supervised
  • low level
  • visual features
  • information retrieval
  • bayesian networks
  • multiscale
  • multi class