Action Completion: A Temporal Model for Moment Detection

Farnoosh Heidarivincheh, Majid Mirmehdi, Dima Damen

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)


We introduce completion moment detection for actions - the problem of locating the moment of completion, when the action's goal is confidently considered achieved. The paper proposes a joint classification-regression recurrent model that predicts completion from a given frame, and then integrates frame-level contributions to detect sequence-level completion moment. We introduce a recurrent voting node that predicts the frame's relative position of the completion moment by either classification or regression. The method is also capable of detecting incompletion. For example, the method is capable of detecting a missed ball-catch, as well as the moment at which the ball is safely caught. We test the method on 16 actions from three public datasets, covering sports as well as daily actions. Results show that when combining contributions from frames prior to the completion moment as well as frames post completion, the completion moment is detected within one second in 89% of all tested sequences.
Original languageEnglish
Title of host publicationBritish Machine Vision Conference 2018
PublisherBritish Machine Vision Association (BMVC Proceedings)
Number of pages12
Publication statusAccepted/In press - 3 Sept 2018
Event29th British Machine Vision Conference - Northumbria University, Newcastle upon Tyne, United Kingdom
Duration: 3 Sept 20186 Sept 2018


Conference29th British Machine Vision Conference
Country/TerritoryUnited Kingdom
CityNewcastle upon Tyne
Internet address


Dive into the research topics of 'Action Completion: A Temporal Model for Moment Detection'. Together they form a unique fingerprint.

Cite this