Challenge and Workshop on Localized and Detailed Understanding of Human Actions in Videos
Monday 11th October 2021
- We changed the calculation of PR (Precision-Recall) curve area same with PASCAL VOC in our GitHub repository (https://github.com/MCG-NJU/MultiSports).
- Slides are now available at Program Schedule.
- Due to a problem with the codalab server which causes uploading failure, we decide to postpone the test phase and winner annonuncement for 2 days.
- Participants can now register on MultiSports (Track 2) - test. Please submit results for evaluation on this website.
Attending the Workshop
ICCV will once again be virtual this year and the workshop will be held on Monday 11th October 2021 as a half day event. Please refer to this page for more information.
Aims and Scope
DeeperAction aims to advance the area of human action understanding with a shift from traditional action recognition to deeper understanding tasks of action, with a focus on localized and detailed understanding of human action from videos in the wild. Specifically, we benchmark three related tasks on localized and detailed action understanding by introducing newly-annotated and high-quality datasets, and organize the action understanding challenge on these benchmarks.
Detecting all segments of containing actions of interest and recognizing their categories from a long video sequence.
Localizing all action instances with spatio-temporal tubes and recognizing their labels from untrimmed and multi-person videos.
Decomposing the action instance into a human part graph and detecting action labels for all human parts an as well the whole human.