Human Action Recognition Using Recurrent Bag-of-Features Pooling

Marios Krestenitis, Nikolaos Passalis, Alexandros Iosifidis, Moncef Gabbouj, Anastasios Tefas

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

Bag-of-Features (BoF)-based models have been traditionally used for various computer vision tasks, due to their ability to provide compact semantic representations of complex objects, e.g., images, videos, etc. Indeed, BoF has been successfully combined with various feature extractions methods, ranging from handcrafted feature extractors to powerful deep learning models. However, BoF, along with most of the pooling approaches employed in deep learning, fails to capture the temporal dynamics of the input sequences. This leads to significant information loss, especially when the informative content of the data is sequentially distributed over the temporal dimension, e.g., videos. In this paper we propose a novel stateful recurrent quantization and aggregation approach in order to overcome the aforementioned limitation. The proposed method is inspired by the well-known Bag-of-Features (BoF) model, but employs a stateful trainable recurrent quantizer, instead of plain static quantization, allowing for effectively encoding the temporal dimension of the data. The effectiveness of the proposed approach is demonstrated using three video action recognition datasets.

Original languageEnglish
Title of host publicationPattern Recognition. ICPR International Workshops and Challenges, 2021, Proceedings
EditorsAlberto Del Bimbo, Rita Cucchiara, Stan Sclaroff, Giovanni Maria Farinella, Tao Mei, Marco Bertini, Hugo Jair Escalante, Roberto Vezzani
PublisherSpringer
Pages63-76
Number of pages14
ISBN (Print)9783030688202
DOIs
Publication statusPublished - 2021
Publication typeA4 Article in conference proceedings
EventInternational Conference on Pattern Recognition - Milan, Italy
Duration: 10 Jan 202115 Jan 2021

Publication series

NameLecture Notes in Computer Science
Volume12665 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceInternational Conference on Pattern Recognition
Country/TerritoryItaly
CityMilan
Period10/01/2115/01/21

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Human Action Recognition Using Recurrent Bag-of-Features Pooling'. Together they form a unique fingerprint.

Cite this