# Video-to-Text Retrieval on LSMDC (Robustness Metrics)

Source: [Video-to-Text Retrieval on LSMDC (Robustness Metrics)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics>)

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

Data updated: 2026-04-24T07:00:48.124Z

Evaluation of Video-to-Text retrieval performance on the LSMDC dataset, focusing on retrieval accuracy (R@1) under various visual corruption and style conditions (e.g., Gaussian blur, Fog, Motion, Defocus).

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) | LSMDC |
| Metric | Gaussian Blur R@1 |
| Unit | PERCENT |
| 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

- [Gaussian Blur R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Gaussian%20Blur%20R%401>): Higher is better; unit: PERCENT.

- [Impulse Noise R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Impulse%20Noise%20R%401>): Higher is better; unit: PERCENT.

- [Fog R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Fog%20R%401>): Higher is better; unit: PERCENT.

- [Snow R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Snow%20R%401>): Higher is better; unit: PERCENT.

- [Elastic Distortion R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Elastic%20Distortion%20R%401>): Higher is better; unit: PERCENT.

- [H.264 Compression R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=H.264%20Compression%20R%401>): Higher is better; unit: PERCENT.

- [Motion Blur R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Motion%20Blur%20R%401>): Higher is better; unit: PERCENT.

- [Defocus R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Defocus%20R%401>): Higher is better; unit: PERCENT.

- [Occlusion R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Occlusion%20R%401>): Higher is better; unit: PERCENT.

- [Style Transfer R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Style%20Transfer%20R%401>): Higher is better; unit: PERCENT.

- [Event Corruption R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Event%20Corruption%20R%401>): Higher is better; unit: PERCENT.

- [Temporal Corruption R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Temporal%20Corruption%20R%401>): Higher is better; unit: PERCENT.

- [Average R@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics.md?metric=Average%20R%401>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Gaussian Blur R@1 | Result date | Report paper |
| --- | --- | --- | --- |
| HAT-VTR | 14.31 | Not recorded | 69eaf90255a3c32af89f888d |
| HAT-VTR | 13.81 | Not recorded | 69eaf90255a3c32af89f888d |
| EATA | 12.01 | Not recorded | 69eaf90255a3c32af89f888d |
| TCR | 11.61 | Not recorded | 69eaf90255a3c32af89f888d |
| EATA | 11.61 | Not recorded | 69eaf90255a3c32af89f888d |
| TCR | 11.51 | Not recorded | 69eaf90255a3c32af89f888d |
| SAR | 11.01 | Not recorded | 69eaf90255a3c32af89f888d |
| Tent | 10.91 | Not recorded | 69eaf90255a3c32af89f888d |
| CLIP4Clip | 10.61 | Not recorded | 69eaf90255a3c32af89f888d |
| READ | 10.41 | Not recorded | 69eaf90255a3c32af89f888d |
| SAR | 9.91 | Not recorded | 69eaf90255a3c32af89f888d |
| Tent | 9.71 | Not recorded | 69eaf90255a3c32af89f888d |
| Xpool | 9.31 | Not recorded | 69eaf90255a3c32af89f888d |
| READ | 9.21 | Not recorded | 69eaf90255a3c32af89f888d |

### HAT-VTR

Gaussian Blur R@1: 14.31. Result ID: 69eb151647f34ce924d2ba6a.

[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

Gaussian Blur R@1: 13.81. Result ID: 69eb151647f34ce924d2ba63.

[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.

### EATA

Gaussian Blur R@1: 12.01. Result ID: 69eb151647f34ce924d2ba61.

[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.

### TCR

Gaussian Blur R@1: 11.61. Result ID: 69eb151647f34ce924d2ba62.

[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

Gaussian Blur R@1: 11.61. Result ID: 69eb151647f34ce924d2ba68.

[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.

### TCR

Gaussian Blur R@1: 11.51. Result ID: 69eb151647f34ce924d2ba69.

[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.

### SAR

Gaussian Blur R@1: 11.01. Result ID: 69eb151647f34ce924d2ba60.

[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.

### Tent

Gaussian Blur R@1: 10.91. Result ID: 69eb151647f34ce924d2ba5e.

[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.

### CLIP4Clip

Gaussian Blur R@1: 10.61. Result ID: 69eb151647f34ce924d2ba5d.

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

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

### READ

Gaussian Blur R@1: 10.41. Result ID: 69eb151647f34ce924d2ba5f.

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

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

### SAR

Gaussian Blur R@1: 9.91. Result ID: 69eb151647f34ce924d2ba67.

[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.

### Tent

Gaussian Blur R@1: 9.71. Result ID: 69eb151647f34ce924d2ba65.

[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.

### Xpool

Gaussian Blur R@1: 9.31. Result ID: 69eb151647f34ce924d2ba64.

[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

Gaussian Blur R@1: 9.21. Result ID: 69eb151647f34ce924d2ba66.

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

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

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