SOTAVerified

Zero-shot Image Retrieval

Papers

Showing 2629 of 29 papers

TitleStatusHype
Revisiting CLIP: Efficient Alignment of 3D MRI and Tabular Data using Domain-Specific Foundation ModelsCode0
Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training BenchmarkCode0
Decoupling the Role of Data, Attention, and Losses in Multimodal TransformersCode0
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient PretrainingCode0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.