# Generalized Zero-Shot Retrieval (Text-to-Audio) on AudioSet ZSL (test) Source: [Generalized Zero-Shot Retrieval (Text-to-Audio) on AudioSet ZSL (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:09:52.801Z Evaluation of Generalized Zero-Shot Retrieval performance, specifically Text-to-Audio, on the test split of the AudioSet ZSL dataset, measured using mAP for Seen (S), Unseen (U), and Harmonic Mean (HM) categories. 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 | Generalized Zero-Shot Retrieval (Text-to-Audio) | | Dataset (including any stated split) | AudioSet ZSL (test) | | Metric | mAP (S) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | 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 - [mAP (S)](): Higher is better; unit: PERCENT. - [mAP (U)](): Higher is better; unit: PERCENT. - [mAP (HM)](): Higher is better; unit: PERCENT. ## Recorded results | Method | mAP (S) | Result date | Report paper | | --- | --- | --- | --- | | AVGZSLNet | 72.25 | Not recorded | 68fa68c11e209131cea1e112 | | AVGZSLNet | 68.94 | Not recorded | 68fa68c11e209131cea1e112 | | CJME | 65.45 | Not recorded | 68fa68c11e209131cea1e112 | | CJME | 62.97 | Not recorded | 68fa68c11e209131cea1e112 | | AVGZSLNet | 62.2 | Not recorded | 68fa68c11e209131cea1e112 | | CJME | 59.39 | Not recorded | 68fa68c11e209131cea1e112 | | GCCA | 57.67 | Not recorded | 68fa68c11e209131cea1e112 | | AVGZSLNet | 51.55 | Not recorded | 68fa68c11e209131cea1e112 | | AVGZSLNet | 51.55 | Not recorded | 68fa68c11e209131cea1e112 | | GCCA | 49.84 | Not recorded | 68fa68c11e209131cea1e112 | | GCCA | 49.84 | Not recorded | 68fa68c11e209131cea1e112 | | video only model | 48.62 | Not recorded | 68fa68c11e209131cea1e112 | | CJME | 48.24 | Not recorded | 68fa68c11e209131cea1e112 | | CJME | 48.24 | Not recorded | 68fa68c11e209131cea1e112 | | audio only model | 43.16 | Not recorded | 68fa68c11e209131cea1e112 | | audio only model | 43.16 | Not recorded | 68fa68c11e209131cea1e112 | | pre-trained model | 3.83 | Not recorded | 68fa68c11e209131cea1e112 | | pre-trained model | 3.83 | Not recorded | 68fa68c11e209131cea1e112 | | pre-trained model | 3.83 | Not recorded | 68fa68c11e209131cea1e112 | ### AVGZSLNet mAP (S): 72.25. Result ID: 698d82e18b517eb433220cfc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Audio-Video","fusion":"equal weight"}. This record does not assert independent reproduction. ### AVGZSLNet mAP (S): 68.94. Result ID: 698d82e18b517eb433220cfe. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Audio-Video","fusion":"with attention"}. This record does not assert independent reproduction. ### CJME mAP (S): 65.45. Result ID: 698d82e18b517eb433220cfb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Audio-Video","fusion":"equal weight"}. This record does not assert independent reproduction. ### CJME mAP (S): 62.97. Result ID: 698d82e18b517eb433220cfd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Audio-Video","fusion":"with attention"}. This record does not assert independent reproduction. ### AVGZSLNet mAP (S): 62.2. Result ID: 698d82e18b517eb433220cfa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Video"}. This record does not assert independent reproduction. ### CJME mAP (S): 59.39. Result ID: 698d82e18b517eb433220cf9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Video"}. This record does not assert independent reproduction. ### GCCA mAP (S): 57.67. Result ID: 698d82e18b517eb433220cf7. [Reporting paper]() Recorded evaluation configuration: {"Test Direction":"Text to Video"}. This record does not assert independent reproduction. ### AVGZSLNet mAP (S): 51.55. Result ID: 698d82e18b517eb433220cd7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test":"T -\> A"}. This record does not assert independent reproduction. ### AVGZSLNet mAP (S): 51.55. Result ID: 698d82e18b517eb433220cf5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Audio"}. This record does not assert independent reproduction. ### GCCA mAP (S): 49.84. Result ID: 698d82e18b517eb433220cd4. [Reporting paper]() Recorded evaluation configuration: {"Test":"T -\> A"}. This record does not assert independent reproduction. ### GCCA mAP (S): 49.84. Result ID: 698d82e18b517eb433220cf2. [Reporting paper]() Recorded evaluation configuration: {"Test Direction":"Text to Audio"}. This record does not assert independent reproduction. ### video only model mAP (S): 48.62. Result ID: 698d82e18b517eb433220cf8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Video"}. This record does not assert independent reproduction. ### CJME mAP (S): 48.24. Result ID: 698d82e18b517eb433220cd6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test":"T -\> A"}. This record does not assert independent reproduction. ### CJME mAP (S): 48.24. Result ID: 698d82e18b517eb433220cf4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Audio"}. This record does not assert independent reproduction. ### audio only model mAP (S): 43.16. Result ID: 698d82e18b517eb433220cd5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test":"T -\> A"}. This record does not assert independent reproduction. ### audio only model mAP (S): 43.16. Result ID: 698d82e18b517eb433220cf3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Audio"}. This record does not assert independent reproduction. ### pre-trained model mAP (S): 3.83. Result ID: 698d82e18b517eb433220cd3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test":"T -\> A"}. This record does not assert independent reproduction. ### pre-trained model mAP (S): 3.83. Result ID: 698d82e18b517eb433220cf1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Audio"}. This record does not assert independent reproduction. ### pre-trained model mAP (S): 3.83. Result ID: 698d82e18b517eb433220cf6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Test Direction":"Text to Video"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.