Skip to Main content Skip to Navigation
New interface
Conference papers

Context Aware Group Activity Recognition

Abstract : This paper addresses the task of group activity recognition in multi-person videos. Existing approaches decompose this task into feature learning and relational reasoning. Despite showing progress, these methods only rely on appearance features for people and overlook the available contextual information, which can play an important role in group activity understanding. In this work, we focus on the feature learning aspect and propose a two-stream architecture that not only considers person-level appearance features, but also makes use of contextual information present in videos for group activity recognition. In particular, we propose to use two types of contextual information beneficial for two different scenarios: pose context and scene context that provide crucial cues for group activity understanding. We combine appearance and contextual features to encode each person with an enriched representation. Finally, these combined features are used in relational reasoning for predicting group activities. We evaluate our method on two benchmarks, Volleyball and Collective Activity and show that joint modeling of contextual information with appearance features benefits in group activity understanding.
Document type :
Conference papers
Complete list of metadata

Cited literature [45 references]  Display  Hide  Download
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Tuesday, November 3, 2020 - 7:55:58 PM
Last modification on : Friday, November 4, 2022 - 3:02:52 PM
Long-term archiving on: : Thursday, February 4, 2021 - 7:01:00 PM


Files produced by the author(s)




Avijit Dasgupta, C. V. Jawahar, Karteek Alahari. Context Aware Group Activity Recognition. ICPR 2020 - International Conference on Pattern Recognition, Jan 2021, Milan (Virtual), Italy. pp.10098-10105, ⟨10.1109/ICPR48806.2021.9412306⟩. ⟨hal-02987414⟩



Record views


Files downloads