# Controllable Video Segmentation and Captioning on Video Dataset

Source: [Controllable Video Segmentation and Captioning on Video Dataset](<https://www.sota2.com/research/sota/controllable-video-segmentation-and-captioning-on-video-dataset>)

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

Data updated: 2026-03-24T13:26:38.289Z

Evaluation of controllable video segmentation and captioning performance on the Video Dataset, measured by inference speed (FPS).

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 | Controllable Video Segmentation and Captioning |
| Dataset (including any stated split) | Video Dataset |
| Metric | FPS |
| Unit | SCALAR |
| 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

- [FPS](<https://www.sota2.com/research/sota/controllable-video-segmentation-and-captioning-on-video-dataset.md?metric=FPS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FPS | Result date | Report paper |
| --- | --- | --- | --- |
| SAM2 | 10.61 | Not recorded | 69c21a700636e5bf4afc471b |
| MA-LMM | 7.35 | Not recorded | 69c21a700636e5bf4afc471b |
| VideoGLaMM | 5.13 | Not recorded | 69c21a700636e5bf4afc471b |
| SG-FSCFormer | 4.96 | Not recorded | 69c21a700636e5bf4afc471b |
| SMOTer | 4.82 | Not recorded | 69c21a700636e5bf4afc471b |
| OVFormer | 2.98 | Not recorded | 69c21a700636e5bf4afc471b |

### SAM2

FPS: 10.61. Result ID: 69c2910347f34ce924aad954.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa756f1e209131cea67e54.md>)

[Implementation](<https://github.com/facebookresearch/sam2>)

Recorded evaluation configuration: {"Hardware":"A6000 GPU"}. This record does not assert independent reproduction.

### MA-LMM

FPS: 7.35. Result ID: 69c2910347f34ce924aad955.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f61e209131cea59960.md>)

[Implementation](<https://boheumd.github.io/MA-LMM/>)

Recorded evaluation configuration: {"Hardware":"A6000 GPU"}. This record does not assert independent reproduction.

### VideoGLaMM

FPS: 5.13. Result ID: 69c2910347f34ce924aad957.

[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: {"Hardware":"A6000 GPU"}. This record does not assert independent reproduction.

### SG-FSCFormer

FPS: 4.96. Result ID: 69c2910347f34ce924aad958.

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

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

Recorded evaluation configuration: {"Hardware":"A6000 GPU"}. This record does not assert independent reproduction.

### SMOTer

FPS: 4.82. Result ID: 69c2910347f34ce924aad956.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa74441e209131cea60a56.md>)

Recorded evaluation configuration: {"Hardware":"A6000 GPU"}. This record does not assert independent reproduction.

### OVFormer

FPS: 2.98. Result ID: 69c2910347f34ce924aad953.

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

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

Recorded evaluation configuration: {"Hardware":"A6000 GPU"}. This record does not assert independent reproduction.

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