ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP
Open paper
Benchmark
Model
Rank
Results
zero-shot-cross-modal-retrieval-on-coco-2014
RISys-Lab/ReasonSigLIP-So14-384-S2 (extra data)
#5
Image-to-text R@1: 73.7
Rank counts only results with a code link.