# Video Sentence Grounding on ActivityNet Captions Source: [Video Sentence Grounding on ActivityNet Captions]() Collection index: [llms.txt]() Data updated: 2026-05-28T08:21:46.273Z Evaluation of Video Sentence Grounding performance on the ActivityNet Captions dataset, measured using Recall at K (R@1, R@5) conditioned on Intersection over Union thresholds of 0.3 and 0.5. 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 | Video Sentence Grounding | | Dataset (including any stated split) | ActivityNet Captions | | Metric | Recall@1 (IoU=0.5) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 32 of 32 | | 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 - [Recall@1 (IoU=0.5)](): Higher is better; unit: PERCENT. - [Recall@1 (IoU=0.3)](): Higher is better; unit: PERCENT. - [Recall@5 (IoU=0.3)](): Higher is better; unit: PERCENT. - [Recall@5 (IoU=0.5)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Recall@1 (IoU=0.5) | Result date | Report paper | | --- | --- | --- | --- | | BM-DETR + Ours | 54.35 | Not recorded | 6a17cc2fdbd7150506f8143c | | G2L + Ours | 54.26 | Not recorded | 6a17cc2fdbd7150506f8143c | | G2L | 51.68 | Not recorded | 6a17cc2fdbd7150506f8143c | | BM-DETR | 49.62 | Not recorded | 6a17cc2fdbd7150506f8143c | | MMN + Ours | 49.31 | Not recorded | 6a17cc2fdbd7150506f8143c | | MMN | 48.59 | Not recorded | 6a17cc2fdbd7150506f8143c | | BM-DETR + Ours | 47.93 | Not recorded | 6a17cc2fdbd7150506f8143c | | G2L + Ours | 46.86 | Not recorded | 6a17cc2fdbd7150506f8143c | | 2D-TAN + Ours | 45.29 | Not recorded | 6a17cc2fdbd7150506f8143c | | 2D-TAN | 44.51 | Not recorded | 6a17cc2fdbd7150506f8143c | | MCMT + Ours | 35.12 | Not recorded | 6a17cc2fdbd7150506f8143c | | CNM + Ours | 34.08 | Not recorded | 6a17cc2fdbd7150506f8143c | | MCMT | 33.97 | Not recorded | 6a17cc2fdbd7150506f8143c | | BM-DETR | 33.52 | Not recorded | 6a17cc2fdbd7150506f8143c | | CNM | 33.33 | Not recorded | 6a17cc2fdbd7150506f8143c | | VCA + Ours | 33.19 | Not recorded | 6a17cc2fdbd7150506f8143c | | MMN + Ours | 33.08 | Not recorded | 6a17cc2fdbd7150506f8143c | | G2L | 33.01 | Not recorded | 6a17cc2fdbd7150506f8143c | | 2D-TAN + Ours | 32.64 | Not recorded | 6a17cc2fdbd7150506f8143c | | MCMT + Ours | 32.42 | Not recorded | 6a17cc2fdbd7150506f8143c | | CNM + Ours | 31.77 | Not recorded | 6a17cc2fdbd7150506f8143c | | MMN | 31.76 | Not recorded | 6a17cc2fdbd7150506f8143c | | WSTAN + Ours | 31.56 | Not recorded | 6a17cc2fdbd7150506f8143c | | VCA | 31 | Not recorded | 6a17cc2fdbd7150506f8143c | | WSTAN | 30.01 | Not recorded | 6a17cc2fdbd7150506f8143c | | MCMT | 29.52 | Not recorded | 6a17cc2fdbd7150506f8143c | | 2D-TAN | 29.38 | Not recorded | 6a17cc2fdbd7150506f8143c | | CNM | 28.95 | Not recorded | 6a17cc2fdbd7150506f8143c | | VCA + Ours | 28.56 | Not recorded | 6a17cc2fdbd7150506f8143c | | WSTAN + Ours | 27.99 | Not recorded | 6a17cc2fdbd7150506f8143c | | WSTAN | 25.74 | Not recorded | 6a17cc2fdbd7150506f8143c | | VCA | 25.37 | Not recorded | 6a17cc2fdbd7150506f8143c | ### BM-DETR + Ours Recall@1 (IoU=0.5): 54.35. Result ID: 6a17fa16fbc373592c11a480. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### G2L + Ours Recall@1 (IoU=0.5): 54.26. Result ID: 6a17fa16fbc373592c11a47c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### G2L Recall@1 (IoU=0.5): 51.68. Result ID: 6a17fa16fbc373592c11a47a. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### BM-DETR Recall@1 (IoU=0.5): 49.62. Result ID: 6a17fa16fbc373592c11a47e. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### MMN + Ours Recall@1 (IoU=0.5): 49.31. Result ID: 6a17fa16fbc373592c11a478. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### MMN Recall@1 (IoU=0.5): 48.59. Result ID: 6a17fa16fbc373592c11a476. