Cross Modal Retrieval On Soundingearth
评估指标
Image-to-sound R@100
Median Rank
Sound-to-image R@100
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | ||||
|---|---|---|---|---|---|
| GeoCLAP | 0.434 | 159 | 0.434 | Learning Tri-modal Embeddings for Zero-Shot Soundscape Mapping | |
| ResNet-18 | 0.291 | 565 | 0.250 | Self-supervised Audiovisual Representation Learning for Remote Sensing Data |
0 of 2 row(s) selected.