loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Abhinaba Roy 1 ; Biplab Banerjee 2 and Vittorio Murino 1

Affiliations: 1 Istituto Italiano di Tecnologia, Italy ; 2 Indian Institute of Technology, India

Keyword(s): Action Recognition, Multiple Instance Learning, Dictionary Learning, Support Vector Machines.

Related Ontology Subjects/Areas/Topics: Applications ; Instance-Based Learning ; Learning of Action Patterns ; Multi-Instance Learning ; Pattern Recognition ; Software Engineering ; Theory and Methods

Abstract: In this paper we deal with the problem of action recognition from unconstrained videos under the notion of multiple instance learning (MIL). The traditional MIL paradigm considers the data items as bags of instances with the constraint that the positive bags contain some class-specific instances whereas the negative bags consist of instances only from negative classes. A classifier is then further constructed using the bag level annotations and a distance metric between the bags. However, such an approach is not robust to outliers and is time consuming for a moderately large dataset. In contrast, we propose a dictionary learning based strategy to MIL which first identifies class-specific discriminative codewords, and then projects the bag-level instances into a probabilistic embedding space with respect to the selected codewords. This essentially generates a fixed-length vector representation of the bags which is specifically dominated by the properties of the class-specific instances. We introduce a novel exhaustive search strategy using a support vector machine classifier in order to highlight the class-specific codewords. The standard multiclass classification pipeline is followed henceforth in the new embedded feature space for the sake of action recognition. We validate the proposed framework on the challenging KTH and Weizmann datasets, and the results obtained are promising and comparable to representative techniques from the literature. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.238.121.7

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Roy, A.; Banerjee, B. and Murino, V. (2017). A Novel Dictionary Learning based Multiple Instance Learning Approach to Action Recognition from Videos. In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-758-222-6; ISSN 2184-4313, SciTePress, pages 519-526. DOI: 10.5220/0006200205190526

@conference{icpram17,
author={Abhinaba Roy. and Biplab Banerjee. and Vittorio Murino.},
title={A Novel Dictionary Learning based Multiple Instance Learning Approach to Action Recognition from Videos},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2017},
pages={519-526},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006200205190526},
isbn={978-989-758-222-6},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - A Novel Dictionary Learning based Multiple Instance Learning Approach to Action Recognition from Videos
SN - 978-989-758-222-6
IS - 2184-4313
AU - Roy, A.
AU - Banerjee, B.
AU - Murino, V.
PY - 2017
SP - 519
EP - 526
DO - 10.5220/0006200205190526
PB - SciTePress