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### BM-DETR + Ours Recall@1 (IoU=0.5): 47.93. Result ID: 6a17fa16fbc373592c11a481. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### G2L + Ours Recall@1 (IoU=0.5): 46.86. Result ID: 6a17fa16fbc373592c11a47d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### 2D-TAN + Ours Recall@1 (IoU=0.5): 45.29. Result ID: 6a17fa16fbc373592c11a474. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### 2D-TAN Recall@1 (IoU=0.5): 44.51. Result ID: 6a17fa16fbc373592c11a472. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### MCMT + Ours Recall@1 (IoU=0.5): 35.12. Result ID: 6a17fa16fbc373592c11a490. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### CNM + Ours Recall@1 (IoU=0.5): 34.08. Result ID: 6a17fa16fbc373592c11a48c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### MCMT Recall@1 (IoU=0.5): 33.97. Result ID: 6a17fa16fbc373592c11a48e. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### BM-DETR Recall@1 (IoU=0.5): 33.52. Result ID: 6a17fa16fbc373592c11a47f. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### CNM Recall@1 (IoU=0.5): 33.33. Result ID: 6a17fa16fbc373592c11a48a. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### VCA + Ours Recall@1 (IoU=0.5): 33.19. Result ID: 6a17fa16fbc373592c11a484. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### MMN + Ours Recall@1 (IoU=0.5): 33.08. Result ID: 6a17fa16fbc373592c11a479. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### G2L Recall@1 (IoU=0.5): 33.01. Result ID: 6a17fa16fbc373592c11a47b. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### 2D-TAN + Ours Recall@1 (IoU=0.5): 32.64. Result ID: 6a17fa16fbc373592c11a475. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### MCMT + Ours Recall@1 (IoU=0.5): 32.42. Result ID: 6a17fa16fbc373592c11a491. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### CNM + Ours Recall@1 (IoU=0.5): 31.77. Result ID: 6a17fa16fbc373592c11a48d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### MMN Recall@1 (IoU=0.5): 31.76. Result ID: 6a17fa16fbc373592c11a477. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### WSTAN + Ours Recall@1 (IoU=0.5): 31.56. Result ID: 6a17fa16fbc373592c11a488. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### VCA Recall@1 (IoU=0.5): 31. Result ID: 6a17fa16fbc373592c11a482. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### WSTAN Recall@1 (IoU=0.5): 30.01. Result ID: 6a17fa16fbc373592c11a486. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"false"}. This record does not assert independent reproduction. ### MCMT Recall@1 (IoU=0.5): 29.52. Result ID: 6a17fa16fbc373592c11a48f. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### 2D-TAN Recall@1 (IoU=0.5): 29.38. Result ID: 6a17fa16fbc373592c11a473. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"fully-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### CNM Recall@1 (IoU=0.5): 28.95. Result ID: 6a17fa16fbc373592c11a48b. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### VCA + Ours Recall@1 (IoU=0.5): 28.56. Result ID: 6a17fa16fbc373592c11a485. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### WSTAN + Ours Recall@1 (IoU=0.5): 27.99. Result ID: 6a17fa16fbc373592c11a489. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### WSTAN Recall@1 (IoU=0.5): 25.74. Result ID: 6a17fa16fbc373592c11a487. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. ### VCA Recall@1 (IoU=0.5): 25.37. Result ID: 6a17fa16fbc373592c11a483. [Reporting paper]() Recorded evaluation configuration: {"Supervision":"weakly-supervised","Text Augmentation":"true"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.