# Video-to-Text Retrieval on MSR-VTT 1kA

Source: [Video-to-Text Retrieval on MSR-VTT 1kA](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msr-vtt-1ka>)

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

Data updated: 2026-02-26T06:01:26.072Z

Evaluation of Video-to-Text Retrieval performance on the MSR-VTT 1kA subset, measured using Recall@K (R@1, R@5, R@10), Median Rank (MdR), Mean Rank (MeanR), and Sum of Ranks (rsum).

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) | MSR-VTT 1kA |
| Metric | Recall@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [Recall@1](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msr-vtt-1ka.md?metric=Recall%401>): Higher is better; unit: PERCENT.

- [Recall@5](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msr-vtt-1ka.md?metric=Recall%405>): Higher is better; unit: PERCENT.

- [Recall@10](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msr-vtt-1ka.md?metric=Recall%4010>): Higher is better; unit: PERCENT.

- [Median Rank (MdR)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msr-vtt-1ka.md?metric=Median%20Rank%20(MdR)>): Lower is better; unit: SCALAR.

- [Mean Rank (MeanR)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msr-vtt-1ka.md?metric=Mean%20Rank%20(MeanR)>): Lower is better; unit: SCALAR.

- [Sum of Ranks (rsum)](<https://www.sota2.com/research/sota/video-to-text-retrieval-on-msr-vtt-1ka.md?metric=Sum%20of%20Ranks%20(rsum)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Recall@1 | Result date | Report paper |
| --- | --- | --- | --- |
| Ourswti | 49.6 | Not recorded | 68fa792e1e209131cea7c773 |
| Baseline | 48 | Not recorded | 68fa792e1e209131cea7c773 |
| XCLIP | 47.9 | Not recorded | 68fa792e1e209131cea7c773 |
| Oursti | 47.9 | Not recorded | 68fa792e1e209131cea7c773 |
| TS2-Net | 47.8 | Not recorded | 68fa792e1e209131cea7c773 |
| CenterCLIP | 47.7 | Not recorded | 68fa792e1e209131cea7c773 |
| DRL+ | 47 | Not recorded | 68fa792e1e209131cea7c773 |
| CLIP2TV | 46.9 | Not recorded | 68fa792e1e209131cea7c773 |
| XCLIP | 46.7 | Not recorded | 68fa792e1e209131cea7c773 |
| DRL | 46.3 | Not recorded | 68fa792e1e209131cea7c773 |
| Ourswti | 46.2 | Not recorded | 68fa792e1e209131cea7c773 |
| Oursti | 46 | Not recorded | 68fa792e1e209131cea7c773 |
| Baseline | 45.5 | Not recorded | 68fa792e1e209131cea7c773 |
| TS2-Net | 44.8 | Not recorded | 68fa792e1e209131cea7c773 |
| CLIP2TV | 43.9 | Not recorded | 68fa792e1e209131cea7c773 |
| CenterCLIP | 42.8 | Not recorded | 68fa792e1e209131cea7c773 |

### Ourswti

Recall@1: 49.6. Result ID: 6995cd263badfaffe6d1963f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Implementation](<https://github.com/alipay/Ant-Multi-Modal-Framework>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/16"}. This record does not assert independent reproduction.

### Baseline

Recall@1: 48. Result ID: 6995cd263badfaffe6d1963d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Implementation](<https://github.com/alipay/Ant-Multi-Modal-Framework>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/16"}. This record does not assert independent reproduction.

### XCLIP

Recall@1: 47.9. Result ID: 6995cd263badfaffe6d1963b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d701e209131cea39e2f.md>)

[Implementation](<https://github.com/xuguohai/X-CLIP>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/16"}. This record does not assert independent reproduction.

### Oursti

Recall@1: 47.9. Result ID: 6995cd263badfaffe6d1963e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Implementation](<https://github.com/alipay/Ant-Multi-Modal-Framework>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/16"}. This record does not assert independent reproduction.

### TS2-Net

Recall@1: 47.8. Result ID: 6995cd263badfaffe6d1963c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cfd1e209131cea3725c.md>)

[Implementation](<https://github.com/yuqi657/ts2_net>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/16","re-training":"true"}. This record does not assert independent reproduction.

### CenterCLIP

Recall@1: 47.7. Result ID: 6995cd263badfaffe6d19638.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c7b1e209131cea343a5.md>)

[Implementation](<https://github.com/mzhaoshuai/CenterCLIP>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/16"}. This record does not assert independent reproduction.

### DRL+

Recall@1: 47. Result ID: 6995cd263badfaffe6d1963a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c001e209131cea31966.md>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/16","re-training":"true"}. This record does not assert independent reproduction.

### CLIP2TV

Recall@1: 46.9. Result ID: 6995cd263badfaffe6d19639.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1a1e209131cea37be2.md>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/16"}. This record does not assert independent reproduction.

### XCLIP

Recall@1: 46.7. Result ID: 6995cd263badfaffe6d19632.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d701e209131cea39e2f.md>)

[Implementation](<https://github.com/xuguohai/X-CLIP>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### DRL

Recall@1: 46.3. Result ID: 6995cd263badfaffe6d19633.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c001e209131cea31966.md>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/32","re-training":"true"}. This record does not assert independent reproduction.

### Ourswti

Recall@1: 46.2. Result ID: 6995cd263badfaffe6d19637.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Implementation](<https://github.com/alipay/Ant-Multi-Modal-Framework>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### Oursti

Recall@1: 46. Result ID: 6995cd263badfaffe6d19636.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Implementation](<https://github.com/alipay/Ant-Multi-Modal-Framework>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### Baseline

Recall@1: 45.5. Result ID: 6995cd263badfaffe6d19635.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Implementation](<https://github.com/alipay/Ant-Multi-Modal-Framework>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### TS2-Net

Recall@1: 44.8. Result ID: 6995cd263badfaffe6d19634.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cfd1e209131cea3725c.md>)

[Implementation](<https://github.com/yuqi657/ts2_net>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/32","re-training":"true"}. This record does not assert independent reproduction.

### CLIP2TV

Recall@1: 43.9. Result ID: 6995cd263badfaffe6d19631.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d1a1e209131cea37be2.md>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### CenterCLIP

Recall@1: 42.8. Result ID: 6995cd263badfaffe6d19630.

[Reporting paper](<https://www.sota2.com/research/paper/68fa792e1e209131cea7c773.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c7b1e209131cea343a5.md>)

[Implementation](<https://github.com/mzhaoshuai/CenterCLIP>)

Recorded evaluation configuration: {"Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

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