DeeperAction Workshop @ ECCV2022
Challenge and Workshop on Detailed Video Action Understanding and Anomaly Recognition
Monday 24th October 2022





NEWS
- 2022-09-26
- Challenge Results have been updated in Challenge Results.
- 2022-09-22
- Details about our workshop schedule have been updated in Program Schedule.
- 2022-04-29
- We have published competitions for FineAction (Track 1), MultiSports (Track 2), SportsMOT (Track 3), Kinetics-TPS (Track 4), and UrbanPipe (Track 5).
- Competitions start at May 1, 2022, midnight UTC and finish at Aug. 31, 2022, 11:59 p.m. UTC.
- Data for training and validation is now available on the competition pages above.
- 2022-04-08
- The DeeperAction Workshop@ECCV2022 website information release.
Attending the Workshop
ECCV 2022 is planned to be held in Tel-Aviv on Oct. 24-28 2022. Decision on physical vs. hybrid vs. virtual event will be made at a later stage. The workshop will be held on Monday 24th October 2022 as a half day event. Please refer to this page for more information.
Aims and Scope
DeeperAction aims to advance the area of video understanding with a shift from traditional action recognition to deeper understanding tasks of action, with a focus on detailed understanding of human action and anomaly recognition from videos in the wild. Specifically, we benchmark five related tasks on detailed action understanding by introducing newly-annotated and high-quality datasets, and organize the video action understanding challenge on these benchmarks.