# Text-to-Video Retrieval on MSR-VTT 1K (val)

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

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

Data updated: 2026-02-26T05:59:28.311Z

Evaluation of Text-to-Video Retrieval performance using the validation split of the MSR-VTT 1K dataset, measured by R@K and Median Rank (MdR).

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 | Text-to-Video Retrieval |
| Dataset (including any stated split) | MSR-VTT 1K (val) |
| Metric | R@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 38 of 38 |
| 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

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

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

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

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

- [MnR](<https://www.sota2.com/research/sota/text-to-video-retrieval-on-msr-vtt-1k-val.md?metric=MnR>): Lower is better; unit: SCALAR.

## Recorded results

| Method | R@1 | Result date | Report paper |
| --- | --- | --- | --- |
| Weighted Token-wise Interaction (WTI) | 53.3 | Not recorded | 68fa6c001e209131cea31966 |
| Cap4Video | 51.4 | Not recorded | 68fa6edf1e209131cea428a9 |
| Weighted Token-wise Interaction (WTI) | 50.2 | Not recorded | 68fa6c001e209131cea31966 |
| DRL | 50.2 | Not recorded | 68fa6edf1e209131cea428a9 |
| TS2-Net | 49.4 | Not recorded | 68fa6edf1e209131cea428a9 |
| Cap4Video | 49.3 | Not recorded | 68fa6edf1e209131cea428a9 |
| CenterCLIP | 48.4 | Not recorded | 68fa6edf1e209131cea428a9 |
| CLIP2TV | 48.3 | Not recorded | 68fa6edf1e209131cea428a9 |
| Weighted Token-wise Interaction (WTI) | 47.4 | Not recorded | 68fa6c001e209131cea31966 |
| DRL | 47.4 | Not recorded | 68fa6edf1e209131cea428a9 |
| QB-Norm | 47.2 | Not recorded | 68fa6edf1e209131cea428a9 |
| TS2-Net | 47 | Not recorded | 68fa6edf1e209131cea428a9 |
| X-Pool | 46.9 | Not recorded | 68fa6edf1e209131cea428a9 |
| CLIP2Video | 45.6 | Not recorded | 68fa6edf1e209131cea428a9 |
| CAMOE | 44.6 | Not recorded | 68fa6edf1e209131cea428a9 |
| CLIP4Clip | 44.5 | Not recorded | 68fa6c001e209131cea31966 |
| CLIP4Clip | 44.5 | Not recorded | 68fa6edf1e209131cea428a9 |
| CenterCLIP | 44.2 | Not recorded | 68fa6edf1e209131cea428a9 |
| WebVid2M | 38.5 | Not recorded | 68fa74c51e209131cea63b50 |
| BridgeFormer | 37.6 | Not recorded | 68fa6edf1e209131cea428a9 |
| HowToCaption | 37.6 | Not recorded | 68fa74c51e209131cea63b50 |
| TMVM | 36.2 | Not recorded | 68fa6edf1e209131cea428a9 |
| BLIP Initialization | 34.3 | Not recorded | 68fa74c51e209131cea63b50 |
| VideoCC3M | 33.9 | Not recorded | 68fa74c51e209131cea63b50 |
| Frozen | 32.5 | Not recorded | 68fa6edf1e209131cea428a9 |
| FROZEN | 31 | Not recorded | 68fa6c001e209131cea31966 |
| HowTo100M (ASRs) | 30.8 | Not recorded | 68fa74c51e209131cea63b50 |
| SupportSet | 30.1 | Not recorded | 68fa6edf1e209131cea428a9 |
| HTM-AA | 29.8 | Not recorded | 68fa74c51e209131cea63b50 |
| T2VLAD | 29.5 | Not recorded | 68fa6edf1e209131cea428a9 |
| HowTo100M (distant supervision) | 28.6 | Not recorded | 68fa74c51e209131cea63b50 |
| SUPPORT | 27.4 | Not recorded | 68fa6c001e209131cea31966 |
| MDMMT | 26.6 | Not recorded | 68fa6c001e209131cea31966 |
| MMT | 26.6 | Not recorded | 68fa6edf1e209131cea428a9 |
| ClipBERT | 22 | Not recorded | 68fa6c001e209131cea31966 |
| ClipBERT | 22 | Not recorded | 68fa6edf1e209131cea428a9 |
| UniVL | 21.2 | Not recorded | 68fa6c001e209131cea31966 |
| HERO | 16.8 | Not recorded | 68fa6c001e209131cea31966 |

### Weighted Token-wise Interaction (WTI)

R@1: 53.3. Result ID: 698eb91cffc3901de0a01cdb.

