• Home
  • Search
  • Spatio-temporal action localization for human action recognition in large dataset
  • Open Access IconOpen Access
  • Cite Icon3
  • https://doi.org/10.1117/12.2082880Copy DOI Icon

Spatio-temporal action localization for human action recognition in large dataset

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Human action recognition has drawn much attention in the field of video analysis. In this paper, we develop a human action detection and recognition process based on the tracking of Interest Points (IP) trajectory. A pre-processing step that performs spatio-temporal action detection is proposed. This step uses optical flow along with dense speed-up-robust-features (SURF) in order to detect and track moving humans in moving fields of view. The video description step is based on a fusion process that combines displacement and spatio-temporal descriptors. Experiments are carried out on the big data-set UCF-101. Experimental results reveal that the proposed techniques achieve better performances compared to many existing state-of-the-art action recognition approaches.

Similar Papers
  • Research Article
  • Citations30

Spatio-temporal action localization and detection for human action recognition in big dataset

  • Oct 31, 2016
  • Journal of Visual Communication and Image Representation
  • Sameh Megrhi +3
  • Supplementary Content

Visual cues for view-invariant human action recognition

  • Feb 17, 2017
  • Figshare
  • N A Anwaar-Ul-Haq
  • Research Article
  • Citations44

Graph-based approach for 3D human skeletal action recognition

  • Aug 03, 2016
  • Pattern Recognition Letters
  • Meng Li +1
  • Research Article
  • Citations2

Review of Literature on Human Activity Detection and Recognition

  • Nov 23, 2023
  • International Journal of Management, Technology, and Social Sciences
  • Pavankumar Naik +1
  • Research Article
  • Citations15

Human Action Recognition Using A Novel Deep Learning Approach

  • Jan 01, 2021
  • IOP Conference Series: Materials Science and Engineering
  • Badhagouni Suresh Kumar +2
  • Research Article
  • Citations133

A combined multiple action recognition and summarization for surveillance video sequences

  • Aug 26, 2020
  • Applied Intelligence
  • Omar Elharrouss +4
  • Conference Article
  • Citations6

Joint detection and recognition of human actions in wireless surveillance camera networks

  • May 01, 2014
  • Nikhil Naikal +2
  • Research Article
  • Citations36

Spatio-Temporal Analysis for Human Action Detection and Recognition in Uncontrolled Environments

  • Jan 01, 2015
  • International Journal of Multimedia Data Engineering and Management
  • Dianting Liu +4
  • PDF
  • Research Article
  • Citations31

Internet-of-Things-Based Suspicious Activity Recognition Using Multimodalities of Computer Vision for Smart City Security

  • Oct 05, 2022
  • Security and Communication Networks
  • Amjad Rehman +4
  • Research Article
  • Citations486

A survey of video datasets for human action and activity recognition

  • Feb 13, 2013
  • Computer Vision and Image Understanding
  • Jose M Chaquet +2
  • Research Article
  • Citations10

Video Based Human Activity Detection, Recognition and Classification of actions using SVM

  • Dec 31, 2018
  • Transactions on Machine Learning and Artificial Intelligence
  • Jagadeesh B +1
  • Conference Article
  • Citations7

Applications of human action analysis and recognition on wireless network infrastructures: State of the art and real world challenges

  • Jul 01, 2018
  • Georgios Tsatiris +2
  • PDF
  • Conference Article

Vision-based Activity Recognition: Present Status & Future Challenges

  • Jan 01, 2022
  • Md Atiqur Rahman Ahad
  • Conference Article
  • Citations9

Robust appearance-based human action recognition

  • Aug 23, 2004
  • Md Mizanur Rahman +1
  • Dissertation

Robust and efficient deep learning methods for vision-based action recognition

  • Jan 01, 2021
  • Yuecong Xu
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.