Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges

About

In this report, we present our champion solutions to five tracks at Ego4D challenge. We leverage our developed InternVideo, a video foundation model, for five Ego4D tasks, including Moment Queries, Natural Language Queries, Future Hand Prediction, State Change Object Detection, and Short-term Object Interaction Anticipation. InternVideo-Ego4D is an effective paradigm to adapt the strong foundation model to the downstream ego-centric video understanding tasks with simple head designs. In these five tasks, the performance of InternVideo-Ego4D comprehensively surpasses the baseline methods and the champions of CVPR2022, demonstrating the powerful representation ability of InternVideo as a video foundation model. Our code will be released at https://github.com/OpenGVLab/ego4d-eccv2022-solutions

Guo Chen, Sen Xing, Zhe Chen, Yi Wang, Kunchang Li, Yizhuo Li, Yi Liu, Jiahao Wang, Yin-Dong Zheng, Bingkun Huang, Zhiyu Zhao, Junting Pan, Yifei Huang, Zun Wang, Jiashuo Yu, Yinan He, Hongjie Zhang, Tong Lu, Yali Wang, Limin Wang, Yu Qiao• 2022

Related benchmarks

TaskDatasetResultRank
Temporal Action DetectionTHUMOS-14 (test)--
330
Temporal Action DetectionActivityNet v1.3 (val)--
185
Natural Language QueriesEgo4D NLQ (val)
Recall@1 (IoU=0.3)15.61
23
Natural Language QueriesEgo4D NLQ (test)
R@1 (IoU=0.3)16.46
21
Moment QueryEgo4D Moment Query (val)
R@1 (IoU=0.5)41.13
19
Short-Term AnticipationEgo4D STA v2 (val)
N mAP19.45
16
Short-Term AnticipationEgo4D-STA v1 (test)
mAP (N)24.6
9
Natural Language QueriesEgo4D-NLQ v1 (test)
R@1 (IoU=0.3)16.45
8
Object DetectionSCOD (val)
AP36.4
7
Temporal GroundingEgo4D 1.0 (test)
Recall@1 (IoU=0.3)16.45
7
Showing 10 of 15 rows

Other info

Code

Follow for update