# Video Summarization on QFVS (Vid 1-4)

Source: [Video Summarization on QFVS (Vid 1-4)](<https://www.sota2.com/research/sota/video-summarization-on-qfvs-vid-1-4>)

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

Data updated: 2026-02-26T05:42:52.370Z

Evaluation of video summarization performance on the QFVS dataset, reporting F1 scores segmented across videos 1 through 4, and the average F1 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 | Video Summarization |
| Dataset (including any stated split) | QFVS (Vid 1-4) |
| Metric | F1 (Vid 1) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [F1 (Vid 1)](<https://www.sota2.com/research/sota/video-summarization-on-qfvs-vid-1-4.md?metric=F1%20(Vid%201)>): Higher is better; unit: PERCENT.

- [F1 (Vid 2)](<https://www.sota2.com/research/sota/video-summarization-on-qfvs-vid-1-4.md?metric=F1%20(Vid%202)>): Higher is better; unit: PERCENT.

- [F1 (Vid 3)](<https://www.sota2.com/research/sota/video-summarization-on-qfvs-vid-1-4.md?metric=F1%20(Vid%203)>): Higher is better; unit: PERCENT.

- [F1 (Vid 4)](<https://www.sota2.com/research/sota/video-summarization-on-qfvs-vid-1-4.md?metric=F1%20(Vid%204)>): Higher is better; unit: PERCENT.

- [F1 (Avg)](<https://www.sota2.com/research/sota/video-summarization-on-qfvs-vid-1-4.md?metric=F1%20(Avg)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 (Vid 1) | Result date | Report paper |
| --- | --- | --- | --- |
| CLIP-It | 84.98 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| CLIP-It | 74.13 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| CLIP-It | 73.9 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| CLIP-Image + Transformer | 70.8 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| CLIP-It | 67.02 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| ResNet + Transformer | 66.97 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| CLIP-Image + Transformer | 65.44 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| CLIP-Image + bi-LSTM | 65.43 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| QFVS | 62.66 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| Quasi | 53.06 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| SubMod | 49.51 | Not recorded | 68fa6b5f1e209131cea2dc9f |

### CLIP-It

F1 (Vid 1): 84.98. Result ID: 698e81d2ffc3901de09e2e4a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

[Implementation](<https://medhini.github.io/clip_it>)

Recorded evaluation configuration: {"Supervision":"Supervised","Caption Source":"Ground Truth"}. This record does not assert independent reproduction.

### CLIP-It

F1 (Vid 1): 74.13. Result ID: 698e81d2ffc3901de09e2e49.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

[Implementation](<https://medhini.github.io/clip_it>)

Recorded evaluation configuration: {"Supervision":"Supervised","Caption Source":"Generated"}. This record does not assert independent reproduction.

### CLIP-It

F1 (Vid 1): 73.9. Result ID: 698e81d2ffc3901de09e2e4e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

[Implementation](<https://medhini.github.io/clip_it>)

Recorded evaluation configuration: {"Supervision":"Unsupervised","Caption Source":"Ground Truth"}. This record does not assert independent reproduction.

### CLIP-Image + Transformer

F1 (Vid 1): 70.8. Result ID: 698e81d2ffc3901de09e2e48.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

Recorded evaluation configuration: {"Supervision":"Supervised"}. This record does not assert independent reproduction.

### CLIP-It

F1 (Vid 1): 67.02. Result ID: 698e81d2ffc3901de09e2e4d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

[Implementation](<https://medhini.github.io/clip_it>)

Recorded evaluation configuration: {"Supervision":"Unsupervised","Caption Source":"Generated"}. This record does not assert independent reproduction.

### ResNet + Transformer

F1 (Vid 1): 66.97. Result ID: 698e81d2ffc3901de09e2e47.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

Recorded evaluation configuration: {"Supervision":"Supervised"}. This record does not assert independent reproduction.

### CLIP-Image + Transformer

F1 (Vid 1): 65.44. Result ID: 698e81d2ffc3901de09e2e4c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

Recorded evaluation configuration: {"Supervision":"Unsupervised"}. This record does not assert independent reproduction.

### CLIP-Image + bi-LSTM

F1 (Vid 1): 65.43. Result ID: 698e81d2ffc3901de09e2e46.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

Recorded evaluation configuration: {"Supervision":"Supervised"}. This record does not assert independent reproduction.

### QFVS

F1 (Vid 1): 62.66. Result ID: 698e81d2ffc3901de09e2e45.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63851e209131ce9ff3ab.md>)

Recorded evaluation configuration: {"Supervision":"Supervised"}. This record does not assert independent reproduction.

### Quasi

F1 (Vid 1): 53.06. Result ID: 698e81d2ffc3901de09e2e4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

Recorded evaluation configuration: {"Supervision":"Unsupervised"}. This record does not assert independent reproduction.

### SubMod

F1 (Vid 1): 49.51. Result ID: 698e81d2ffc3901de09e2e44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b5f1e209131cea2dc9f.md>)

Recorded evaluation configuration: {"Supervision":"Supervised"}. This record does not assert independent reproduction.

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