ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data
Open paper
Benchmark
Model
Rank
Results
zero-shot-cross-modal-retrieval-on-coco-2014
ImageBERT
–
Image-to-text R@1: 44.0
Image-to-text R@5: 71.2
…
zero-shot-cross-modal-retrieval-on-flickr30k
ImageBERT
–
Image-to-text R@1: 70.7
Image-to-text R@5: 90.2
…
Rank counts only results with a code link.