# Video Object Detection on YouTube-BoundingBoxes Sparsely annotated

Source: [Video Object Detection on YouTube-BoundingBoxes Sparsely annotated](<https://www.sota2.com/research/sota/video-object-detection-on-youtube-boundingboxes-sparsely-annotated>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:09:31.063Z

Evaluation of Video Object Detection performance on the sparsely annotated split of the YouTube-BoundingBoxes dataset, typically measured using mAP.

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 Object Detection |
| Dataset (including any stated split) | YouTube-BoundingBoxes Sparsely annotated |
| Metric | mAP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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](<https://www.sota2.com/research/sota/video-object-detection-on-youtube-boundingboxes-sparsely-annotated.md?metric=mAP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP | Result date | Report paper |
| --- | --- | --- | --- |
| Location Anticipation (L\_traj^sa) | 59.8 | Not recorded | 68fa70481e209131cea4a2cc |
| Faster RCNN | 58.7 | Not recorded | 68fa70481e209131cea4a2cc |
| Location Anticipation (L\_traj) | 51.3 | Not recorded | 68fa70481e209131cea4a2cc |
| Faster RCNN | 47.6 | Not recorded | 68fa70481e209131cea4a2cc |

### Location Anticipation (L\_traj^sa)

mAP: 59.8. Result ID: 699111573a6c314849057116.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70481e209131cea4a2cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70481e209131cea4a2cc.md>)

[Implementation](<https://github.com/L-KID/Video-object-detection-by-location-anticipation>)

Recorded evaluation configuration: {"Keyframe step":30,"Label step":1}. This record does not assert independent reproduction.

### Faster RCNN

mAP: 58.7. Result ID: 699111573a6c314849057114.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70481e209131cea4a2cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62451e209131ce9f8655.md>)

[Implementation](<https://github.com/shaoqingren/faster_rcnn>)

Recorded evaluation configuration: {"Keyframe step":30,"Label step":30}. This record does not assert independent reproduction.

### Location Anticipation (L\_traj)

mAP: 51.3. Result ID: 699111573a6c314849057115.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70481e209131cea4a2cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70481e209131cea4a2cc.md>)

[Implementation](<https://github.com/L-KID/Video-object-detection-by-location-anticipation>)

Recorded evaluation configuration: {"Keyframe step":60,"Label step":30}. This record does not assert independent reproduction.

### Faster RCNN

mAP: 47.6. Result ID: 699111573a6c314849057113.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70481e209131cea4a2cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62451e209131ce9f8655.md>)

[Implementation](<https://github.com/shaoqingren/faster_rcnn>)

Recorded evaluation configuration: {"Keyframe step":60,"Label step":60}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.