Beyond Action Recognition: Action Completion in RGB-D Data

Farnoosh Heidarivincheh, Majid Mirmehdi, Dima Damen

Research output: Contribution to conferenceConference Paperpeer-review

348 Downloads (Pure)


An action is completed when its goal has been successfully achieved. Using current state-of-the-art depth features, designed primarily for action recognition, an incomplete sequence may still be classified as its complete counterpart due to the overlap in evidence. In this work we show that while features can perform comparably for action recognition, they vary in their ability to recognise incompletion. Experimenting on a novel dataset of 414 complete/incomplete object interaction sequences, spanning six actions and captured using an RGB-D camera, we test for completion using binary classification on labelled data. Results show that by selecting the suitable feature per action, we achieve 95.7% accuracy for recognising action completion.
Original languageEnglish
Number of pages11
Publication statusPublished - 19 Sep 2016
Event27th British Machine Vision Conference - York, United Kingdom
Duration: 19 Sep 201622 Sep 2016


Conference27th British Machine Vision Conference
Abbreviated titleBMVC
Country/TerritoryUnited Kingdom


Dive into the research topics of 'Beyond Action Recognition: Action Completion in RGB-D Data'. Together they form a unique fingerprint.

Cite this