On the use of deep learning for video classification

A Ur Rehman, SB Belhaouari, MA Kabir, A Khan - Applied Sciences, 2023 - mdpi.com
The video classification task has gained significant success in the recent years. Specifically,
the topic has gained more attention after the emergence of deep learning models as a …

Deep learning for video classification: A review

A Rehman, SB Belhaouari - Authorea Preprints, 2021 - techrxiv.org
Video classification task has gained a significant success in the recent years. Specifically,
the topic has gained more attention after the emergence of deep learning models as a …

Channel Attention‐Based Approach with Autoencoder Network for Human Action Recognition in Low‐Resolution Frames

E Dastbaravardeh, S Askarpour… - … Journal of Intelligent …, 2024 - Wiley Online Library
Action recognition (AR) has many applications, including surveillance, health/disabilities
care, man‐machine interactions, video‐content‐based monitoring, and activity recognition …

Spatio-temporal vector of locally max pooled features for action recognition in videos

IC Duta, B Ionescu, K Aizawa… - 2017 IEEE Conference on …, 2017 - ieeexplore.ieee.org
We introduce Spatio-Temporal Vector of Locally Max Pooled Features (ST-VLMPF), a super
vector-based encoding method specifically designed for local deep features encoding. The …

Linear dynamical systems approach for human action recognition with dual-stream deep features

Z Du, H Mukaidani - Applied Intelligence, 2022 - Springer
Human action recognition with a dual-stream architecture using linear dynamical systems
(LDSs) approach is discussed in this paper. First, a slice process is established to extract …

Two-branch relational prototypical network for weakly supervised temporal action localization

L Huang, Y Huang, W Ouyang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
As a challenging task of high-level video understanding, weakly supervised temporal action
localization has attracted more attention recently. With only video-level category labels, this …

Spatio-temporal vlad encoding for human action recognition in videos

IC Duta, B Ionescu, K Aizawa, N Sebe - … 4-6, 2017, Proceedings, Part I 23, 2017 - Springer
Encoding is one of the key factors for building an effective video representation. In the recent
works, super vector-based encoding approaches are highlighted as one of the most …

Efficient human action recognition using histograms of motion gradients and VLAD with descriptor shape information

IC Duta, JR R. Uijlings, B Ionescu, K Aizawa… - Multimedia Tools and …, 2017 - Springer
Feature extraction and encoding represent two of the most crucial steps in an action
recognition system. For building a powerful action recognition pipeline it is important that …

Human action recognition based on spatio-temporal three-dimensional scattering transform descriptor and an improved VLAD feature encoding algorithm

B Lin, B Fang, W Yang, J Qian - Neurocomputing, 2019 - Elsevier
The local spatio-temporal descriptor and feature encoding algorithm are two crucial key
steps for human action recognition based on spatio-temporal interest points (STIP). Since …

Machine cognition of violence in videos using novel outlier-resistant vlad

T Deb, A Arman, A Firoze - 2018 17th IEEE international …, 2018 - ieeexplore.ieee.org
Understanding highly accurate and real-time violent actions from surveillance videos is a
demanding challenge. Our primary contribution of this work is divided into two parts. Firstly …