Human Action Recognition using Recurrent Bag-of-Features Pooling - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Human Action Recognition using Recurrent Bag-of-Features Pooling

Résumé

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.
Fichier principal
Vignette du fichier
Human Action Recognition using Recurrent Bag-of-Features Pooling.pdf (295.74 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03265177 , version 1 (19-06-2021)

Identifiants

  • HAL Id : hal-03265177 , version 1

Citer

Marios Krestenitis, Nikolaos Passalis, Alexandros Iosifidis, Moncef Gabbouj, Anastasios Tefas. Human Action Recognition using Recurrent Bag-of-Features Pooling. 7th workshop Image Mining Theory and Applications (IMTA VII) -, 2021, Virtual, Italy. ⟨hal-03265177⟩
18 Consultations
60 Téléchargements

Partager

Gmail Facebook X LinkedIn More