InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges
TL
TL;DR
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 Intern video as a video foundation model.
Abstract
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
References60 items
1
Egocentric Video-Language Pretraining
2
Vision Transformer Adapter for Dense Predictions
3
BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection
4
An Empirical Study of End-to-End Temporal Action Detection
5