Video Object Detection On Imagenet Vid
평가 지표
MAP
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | MAP |
|---|---|
| yolov-making-still-image-object-detectors | 87.5 |
| sequence-level-semantics-aggregation-for | 82.69 |
| robust-and-efficient-post-processing-for | 84.2 |
| boxmask-revisiting-bounding-box-supervision | 80.7 |
| sequence-level-semantics-aggregation-for | 84.3 |
| practical-video-object-detection-via-feature | 93.2 |
| objects-do-not-disappear-video-object | 87.2 |
| objects-do-not-disappear-video-object | 91.3 |
| diffusionvid-denoising-object-boxes-with | 87.1 |
| spatio-temporal-learnable-proposals-for-end | 80.3 |
| temporal-shift-module-for-efficient-video | 76.3 |
| diffusionvid-denoising-object-boxes-with | 92.5 |
| learning-motion-priors-for-efficient-video | 81.7 |
| robust-and-efficient-post-processing-for | 75.1 |
| integrated-object-detection-and-tracking-with | 83.5 |
| transvod-end-to-end-video-object-detection | 90.1 |
| identity-consistent-aggregation-for-video | 85.8 |
| memory-enhanced-global-local-aggregation-for | 85.4 |
| ptseformer-progressive-temporal-spatial | 88.1 |
| looking-fast-and-slow-memory-guided-mobile | 63.9 |
| flow-guided-feature-aggregation-for-video | 80.1 |
| dafa-diversity-aware-feature-aggregation-for | 84.5 |
| temporal-roi-align-for-video-object | 84.3 |
| tgbformer-transformer-graphformer-blender | 90.3 |
| objects-do-not-disappear-video-object | 87.9 |
| robust-and-efficient-post-processing-for | 80.1 |
| boxmask-revisiting-bounding-box-supervision | 84.8 |
| mining-inter-video-proposal-relations-for | 85.5 |
| short-term-anchor-linking-and-long-term-self | 82.4 |
| video-sparse-transformer-with-attention | 91.1 |
| dafa-diversity-aware-feature-aggregation-for | 85.9 |
| robust-and-efficient-post-processing-for | 68.6 |
| mining-inter-video-proposal-relations-for | 83.8 |