Speech-to-Image Retrieval on Places audio caption dataset 1,000 image/caption (held out) benchmark leaderboard · SOTA2 Research

Speech-to-Image Retrieval on Places audio caption dataset 1,000 image/caption (held out)

0.271R@1MISA

Evaluation Results

Method	Links
MISA2018.04		0.271	0.567	0.701
SISA2018.04		0.23	0.525	0.665
SIMA2018.04		0.215	0.518	0.639
MISA2018.04		0.2	0.469	0.604
SISA2018.04		0.165	0.431	0.559
MISA2018.04		0.162	0.417	0.547
[43]2018.04		0.161	0.404	0.564
[19]2018.04		0.148	0.403	0.548
SIMA2018.04		0.147	0.375	0.506
SISA2018.04		0.136	0.365	0.503
SIMA2018.04		0.134	0.389	0.513
MISA2018.04		0.079	0.225	0.314
SIMA2018.04		0.073	0.213	0.284
SISA2018.04		0.063	0.191	0.274