# Motion Description Retrieval on HMDB-51 (test) Source: [Motion Description Retrieval on HMDB-51 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:42.997Z Evaluation of motion description retrieval performance on the test split of the HMDB-51 dataset, measured using accuracy. 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 | Motion Description Retrieval | | Dataset (including any stated split) | HMDB-51 (test) | | Metric | Accuracy | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Accuracy](): Higher is better; unit: SCALAR. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Human estimate | 0.975 | Not recorded | 68fa73831e209131cea5cdc7 | | Human estimate | 0.96 | Not recorded | 68fa73831e209131cea5cdc7 | | Our Method | 0.3924 | Not recorded | 68fa73831e209131cea5cdc7 | | ViFiCLIP | 0.362 | Not recorded | 68fa73831e209131cea5cdc7 | | Text4Vis | 0.3412 | Not recorded | 68fa73831e209131cea5cdc7 | | XCLIP | 0.2935 | Not recorded | 68fa73831e209131cea5cdc7 | | ViFiCLIP | 0.289 | Not recorded | 68fa73831e209131cea5cdc7 | | Our Method | 0.2841 | Not recorded | 68fa73831e209131cea5cdc7 | | Vanilla CLIP | 0.2526 | Not recorded | 68fa73831e209131cea5cdc7 | | Text4Vis | 0.2493 | Not recorded | 68fa73831e209131cea5cdc7 | | XCLIP | 0.1935 | Not recorded | 68fa73831e209131cea5cdc7 | | Vanilla CLIP | 0.1667 | Not recorded | 68fa73831e209131cea5cdc7 | ### Human estimate Accuracy: 0.975. Result ID: 6992e4963a6c3148491236c9. [Reporting paper]() Recorded evaluation configuration: {"Description Variant":"Object"}. This record does not assert independent reproduction. ### Human estimate Accuracy: 0.96. Result ID: 6992e4963a6c3148491236ca. [Reporting paper]() Recorded evaluation configuration: {"Description Variant":"Masked Object"}. This record does not assert independent reproduction. ### Our Method Accuracy: 0.3924. Result ID: 6992e4963a6c3148491236c7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Description Variant":"Object"}. This record does not assert independent reproduction. ### ViFiCLIP Accuracy: 0.362. Result ID: 6992e4963a6c3148491236c5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Description Variant":"Object"}. This record does not assert independent reproduction. ### Text4Vis Accuracy: 0.3412. Result ID: 6992e4963a6c3148491236c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Description Variant":"Object"}. This record does not assert independent reproduction. ### XCLIP Accuracy: 0.2935. Result ID: 6992e4963a6c3148491236c1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Description Variant":"Object"}. This record does not assert independent reproduction. ### ViFiCLIP Accuracy: 0.289. Result ID: 6992e4963a6c3148491236c6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Description Variant":"Masked Object"}. This record does not assert independent reproduction. ### Our Method Accuracy: 0.2841. Result ID: 6992e4963a6c3148491236c8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Description Variant":"Masked Object"}. This record does not assert independent reproduction. ### Vanilla CLIP Accuracy: 0.2526. Result ID: 6992e4963a6c3148491236bf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Description Variant":"Object"}. This record does not assert independent reproduction. ### Text4Vis Accuracy: 0.2493. Result ID: 6992e4963a6c3148491236c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Description Variant":"Masked Object"}. This record does not assert independent reproduction. ### XCLIP Accuracy: 0.1935. Result ID: 6992e4963a6c3148491236c2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Description Variant":"Masked Object"}. This record does not assert independent reproduction. ### Vanilla CLIP Accuracy: 0.1667. Result ID: 6992e4963a6c3148491236c0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Description Variant":"Masked Object"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.