SCAN i-t

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision3 results

Image RetrievalonFlickr30K 1K test
R@1· 2018-03-21
44
best: 86.9 (X-VLM (base))
SOTA
Stacked Cross Attention for Image-Text Matching arXiv:1803.08024
Image RetrievalonFlickr30K 1K test
R@10· 2018-03-21
82.6
best: 98.7 (X-VLM (base))
SOTA
Stacked Cross Attention for Image-Text Matching arXiv:1803.08024
Image RetrievalonFlickr30K 1K test
R@5· 2018-03-21
74.2
best: 97.3 (X-VLM (base))
SOTA
Stacked Cross Attention for Image-Text Matching arXiv:1803.08024