• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions.

Jack UrbanekFlorian BordesPietro AstolfiMary WilliamsonVasu SharmaAdriana Romero-Soriano
Published in: CoRR (2023)
Keyphrases
  • probabilistic model
  • database
  • hidden markov models
  • free text
  • learning algorithm
  • model selection
  • visual features
  • web documents
  • experimental data