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

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

17 Nov 2022arXiv:2211.09529archive 2025-07-28

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

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

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

opengvlab/ego4d-eccv2022-solutions officialmentioned in papermentioned on GitHubpytorch report
jonnys1226/ego4d_asl mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Future Hand PredictionMoment QueriesNatural Language QueriesObjectObject DetectionShort-term Object Interaction AnticipationState Change Object DetectionVideo Understandingobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Future Hand Prediction Ego4D InternVideo C.Disp(Left) 53.33 #1 of 1 Archive leaderboard report
Future Hand Prediction Ego4D InternVideo C.Disp(Right) 53.37 #1 of 1 Archive leaderboard report
Future Hand Prediction Ego4D InternVideo Disp(Total) 196.8 #1 of 1 Archive leaderboard report
Future Hand Prediction Ego4D InternVideo M.Disp(Left) 43.25 #1 of 1 Archive leaderboard report
Future Hand Prediction Ego4D InternVideo M.Disp(Right) 46.25 #1 of 1 Archive leaderboard report
Natural Language Queries Ego4D InternVideo R@1 IoU=0.3 16.45 #6 of 10 Archive leaderboard report
Natural Language Queries Ego4D InternVideo R@1 IoU=0.5 10.06 #6 of 10 Archive leaderboard report
Natural Language Queries Ego4D InternVideo R@1 Mean(0.3 and 0.5) 13.26 #6 of 10 Archive leaderboard report
Natural Language Queries Ego4D InternVideo R@5 IoU=0.3 22.95 #6 of 10 Archive leaderboard report
Natural Language Queries Ego4D InternVideo R@5 IoU=0.5 16.10 #6 of 10 Archive leaderboard report
Short-term Object Interaction Anticipation Ego4D InternVideo Noun (Top5 mAP) 24.6 #4 of 4 Archive leaderboard report
Short-term Object Interaction Anticipation Ego4D InternVideo Noun+TTC (Top5 mAP) 7.64 #4 of 4 Archive leaderboard report
Short-term Object Interaction Anticipation Ego4D InternVideo Noun+Verb(Top5 mAP) 9.18 #4 of 4 Archive leaderboard report
Short-term Object Interaction Anticipation Ego4D InternVideo Overall (Top5 mAP) 3.4 #4 of 4 Archive leaderboard report
State Change Object Detection Ego4D InternVideo AP 37.19 #1 of 1 Archive leaderboard report
State Change Object Detection Ego4D InternVideo AP50 55.97 #1 of 1 Archive leaderboard report
State Change Object Detection Ego4D InternVideo AP75 38.44 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

InternVideo

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections