Login / Signup

Single-Stream Multi-level Alignment for Vision-Language Pretraining.

Zaid KhanB. G. Vijay KumarXiang YuSamuel SchulterManmohan ChandrakerYun Fu
Published in: ECCV (36) (2022)
Keyphrases
  • real time
  • vision system
  • computer vision
  • databases
  • natural language
  • sliding window
  • information retrieval
  • image processing
  • face recognition
  • data streams
  • visual perception
  • english language
  • procrustes analysis