Behera, A, Chapman, M, Cohn, AG et al. (1 more author) (2014) Egocentric activity recognition using histograms of oriented pairwise relations. In: VISAPP 2014 - Proceedings of the 9th International Conference on Computer Vision Theory and Applications. VISAPP 2014, 05-08 Jan 2014, Lisbon, Portugal. SciTePress , 22 - 30. ISBN 9789897580048
Abstract
This paper presents an approach for recognising activities using video from an egocentric (first-person view) setup. Our approach infers activity from the interactions of objects and hands. In contrast to previous approaches to activity recognition, we do not require to use an intermediate such as object detection, pose estimation, etc. Recently, it has been shown that modelling the spatial distribution of visual words corresponding to local features further improves the performance of activity recognition using the bag-of-visual words representation. Influenced and inspired by this philosophy, our method is based on global spatio-temporal relationships between visual words. We consider the interaction between visual words by encoding their spatial distances, orientations and alignments. These interactions are encoded using a histogram that we name the Histogram of Oriented Pairwise Relations (HOPR). The proposed approach is robust to occlusion and background variation and is evaluated on two challenging egocentric activity datasets consisting of manipulative task. We introduce a novel representation of activities based on interactions of local features and experimentally demonstrate its superior performance in comparison to standard activity representations such as bag-of-visual words.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | (c) 2014. SciTePress. Reproduced with permission from the publisher. |
Keywords: | Bag-of-visual-words; Egocentric Activity Recognition; Histogram of Oriented Pairwise Relations (HOPR); Pairwise Qualitative Relations; Spatio-temporal Relationships |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) > Artificial Intelligence & Biological Systems (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 19 Nov 2014 11:46 |
Last Modified: | 19 Dec 2022 13:28 |
Published Version: | http://www.visapp.visigrapp.org/ |
Status: | Published |
Publisher: | SciTePress |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:81155 |