Login / Signup

UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding.

Dave Zhenyu ChenRonghang HuXinlei ChenMatthias NießnerAngel X. Chang
Published in: CoRR (2022)
Keyphrases
  • visual features
  • visual information
  • fuzzy logic
  • high level
  • low level
  • unified model
  • data sets
  • neural network
  • artificial neural networks
  • image classification
  • visual cues
  • visual perception
  • visual exploration