# Video-to-Text Retrieval on MSVD MLVP (test)

Source: [Video-to-Text Retrieval on MSVD MLVP (test)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test>)

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

Data updated: 2026-04-24T07:00:48.284Z

Evaluation of Video-to-Text Retrieval performance on the MSVD MLVP test split, measured across various visual corruption and environmental conditions (e.g., Fog, Motion, Compression artifacts).

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-to-Text Retrieval |
| Dataset (including any stated split) | MSVD MLVP (test) |
| Metric | Score (Gaussian Noise) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Score (Gaussian Noise)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(Gaussian%20Noise)>): Higher is better; unit: SCALAR.

- [Score (Impulse Noise)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(Impulse%20Noise)>): Higher is better; unit: SCALAR.

- [Score (Fog)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(Fog)>): Higher is better; unit: SCALAR.

- [Score (Snow)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(Snow)>): Higher is better; unit: SCALAR.

- [Score (Elastic Distortion)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(Elastic%20Distortion)>): Higher is better; unit: SCALAR.

- [Score (H.264 Compression)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(H.264%20Compression)>): Higher is better; unit: SCALAR.

- [Score (Motion Blur)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(Motion%20Blur)>): Higher is better; unit: SCALAR.

- [Score (Defocus Blur)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(Defocus%20Blur)>): Higher is better; unit: SCALAR.

- [Score (Occlusion)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(Occlusion)>): Higher is better; unit: SCALAR.

- [Score (Style Corruption)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(Style%20Corruption)>): Higher is better; unit: SCALAR.

- [Score (Event Corruption)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(Event%20Corruption)>): Higher is better; unit: SCALAR.

- [Score (Temporal Corruption)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Score%20(Temporal%20Corruption)>): Higher is better; unit: SCALAR.

- [Average Retrieval Score](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test.md?metric=Average%20Retrieval%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score (Gaussian Noise) | Result date | Report paper |
| --- | --- | --- | --- |
| HAT-VTR | 36.57 | Not recorded | 69eaf90255a3c32af89f888d |
| HAT-VTR | 33.28 | Not recorded | 69eaf90255a3c32af89f888d |
| TCR | 32.09 | Not recorded | 69eaf90255a3c32af89f888d |
| EATA | 30 | Not recorded | 69eaf90255a3c32af89f888d |
| Tent | 28.21 | Not recorded | 69eaf90255a3c32af89f888d |
| SAR | 28.21 | Not recorded | 69eaf90255a3c32af89f888d |
| TCR | 28.06 | Not recorded | 69eaf90255a3c32af89f888d |
| EATA | 27.76 | Not recorded | 69eaf90255a3c32af89f888d |
| Xpool | 26.42 | Not recorded | 69eaf90255a3c32af89f888d |
| READ | 25.67 | Not recorded | 69eaf90255a3c32af89f888d |
| Tent | 25.07 | Not recorded | 69eaf90255a3c32af89f888d |
| SAR | 24.48 | Not recorded | 69eaf90255a3c32af89f888d |
| CLIP4Clip | 23.88 | Not recorded | 69eaf90255a3c32af89f888d |
| READ | 23.28 | Not recorded | 69eaf90255a3c32af89f888d |

### HAT-VTR

Score (Gaussian Noise): 36.57. Result ID: 69eb151647f34ce924d2bafd.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

Recorded evaluation configuration: {"Base Model":"Xpool"}. This record does not assert independent reproduction.

### HAT-VTR

Score (Gaussian Noise): 33.28. Result ID: 69eb151647f34ce924d2baf6.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

Recorded evaluation configuration: {"Base Model":"CLIP4Clip"}. This record does not assert independent reproduction.

### TCR

Score (Gaussian Noise): 32.09. Result ID: 69eb151647f34ce924d2bafc.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75561e209131cea6749e.md>)

Recorded evaluation configuration: {"Base Model":"Xpool"}. This record does not assert independent reproduction.

### EATA

Score (Gaussian Noise): 30. Result ID: 69eb151647f34ce924d2bafb.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea35123.md>)

Recorded evaluation configuration: {"Base Model":"Xpool"}. This record does not assert independent reproduction.

### Tent

Score (Gaussian Noise): 28.21. Result ID: 69eb151647f34ce924d2baf8.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69941e209131cea22d2b.md>)

Recorded evaluation configuration: {"Base Model":"Xpool"}. This record does not assert independent reproduction.

### SAR

Score (Gaussian Noise): 28.21. Result ID: 69eb151647f34ce924d2bafa.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e961e209131cea40e77.md>)

Recorded evaluation configuration: {"Base Model":"Xpool"}. This record does not assert independent reproduction.

### TCR

Score (Gaussian Noise): 28.06. Result ID: 69eb151647f34ce924d2baf5.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75561e209131cea6749e.md>)

Recorded evaluation configuration: {"Base Model":"CLIP4Clip"}. This record does not assert independent reproduction.

### EATA

Score (Gaussian Noise): 27.76. Result ID: 69eb151647f34ce924d2baf4.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ca11e209131cea35123.md>)

Recorded evaluation configuration: {"Base Model":"CLIP4Clip"}. This record does not assert independent reproduction.

### Xpool

Score (Gaussian Noise): 26.42. Result ID: 69eb151647f34ce924d2baf7.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c161e209131cea320b3.md>)

[Implementation](<https://www.sota2.com/layer6ai-labs.github.io/xpool/>)

Recorded evaluation configuration: {"Base Model":"Xpool"}. This record does not assert independent reproduction.

### READ

Score (Gaussian Noise): 25.67. Result ID: 69eb151647f34ce924d2baf9.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

Recorded evaluation configuration: {"Base Model":"Xpool"}. This record does not assert independent reproduction.

### Tent

Score (Gaussian Noise): 25.07. Result ID: 69eb151647f34ce924d2baf1.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69941e209131cea22d2b.md>)

Recorded evaluation configuration: {"Base Model":"CLIP4Clip"}. This record does not assert independent reproduction.

### SAR

Score (Gaussian Noise): 24.48. Result ID: 69eb151647f34ce924d2baf3.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e961e209131cea40e77.md>)

Recorded evaluation configuration: {"Base Model":"CLIP4Clip"}. This record does not assert independent reproduction.

### CLIP4Clip

Score (Gaussian Noise): 23.88. Result ID: 69eb151647f34ce924d2baf0.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

Recorded evaluation configuration: {"Base Model":"CLIP4Clip"}. This record does not assert independent reproduction.

### READ

Score (Gaussian Noise): 23.28. Result ID: 69eb151647f34ce924d2baf2.

[Reporting paper](<https://www.sota2.com/research/paper/69eaf90255a3c32af89f888d.md>)

Recorded evaluation configuration: {"Base Model":"CLIP4Clip"}. This record does not assert independent reproduction.

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