# Video Multimodal Interpretation on LV-VIS (val)

Source: [Video Multimodal Interpretation on LV-VIS (val)](<https://www.sota2.com/research/sota/video-multimodal-interpretation-on-lv-vis-val>)

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

Data updated: 2026-03-24T13:26:38.310Z

Evaluation of model performance on the LV-VIS validation split for Video Multimodal Interpretation, measured using AP, AP50, and AP75.

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 Multimodal Interpretation |
| Dataset (including any stated split) | LV-VIS (val) |
| Metric | AP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [AP](<https://www.sota2.com/research/sota/video-multimodal-interpretation-on-lv-vis-val.md?metric=AP>): Higher is better; unit: PERCENT.

- [AP50](<https://www.sota2.com/research/sota/video-multimodal-interpretation-on-lv-vis-val.md?metric=AP50>): Higher is better; unit: PERCENT.

- [AP75](<https://www.sota2.com/research/sota/video-multimodal-interpretation-on-lv-vis-val.md?metric=AP75>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP | Result date | Report paper |
| --- | --- | --- | --- |
| SG-FSCFormer | 26 | Not recorded | 69c21a700636e5bf4afc471b |
| VideoGLaMM | 25.4 | Not recorded | 69c21a700636e5bf4afc471b |
| SG-FSCFormer | 25.2 | Not recorded | 69c21a700636e5bf4afc471b |
| SG-FSCFormer† | 24.8 | Not recorded | 69c21a700636e5bf4afc471b |
| OVFormer | 24.7 | Not recorded | 69c21a700636e5bf4afc471b |
| GLEE | 23.9 | Not recorded | 69c21a700636e5bf4afc471b |

### SG-FSCFormer

AP: 26. Result ID: 69c2910347f34ce924aad95e.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a700636e5bf4afc471b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21a700636e5bf4afc471b.md>)

Recorded evaluation configuration: {"Mask Decoder":"SAM2"}. This record does not assert independent reproduction.

### VideoGLaMM

AP: 25.4. Result ID: 69c2910347f34ce924aad95c.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a700636e5bf4afc471b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77921e209131cea740c1.md>)

[Implementation](<https://mbzuai-oryx.github.io/VideoGLaMM>)

Recorded evaluation configuration: {"Mask Decoder":"SAM2"}. This record does not assert independent reproduction.

### SG-FSCFormer

AP: 25.2. Result ID: 69c2910347f34ce924aad95b.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a700636e5bf4afc471b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21a700636e5bf4afc471b.md>)

Recorded evaluation configuration: {"Mask Decoder":"Mask2Former"}. This record does not assert independent reproduction.

### SG-FSCFormer†

AP: 24.8. Result ID: 69c2910347f34ce924aad95d.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a700636e5bf4afc471b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21a700636e5bf4afc471b.md>)

Recorded evaluation configuration: {"Mask Decoder":"SAM2","Evaluation Protocol":"instance-level AP"}. This record does not assert independent reproduction.

### OVFormer

AP: 24.7. Result ID: 69c2910347f34ce924aad95a.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a700636e5bf4afc471b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa740d1e209131cea5f796.md>)

Recorded evaluation configuration: {"Mask Decoder":"Mask2Former"}. This record does not assert independent reproduction.

### GLEE

AP: 23.9. Result ID: 69c2910347f34ce924aad959.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a700636e5bf4afc471b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71731e209131cea51508.md>)

[Implementation](<https://glee-vision.github.io/>)

Recorded evaluation configuration: {"Mask Decoder":"MaskDINO"}. This record does not assert independent reproduction.

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