Temporal Action Localization On Thumos14
Metrics
mAP IOU@0.1
mAP IOU@0.2
mAP IOU@0.3
mAP IOU@0.4
mAP IOU@0.5
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | mAP IOU@0.1 | mAP IOU@0.2 | mAP IOU@0.3 | mAP IOU@0.4 | mAP IOU@0.5 |
|---|---|---|---|---|---|
| graph-convolutional-module-for-temporal | 72.5 | 70.9 | 66.5 | 60.8 | 51.9 |
| temporalmaxer-maximize-temporal-context-with | - | - | 82.8 | 78.9 | 71.8 |
| cdc-convolutional-de-convolutional-networks | - | - | 40.1 | 29.4 | 23.3 |
| rethinking-the-faster-r-cnn-architecture-for | 59.8 | 57.1 | 53.2 | 48.5 | 42.8 |
| rgb-stream-is-enough-for-temporal-action | - | - | 62.8 | 59.5 | 53.8 |
| internvideo2-scaling-video-foundation-models | - | - | - | - | - |
| dual-detrs-for-multi-label-temporal-action | - | - | 82.9 | 78.0 | 70.4 |
| dcan-improving-temporal-action-detection-via | - | - | 68.2 | 62.7 | 54.1 |
| turn-tap-temporal-unit-regression-network-for | 54 | 50.9 | 44.1 | 34.9 | 25.6 |
| enhancing-temporal-action-localization | - | - | 88.7 | 84.6 | 78.2 |
| multi-shot-temporal-event-localization-a | - | - | 68.9 | 64.0 | 56.9 |
| tadml-a-fast-temporal-action-detection-with | - | - | 73.29 | 69.73 | 62.53 |
| tsp-temporally-sensitive-pretraining-of-video | 74.02 | 72.29 | 69.1 | 63.3 | 53.5 |
| react-temporal-action-detection-with | - | - | 69.2 | 65.0 | 57.1 |
| basictad-an-astounding-rgb-only-baseline-for | - | - | 75.5 | 70.8 | 63.5 |
| end-to-end-temporal-action-detection-with | - | - | 74.8 | 69.1 | 60.1 |
| videomae-v2-scaling-video-masked-autoencoders | - | - | 84.0 | 79.6 | 73.0 |
| internvideo2-scaling-video-foundation-models | - | - | - | - | - |
| internvideo-general-video-foundation-models | - | - | - | - | - |
| hear-me-out-fusional-approaches-for-audio | - | - | 70.1 | 64.9 | 57.1 |
| bmn-boundary-matching-network-for-temporal | - | - | - | - | 32.2 |
| graph-convolutional-networks-for-temporal | 69.5 | 67.8 | 63.6 | 57.8 | 49.1 |
| activity-graph-transformer-for-temporal | 72.1 | 69.8 | 65 | 58.1 | 50.2 |
| temporal-action-detection-with-global | - | - | 68.6 | 63.8 | 57.0 |
| action-sensitivity-learning-for-temporal | - | - | 83.1 | 79.0 | 71.7 |
| tadml-a-fast-temporal-action-detection-with | - | - | 68.78 | 64.66 | 56.61 |
| cascaded-boundary-regression-for-temporal | 60.1 | 56.7 | 50.1 | 41.3 | 31 |
| actionformer-localizing-moments-of-actions | - | - | 82.1 | 77.8 | 71.0 |
| weakly-supervised-temporal-action-1 | 62.3 | - | 46.8 | - | 29.6 |
| bsn-boundary-sensitive-network-for-temporal | - | - | 53.5 | 45 | 36.9 |
| temporal-action-localization-with-enhanced | - | - | 84.8 | 80.0 | 73.3 |
| tridet-temporal-action-detection-with | - | - | 83.6 | 80.1 | 72.9 |
| end-to-end-temporal-action-detection-with-1b | - | - | 89.7 | 86.7 | 80.9 |
| basictad-an-astounding-rgb-only-baseline-for | - | - | 68.4 | 65.0 | 58.6 |
| decoupling-localization-and-classification-in | - | - | 60.2 | 54.1 | 44.2 |
| g-tad-sub-graph-localization-for-temporal | - | - | - | - | 40.2 |
| end-to-end-learning-of-action-detection-from | 48.9 | 44.0 | 36.0 | 26.4 | 17.1 |
| r-c3d-region-convolutional-3d-network-for | 54.5 | 51.5 | 44.8 | 35.6 | 28.9 |
| an-empirical-study-of-end-to-end-temporal | - | - | 69.4 | 64.3 | 56.0 |
| temporal-action-localization-in-untrimmed | 47.7 | 43.5 | 36.3 | 28.7 | 19 |
| video-mamba-suite-state-space-model-as-a | - | - | 86.89 | 83.09 | 76.90 |
| video-self-stitching-graph-network-for | - | - | 66.7 | 60.4 | 52.4 |