# Interactive Video Feedback Generation on QEVD-FIT-COACH

Source: [Interactive Video Feedback Generation on QEVD-FIT-COACH](<https://www.sota2.com/research/sota/interactive-video-feedback-generation-on-qevd-fit-coach>)

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

Data updated: 2026-04-14T10:20:55.318Z

Evaluation of models generating interactive video feedback using the QEVD-FIT-COACH dataset, assessed using generation metrics (METEOR, ROUGE-L) and specialized accuracy/score metrics (BERT, LLM-Acc., T-F-Score).

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 | Interactive Video Feedback Generation |
| Dataset (including any stated split) | QEVD-FIT-COACH |
| Metric | METEOR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [METEOR](<https://www.sota2.com/research/sota/interactive-video-feedback-generation-on-qevd-fit-coach.md?metric=METEOR>): Higher is better; unit: SCALAR.

- [ROUGE-L](<https://www.sota2.com/research/sota/interactive-video-feedback-generation-on-qevd-fit-coach.md?metric=ROUGE-L>): Higher is better; unit: SCALAR.

- [BERT Score](<https://www.sota2.com/research/sota/interactive-video-feedback-generation-on-qevd-fit-coach.md?metric=BERT%20Score>): Higher is better; unit: SCALAR.

- [LLM Accuracy](<https://www.sota2.com/research/sota/interactive-video-feedback-generation-on-qevd-fit-coach.md?metric=LLM%20Accuracy>): Higher is better; unit: SCALAR.

- [T-F Score](<https://www.sota2.com/research/sota/interactive-video-feedback-generation-on-qevd-fit-coach.md?metric=T-F%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | METEOR | Result date | Report paper |
| --- | --- | --- | --- |
| STREAM-VLM | 0.127 | Not recorded | 68fa76581e209131cea6c823 |
| STREAM-VLM (w/o Action-Tokens) | 0.125 | Not recorded | 68fa76581e209131cea6c823 |
| Video-ChatGPT | 0.108 | Not recorded | 68fa76581e209131cea6c823 |
| LLaMA-VID | 0.106 | Not recorded | 68fa76581e209131cea6c823 |
| STREAM-VLM (w/o Pre-training) | 0.095 | Not recorded | 68fa76581e209131cea6c823 |
| Socratic-LLaMA-2-7B | 0.094 | Not recorded | 68fa76581e209131cea6c823 |
| STREAM-VLM (w/o 3D CNN) | 0.09 | Not recorded | 68fa76581e209131cea6c823 |

### STREAM-VLM

METEOR: 0.127. Result ID: 69de14ff47f34ce924c61f3c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76581e209131cea6c823.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76581e209131cea6c823.md>)

Recorded evaluation configuration: {"Fine-tuned on QEVD":"true"}. This record does not assert independent reproduction.

### STREAM-VLM (w/o Action-Tokens)

METEOR: 0.125. Result ID: 69de14ff47f34ce924c61f3f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76581e209131cea6c823.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76581e209131cea6c823.md>)

Recorded evaluation configuration: {"Fine-tuned on QEVD":"true","Action-Tokens":"false","Evaluation mode":"non-interactive (evaluated at regular intervals)"}. This record does not assert independent reproduction.

### Video-ChatGPT

METEOR: 0.108. Result ID: 69de14ff47f34ce924c61f3a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76581e209131cea6c823.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73841e209131cea5ce32.md>)

[Implementation](<https://github.com/mbzuai-oryx/Video-ChatGPT>)

Recorded evaluation configuration: {"Fine-tuned on QEVD":"true","Fine-tuned by":"ourselves","Evaluation mode":"non-interactive (evaluated at regular intervals)"}. This record does not assert independent reproduction.

### LLaMA-VID

METEOR: 0.106. Result ID: 69de14ff47f34ce924c61f3b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76581e209131cea6c823.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea50559.md>)

[Implementation](<https://github.com/dvlab-research/LLaMA-VID>)

Recorded evaluation configuration: {"Fine-tuned on QEVD":"true","Fine-tuned by":"ourselves","Evaluation mode":"non-interactive (evaluated at regular intervals)"}. This record does not assert independent reproduction.

### STREAM-VLM (w/o Pre-training)

METEOR: 0.095. Result ID: 69de14ff47f34ce924c61f3e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76581e209131cea6c823.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76581e209131cea6c823.md>)

Recorded evaluation configuration: {"Fine-tuned on QEVD":"true","Pre-training":"false"}. This record does not assert independent reproduction.

### Socratic-LLaMA-2-7B

METEOR: 0.094. Result ID: 69de14ff47f34ce924c61f39.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76581e209131cea6c823.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca51e209131cea3533c.md>)

[Implementation](<https://www.sota2.com/socraticmodels.github.io>)

Recorded evaluation configuration: {"Fine-tuned on QEVD":"true","Evaluation mode":"non-interactive (evaluated at regular intervals)"}. This record does not assert independent reproduction.

### STREAM-VLM (w/o 3D CNN)

METEOR: 0.09. Result ID: 69de14ff47f34ce924c61f3d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76581e209131cea6c823.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76581e209131cea6c823.md>)

Recorded evaluation configuration: {"Fine-tuned on QEVD":"true","3D CNN":"false"}. This record does not assert independent reproduction.

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