OpenCodePapers
natural-language-queries-on-ego4d
Visual Grounding
Video Grounding
Natural Language Queries
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
R@1 Mean(0.3 and 0.5)
↕
R@1 IoU=0.3
↕
R@1 IoU=0.5
↕
R@5 IoU=0.3
↕
R@5 IoU=0.5
↕
ModelName
ReleaseDate
↕
EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation
✓ Link
23.68
28.05
19.31
44.16
31.37
EgoVideo
2024-06-26
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos
✓ Link
18.86
22.21
15.52
45.63
33.93
DeCafNet-100%
2025-05-22
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos
✓ Link
17.93
20.81
15.04
42.40
31.68
DeCafNet-50%
2025-05-22
RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos
✓ Link
16.55
20.63
12.47
41.67
25.08
RGNet
2023-12-11
DeCafNet: Delegate and Conquer for Efficient Temporal Grounding in Long Videos
✓ Link
15.32
18.10
12.55
38.85
28.27
DeCafNet-50% (no NaQ)
2025-05-22
InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges
✓ Link
13.26
16.45
10.06
22.95
16.10
InternVideo
2022-11-17
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection
✓ Link
12.11
14.16
10.06
26.95
19.16
UniMD+Sync.
2024-04-07
ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022
✓ Link
10.52
12.89
8.14
15.41
9.94
ReLER@ZJU-Alibaba
2022-07-01
Egocentric Video-Language Pretraining
✓ Link
8.35
10.46
6.24
16.76
11.29
EgoVLP
2022-06-03
EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone
✓ Link
12.95
7.91
23.80
16.11
EgoVLPv2
2023-07-11
×