# Query-focused Video Summarization on QFVS

Source: [Query-focused Video Summarization on QFVS](<https://www.sota2.com/research/sota/query-focused-video-summarization-on-qfvs>)

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

Data updated: 2026-02-26T06:08:16.268Z

Evaluation of query-focused video summarization performance on the QFVS dataset, using metrics specific to individual video results and their average.

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 | Query-focused Video Summarization |
| Dataset (including any stated split) | QFVS |
| Metric | Video Score 1 |
| Unit | SCALAR |
| 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

- [Video Score 1](<https://www.sota2.com/research/sota/query-focused-video-summarization-on-qfvs.md?metric=Video%20Score%201>): Higher is better; unit: SCALAR.

- [Video Score 2](<https://www.sota2.com/research/sota/query-focused-video-summarization-on-qfvs.md?metric=Video%20Score%202>): Higher is better; unit: SCALAR.

- [Video Score 3](<https://www.sota2.com/research/sota/query-focused-video-summarization-on-qfvs.md?metric=Video%20Score%203>): Higher is better; unit: SCALAR.

- [Video Score 4](<https://www.sota2.com/research/sota/query-focused-video-summarization-on-qfvs.md?metric=Video%20Score%204>): Higher is better; unit: SCALAR.

- [Average Score](<https://www.sota2.com/research/sota/query-focused-video-summarization-on-qfvs.md?metric=Average%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Video Score 1 | Result date | Report paper |
| --- | --- | --- | --- |
| CLIP-It | 57.13 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| CLIP-It | 57.13 | Not recorded | 68fa79561e209131cea7d268 |
| ResNet + Query + Transformer | 55.19 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| CLIP-It | 55.19 | Not recorded | 68fa79561e209131cea7d268 |
| CLIP-Image + Query + bi-LSTM | 54.47 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| Prompts-to-Summaries | 53.57 | Not recorded | 68fa79561e209131cea7d268 |
| Prompts-to-Summaries | 51.47 | Not recorded | 68fa79561e209131cea7d268 |
| IntentVizor | 51.27 | Not recorded | 68fa79561e209131cea7d268 |
| QFVS | 48.68 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| QFVS | 48.68 | Not recorded | 68fa79561e209131cea7d268 |
| Prompts-to-Summaries | 48.66 | Not recorded | 68fa79561e209131cea7d268 |
| QSAN | 48.52 | Not recorded | 68fa79561e209131cea7d268 |
| SeqDPP | 36.59 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| SeqDPP | 36.59 | Not recorded | 68fa79561e209131cea7d268 |
| SH-DPP | 35.67 | Not recorded | 68fa6b5f1e209131cea2dc9f |
| SH-DPP | 35.67 | Not recorded | 68fa79561e209131cea7d268 |

### CLIP-It

Video Score 1: 57.13. Result ID: 698e81d2ffc3901de09e2e43.

[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: {"Backbone":"CLIP-Image","Query":"true","Architecture":"Transformer"}. This record does not assert independent reproduction.

### CLIP-It

Video Score 1: 57.13. Result ID: 699a8b905698665ec415c09b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

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

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

Recorded evaluation configuration: {"Property":"Supervised","Requires training data":true,"Backbone":"CLIP-Image"}. This record does not assert independent reproduction.

### ResNet + Query + Transformer

Video Score 1: 55.19. Result ID: 698e81d2ffc3901de09e2e42.

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

Recorded evaluation configuration: {"Backbone":"ResNet","Query":"true","Architecture":"Transformer"}. This record does not assert independent reproduction.

### CLIP-It

Video Score 1: 55.19. Result ID: 699a8b905698665ec415c09a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

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

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

Recorded evaluation configuration: {"Property":"Supervised","Requires training data":true,"Backbone":"ResNet"}. This record does not assert independent reproduction.

### CLIP-Image + Query + bi-LSTM

Video Score 1: 54.47. Result ID: 698e81d2ffc3901de09e2e41.

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

Recorded evaluation configuration: {"Backbone":"CLIP-Image","Query":"true","Architecture":"bi-LSTM"}. This record does not assert independent reproduction.

### Prompts-to-Summaries

Video Score 1: 53.57. Result ID: 699a8b905698665ec415c09e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

Recorded evaluation configuration: {"Property":"Zero-Shot","Requires training data":false,"Normalization":"(MinMax + Exp) norm"}. This record does not assert independent reproduction.

### Prompts-to-Summaries

Video Score 1: 51.47. Result ID: 699a8b905698665ec415c09c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

Recorded evaluation configuration: {"Property":"Zero-Shot","Requires training data":false,"Normalization":"MinMax norm"}. This record does not assert independent reproduction.

### IntentVizor

Video Score 1: 51.27. Result ID: 699a8b905698665ec415c099.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32513.md>)

[Implementation](<https://github.com/jnzs1836/intent-vizor>)

Recorded evaluation configuration: {"Property":"Supervised","Requires training data":true}. This record does not assert independent reproduction.

### QFVS

Video Score 1: 48.68. Result ID: 698e81d2ffc3901de09e2e40.

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

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

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

### QFVS

Video Score 1: 48.68. Result ID: 699a8b905698665ec415c097.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

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

Recorded evaluation configuration: {"Property":"Supervised","Requires training data":true}. This record does not assert independent reproduction.

### Prompts-to-Summaries

Video Score 1: 48.66. Result ID: 699a8b905698665ec415c09d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

Recorded evaluation configuration: {"Property":"Zero-Shot","Requires training data":false,"Normalization":"Exp norm"}. This record does not assert independent reproduction.

### QSAN

Video Score 1: 48.52. Result ID: 699a8b905698665ec415c098.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

Recorded evaluation configuration: {"Property":"Supervised","Requires training data":true}. This record does not assert independent reproduction.

### SeqDPP

Video Score 1: 36.59. Result ID: 698e81d2ffc3901de09e2e3e.

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

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

### SeqDPP

Video Score 1: 36.59. Result ID: 699a8b905698665ec415c095.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

Recorded evaluation configuration: {"Property":"Supervised","Requires training data":true}. This record does not assert independent reproduction.

### SH-DPP

Video Score 1: 35.67. Result ID: 698e81d2ffc3901de09e2e3f.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa629c1e209131ce9fa2b1.md>)

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

### SH-DPP

Video Score 1: 35.67. Result ID: 699a8b905698665ec415c096.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79561e209131cea7d268.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa629c1e209131ce9fa2b1.md>)

Recorded evaluation configuration: {"Property":"Supervised","Requires training data":true}. This record does not assert independent reproduction.

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