Modeling long-term interactions to enhance action recognition
Document typeConference report
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Rights accessOpen Access
In this paper, we propose a new approach to understand actions in egocentric videos that exploits the semantics of object interactions at both frame and temporal levels. At the frame level, we use a region-based approach that takes as input a primary region roughly corresponding to the user hands and a set of secondary regions potentially corresponding to the interacting objects and calculates the action score through a CNN formulation. This information is then fed to a Hierarchical Long Short-Term Memory Network (HLSTM) that captures temporal dependencies between actions within and across shots. Ablation studies thoroughly validate the proposed approach, showing in particular that both levels of the HLSTM architecture contribute to performance improvement. Furthermore, quantitative comparisons show that the proposed approach outperforms the state-of-the-art in terms of action recognition on standard benchmarks, without relying on motion information.
© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
CitationCartas, A.; Radeva, P.; Dimiccoli, M. Modeling long-term interactions to enhance action recognition. A: International Conference on Pattern Recognition. "Proceedings of ICPR 2020: 25th International Conference on Pattern Recognition: Milan, 10–15 January 2021". Institute of Electrical and Electronics Engineers (IEEE), 2021, p. 10351-10358. ISBN 978-1-7281-8808-9. DOI 10.1109/ICPR48806.2021.9412148.