Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 29, 2024Open Access

Modeling Caption Diversity in Contrastive Vision-Language Pretraining

View Full Paper
Ask AI
Bookmark
Share

Authors

SLSamuel LavoieHydro-QuébecPKPolina KirichenkoSupélecMIMark IbrahimCapital One (United States)

Discussion

Loading...

Member takes

Implication

Key Points

Key points are not available for this paper at this time.

Cite This Study

Lavoie et al. (2024) studied this question.

synapsesocial.com/papers/68e6d2d6b6db643587650484https://doi.org/10.48550/arxiv.2405.00740
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity2024 · 3 citations
  2. 2CLIP with Quality Captions: A Strong Pretraining for Vision Tasks2024 · 2 citations
  3. 3DreamLIP: Language-Image Pre-training with Long Captions2024
  4. 4Perceptual Image Quality Prediction: Are Contrastive Language–Image Pretraining (CLIP) Visual Features Effective?2024 · 9 citations
  5. 5RankCLIP: Ranking-Consistent Language-Image Pretraining2025 · 1 citations