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

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

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

### Cap4Video

R@1: 51.4. Result ID: 699076233a6c31484900b7a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Implementation](<https://github.com/whwu95/Cap4Video>)

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

### Weighted Token-wise Interaction (WTI)

R@1: 50.2. Result ID: 698eb91cffc3901de0a01cda.

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

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

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

### DRL

R@1: 50.2. Result ID: 699076233a6c31484900b7a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

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

Recorded evaluation configuration: {"Venue":"arXiv'22","Backbone":"CLIP-ViT-B/16"}. This record does not assert independent reproduction.

### TS2-Net

R@1: 49.4. Result ID: 699076233a6c31484900b7a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

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

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

Recorded evaluation configuration: {"Venue":"ECCV'22","Backbone":"CLIP-ViT-B/16"}. This record does not assert independent reproduction.

### Cap4Video

R@1: 49.3. Result ID: 699076233a6c31484900b79e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Implementation](<https://github.com/whwu95/Cap4Video>)

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

### CenterCLIP

R@1: 48.4. Result ID: 699076233a6c31484900b7a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

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

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

Recorded evaluation configuration: {"Venue":"SIGIR'22","Backbone":"CLIP-ViT-B/16"}. This record does not assert independent reproduction.

### CLIP2TV

R@1: 48.3. Result ID: 699076233a6c31484900b79f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

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

Recorded evaluation configuration: {"Venue":"arXiv'21","Backbone":"CLIP-ViT-B/16"}. This record does not assert independent reproduction.

### Weighted Token-wise Interaction (WTI)

R@1: 47.4. Result ID: 698eb91cffc3901de0a01cd9.

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

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DRL

R@1: 47.4. Result ID: 699076233a6c31484900b79d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

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

Recorded evaluation configuration: {"Venue":"arXiv'22","Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### QB-Norm

R@1: 47.2. Result ID: 699076233a6c31484900b79b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c5e1e209131cea339ff.md>)

[Implementation](<https://vladbogo.github.io/QB-Norm/>)

Recorded evaluation configuration: {"Venue":"CVPR'22","Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### TS2-Net

R@1: 47. Result ID: 699076233a6c31484900b79c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

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

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

Recorded evaluation configuration: {"Venue":"ECCV'22","Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### X-Pool

R@1: 46.9. Result ID: 699076233a6c31484900b79a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.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: {"Venue":"CVPR'22","Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### CLIP2Video

R@1: 45.6. Result ID: 699076233a6c31484900b799.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a3e1e209131cea26f12.md>)

[Implementation](<https://github.com/CryhanFang/CLIP2Video>)

Recorded evaluation configuration: {"Venue":"arXiv'21","Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### CAMOE

R@1: 44.6. Result ID: 699076233a6c31484900b798.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b441e209131cea2d184.md>)

[Implementation](<https://github.com/starmemda/CAMoE/>)

Recorded evaluation configuration: {"Venue":"arXiv'21","Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### CLIP4Clip

R@1: 44.5. Result ID: 698eb91cffc3901de0a01cd8.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa69e61e209131cea24b15.md>)

[Implementation](<https://github.com/ArrowLuo/CLIP4Clip>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CLIP4Clip

R@1: 44.5. Result ID: 699076233a6c31484900b796.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

Recorded evaluation configuration: {"Venue":"arXiv'21","Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### CenterCLIP

R@1: 44.2. Result ID: 699076233a6c31484900b797.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

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

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

Recorded evaluation configuration: {"Venue":"SIGIR'22","Backbone":"CLIP-ViT-B/32"}. This record does not assert independent reproduction.

### WebVid2M

R@1: 38.5. Result ID: 69935b043a6c314849155955.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c8b1e209131cea349cb.md>)

[Implementation](<https://m-bain.github.io/webvid-dataset/>)

Recorded evaluation configuration: {"Video-Text Training Data":"WebVid2M \[4\]","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### BridgeFormer

R@1: 37.6. Result ID: 699076233a6c31484900b794.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c141e209131cea32017.md>)

Recorded evaluation configuration: {"Venue":"CVPR'22"}. This record does not assert independent reproduction.

