# Video Temporal Grounding on Ego4D NLQ

Source: [Video Temporal Grounding on Ego4D NLQ](<https://www.sota2.com/research/sota/video-temporal-grounding-on-ego4d-nlq>)

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

Data updated: 2026-06-09T10:34:18.919Z

Evaluation of Video Temporal Grounding performance on the Ego4D NLQ dataset, measured using Recall@1 metrics at IoU thresholds of 0.3, 0.5, and 0.7.

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 Temporal Grounding |
| Dataset (including any stated split) | Ego4D NLQ |
| Metric | Recall@1 (IoU=0.3) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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 (IoU=0.3)](<https://www.sota2.com/research/sota/video-temporal-grounding-on-ego4d-nlq.md?metric=Recall%401%20(IoU%3D0.3)>): Higher is better; unit: PERCENT.

- [Recall@1 (IoU=0.5)](<https://www.sota2.com/research/sota/video-temporal-grounding-on-ego4d-nlq.md?metric=Recall%401%20(IoU%3D0.5)>): Higher is better; unit: PERCENT.

- [Recall@1 (IoU=0.7)](<https://www.sota2.com/research/sota/video-temporal-grounding-on-ego4d-nlq.md?metric=Recall%401%20(IoU%3D0.7)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Recall@1 (IoU=0.3) | Result date | Report paper |
| --- | --- | --- | --- |
| TaRO | 13.8 | Not recorded | 6a279e5990966ade919bfa22 |
| TaRO | 8.19 | Not recorded | 6a279e5990966ade919bfa22 |
| Time-R1 | 6.48 | Not recorded | 6a279e5990966ade919bfa22 |
| Qwen3-VL-8B-Instruct | 5.1 | Not recorded | 6a279e5990966ade919bfa22 |
| VideoChat-R1.5 | 3.84 | Not recorded | 6a279e5990966ade919bfa22 |

### TaRO

Recall@1 (IoU=0.3): 13.8. Result ID: 6a27ec0efbc373592c256692.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e5990966ade919bfa22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e5990966ade919bfa22.md>)

Recorded evaluation configuration: {"Base model":"Qwen3-VL-8B-Instruct","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### TaRO

Recall@1 (IoU=0.3): 8.19. Result ID: 6a27ec0efbc373592c256690.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e5990966ade919bfa22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a279e5990966ade919bfa22.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-VL-7B-Instruct","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### Time-R1

Recall@1 (IoU=0.3): 6.48. Result ID: 6a27ec0efbc373592c25668f.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e5990966ade919bfa22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79b81e209131cea7f1a6.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-VL-7B-Instruct","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### Qwen3-VL-8B-Instruct

Recall@1 (IoU=0.3): 5.1. Result ID: 6a27ec0efbc373592c256691.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e5990966ade919bfa22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6927db54d6b0dd3342930f66.md>)

Recorded evaluation configuration: {"Base model":"Qwen3-VL-8B-Instruct","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### VideoChat-R1.5

Recall@1 (IoU=0.3): 3.84. Result ID: 6a27ec0efbc373592c25668e.

[Reporting paper](<https://www.sota2.com/research/paper/6a279e5990966ade919bfa22.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b8f1e209131cea891be.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-VL-7B-Instruct","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

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