DVSA (R-CNN, AlexNet)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision2 results

Image RetrievalonFlickr30K 1K test
R@1· 2014-12-07
15.2
best: 86.9 (X-VLM (base))
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306
Image RetrievalonFlickr30K 1K test
R@10· 2014-12-07
50.5
best: 98.7 (X-VLM (base))
SOTA
Deep Visual-Semantic Alignments for Generating Image Descriptions arXiv:1412.2306