### HowToCaption

R@1: 37.6. Result ID: 69935b043a6c314849155953.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b50.md>)

[Implementation](<https://www.sota2.com/github.com/ninatu/howtocaption>)

Recorded evaluation configuration: {"Video-Text Training Data":"HowToCaption (ours)","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### TMVM

R@1: 36.2. Result ID: 699076233a6c31484900b795.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d801e209131cea3a1dd.md>)

Recorded evaluation configuration: {"Venue":"NeurIPS'22"}. This record does not assert independent reproduction.

### BLIP Initialization

R@1: 34.3. Result ID: 69935b043a6c31484915594f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bd81e209131cea30874.md>)

[Implementation](<https://github.com/salesforce/BLIP>)

Recorded evaluation configuration: {"Video-Text Training Data":"None (BLIP initialization)","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### VideoCC3M

R@1: 33.9. Result ID: 69935b043a6c314849155954.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32ceb.md>)

Recorded evaluation configuration: {"Video-Text Training Data":"VideoCC3M \[39\]","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### Frozen

R@1: 32.5. Result ID: 699076233a6c31484900b793.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c8b1e209131cea349cb.md>)

[Implementation](<https://m-bain.github.io/webvid-dataset/>)

Recorded evaluation configuration: {"Venue":"ICCV'21"}. This record does not assert independent reproduction.

### FROZEN

R@1: 31. Result ID: 698eb91cffc3901de0a01cd7.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c8b1e209131cea349cb.md>)

[Implementation](<https://m-bain.github.io/webvid-dataset/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HowTo100M (ASRs)

R@1: 30.8. Result ID: 69935b043a6c314849155950.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2d1e209131cea32967.md>)

[Implementation](<https://www.robots.ox.ac.uk/~vgg/tan/>)

Recorded evaluation configuration: {"Video-Text Training Data":"HowTo100M with ASRs \[17\]","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### SupportSet

R@1: 30.1. Result ID: 699076233a6c31484900b792.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa691b1e209131cea2044f.md>)

Recorded evaluation configuration: {"Venue":"ICLR'21"}. This record does not assert independent reproduction.

### HTM-AA

R@1: 29.8. Result ID: 69935b043a6c314849155952.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2d1e209131cea32967.md>)

[Implementation](<https://www.robots.ox.ac.uk/~vgg/tan/>)

Recorded evaluation configuration: {"Video-Text Training Data":"HTM-AA (auto-aligned ASRs) \[17\]","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### T2VLAD

R@1: 29.5. Result ID: 699076233a6c31484900b791.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69c81e209131cea23f66.md>)

Recorded evaluation configuration: {"Venue":"CVPR'21"}. This record does not assert independent reproduction.

### HowTo100M (distant supervision)

R@1: 28.6. Result ID: 69935b043a6c314849155951.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cda1e209131cea36445.md>)

[Implementation](<https://github.com/facebookresearch/video-distant-supervision>)

Recorded evaluation configuration: {"Video-Text Training Data":"HowTo100M with distant supervision \[31\]","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### SUPPORT

R@1: 27.4. Result ID: 698eb91cffc3901de0a01cd6.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa691b1e209131cea2044f.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MDMMT

R@1: 26.6. Result ID: 698eb91cffc3901de0a01cd5.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa680d1e209131cea19dc1.md>)

[Implementation](<http://thoth.inrialpes.fr/research/MMT>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MMT

R@1: 26.6. Result ID: 699076233a6c31484900b790.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680d1e209131cea19dc1.md>)

[Implementation](<http://thoth.inrialpes.fr/research/MMT>)

Recorded evaluation configuration: {"Venue":"ECCV'20"}. This record does not assert independent reproduction.

### ClipBERT

R@1: 22. Result ID: 698eb91cffc3901de0a01cd4.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa694e1e209131cea216c8.md>)

[Implementation](<https://github.com/jayleicn/ClipBERT>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ClipBERT

R@1: 22. Result ID: 699076233a6c31484900b78f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428a9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa694e1e209131cea216c8.md>)

[Implementation](<https://github.com/jayleicn/ClipBERT>)

Recorded evaluation configuration: {"Venue":"CVPR'20"}. This record does not assert independent reproduction.

### UniVL

R@1: 21.2. Result ID: 698eb91cffc3901de0a01cd3.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa68541e209131cea1b878.md>)

[Implementation](<https://www.di.ens.fr/willow/research/howto100m/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HERO

R@1: 16.8. Result ID: 698eb91cffc3901de0a01cd2.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa686a1e209131cea1bf6a.md>)

[Implementation](<https://github.com/linjieli222/HERO>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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