-
Notifications
You must be signed in to change notification settings - Fork 7
1805.06749
[Arxiv 1805.06749] Action Completion: A Temporal Model for Moment Detection [project page] [PdF] [notes]
Farnoosh Heidarivincheh, Majid Mirmehdi, Dima Damen
read 2019/07/03
Detect the completion moment for actions: when the action's goal is considered as achieved
Action recognition often doesn't focus on detecting whether an action's aim has been achieved.
Action completion is different end of action localization as it focuses on the goal of the action
Use a convolutional-recurrent neural network for the task of predicting completion
At each time step t, the sequence is split in two parts (up until time step t and starting time step t+1). The classification vote distinguishes the split containing the completion moment.
At t, predict the relative position of the completion moment
When combining contributions from frames prior to the completion moment, as well as frames post completion, the completion moment is detected with confidence
Use 3 public datasets, including sports and daily actions
- RGBD-AC (from their previous work)
-
- annotations of some videos in HMDB and UCF 101
Supervised problem with completion as binary classification
Detect a specific frame at which we are confident that an action has been completed. Assumes labeling is consistent accross images.
Evaluation metrics:
- Accuracy (for every sequence, compute ratio of frames that are correctly labelled as pre or post-completion)
- Relative distance error: normalized (by the length of the sequence) distance between predicted and ground truth completion moments
They correctly detect the completion moment within 1 second (30 frames) in 89% of all test sequences, and within 0.5 second in 74% of sequences.
When will you do what? anticipating temporal occurrences of activities. Am I done? predicting action progress in videos. arXiv preprint arXiv:1705.01781, 2018.