# Image-to-Speech Retrieval on Places Audio Caption Dataset 1,000 image/caption (held out) Source: [Image-to-Speech Retrieval on Places Audio Caption Dataset 1,000 image/caption (held out)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:59:21.866Z Evaluation of Image-to-Speech Retrieval performance using the held-out set of the Places Audio Caption Dataset (1,000 image/caption pairs). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Image-to-Speech Retrieval | | Dataset (including any stated split) | Places Audio Caption Dataset 1,000 image/caption (held out) | | Metric | R@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [R@1](): Higher is better; unit: PERCENT. - [R@5](): Higher is better; unit: PERCENT. - [R@10](): Higher is better; unit: PERCENT. ## Recorded results | Method | R@1 | Result date | Report paper | | --- | --- | --- | --- | | SIMA | 13.9 | Not recorded | 68fa642c1e209131cea03264 | | \[43\] | 13 | Not recorded | 68fa642c1e209131cea03264 | | MISA | 12.7 | Not recorded | 68fa642c1e209131cea03264 | | \[19\] | 12.1 | Not recorded | 68fa642c1e209131cea03264 | | SISA | 12 | Not recorded | 68fa642c1e209131cea03264 | | SIMA | 6.5 | Not recorded | 68fa642c1e209131cea03264 | | MISA | 5.7 | Not recorded | 68fa642c1e209131cea03264 | | SISA | 4.8 | Not recorded | 68fa642c1e209131cea03264 | ### SIMA R@1: 13.9. Result ID: 698c1598f729bc7f68e8311d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ImageNet pre-trained":true}. This record does not assert independent reproduction. ### \[43\] R@1: 13. Result ID: 698c1598f729bc7f68e8311f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ImageNet pre-trained":true}. This record does not assert independent reproduction. ### MISA R@1: 12.7. Result ID: 698c1598f729bc7f68e8311c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ImageNet pre-trained":true}. This record does not assert independent reproduction. ### \[19\] R@1: 12.1. Result ID: 698c1598f729bc7f68e8311e. [Reporting paper]() Recorded evaluation configuration: {"ImageNet pre-trained":true}. This record does not assert independent reproduction. ### SISA R@1: 12. Result ID: 698c1598f729bc7f68e8311b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ImageNet pre-trained":true}. This record does not assert independent reproduction. ### SIMA R@1: 6.5. Result ID: 698c1598f729bc7f68e8311a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ImageNet pre-trained":false}. This record does not assert independent reproduction. ### MISA R@1: 5.7. Result ID: 698c1598f729bc7f68e83119. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ImageNet pre-trained":false}. This record does not assert independent reproduction. ### SISA R@1: 4.8. Result ID: 698c1598f729bc7f68e83118. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"ImageNet pre-trained":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.