Human Action Recognition Using Recurrent Bag-of-Features Pooling

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

Tutkimustuotos: KonferenssiartikkeliScientificvertaisarvioitu

Abstrakti

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.

AlkuperäiskieliEnglanti
OtsikkoPattern Recognition. ICPR International Workshops and Challenges, 2021, Proceedings
ToimittajatAlberto Del Bimbo, Rita Cucchiara, Stan Sclaroff, Giovanni Maria Farinella, Tao Mei, Marco Bertini, Hugo Jair Escalante, Roberto Vezzani
KustantajaSpringer
Sivut63-76
Sivumäärä14
ISBN (painettu)9783030688202
DOI - pysyväislinkit
TilaJulkaistu - 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInternational Conference on Pattern Recognition - Milan, Italia
Kesto: 10 tammik. 202115 tammik. 2021

Julkaisusarja

NimiLecture Notes in Computer Science
Vuosikerta12665 LNCS
ISSN (painettu)0302-9743
ISSN (elektroninen)1611-3349

Conference

ConferenceInternational Conference on Pattern Recognition
Maa/AlueItalia
KaupunkiMilan
Ajanjakso10/01/2115/01/21

Julkaisufoorumi-taso

  • Jufo-taso 1

!!ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Sormenjälki

Sukella tutkimusaiheisiin 'Human Action Recognition Using Recurrent Bag-of-Features Pooling'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä