Action recognition based on RGB and skeleton data sets: A survey
Action recognition is a major branch of computer vision research. As a widely used
technology, action recognition has been applied to human–computer interaction, intelligent …
technology, action recognition has been applied to human–computer interaction, intelligent …
Expansion-squeeze-excitation fusion network for elderly activity recognition
This work focuses on the task of elderly activity recognition, which is a challenging task due
to the existence of individual actions and human-object interactions in elderly activities …
to the existence of individual actions and human-object interactions in elderly activities …
Slowfast networks for video recognition
We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway,
operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating …
operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating …
A short note on the kinetics-700 human action dataset
We describe an extension of the DeepMind Kinetics human action dataset from 600 classes
to 700 classes, where for each class there are at least 600 video clips from different …
to 700 classes, where for each class there are at least 600 video clips from different …
A short note about kinetics-600
J Carreira, E Noland, A Banki-Horvath, C Hillier… - arxiv preprint arxiv …, 2018 - arxiv.org
We describe an extension of the DeepMind Kinetics human action dataset from 400 classes,
each with at least 400 video clips, to 600 classes, each with at least 600 video clips. In order …
each with at least 400 video clips, to 600 classes, each with at least 600 video clips. In order …
Learning spatio-temporal representation with local and global diffusion
Abstract Convolutional Neural Networks (CNN) have been regarded as a powerful class of
models for visual recognition problems. Nevertheless, the convolutional filters in these …
models for visual recognition problems. Nevertheless, the convolutional filters in these …
Video action understanding
MS Hutchinson, VN Gadepally - IEEE Access, 2021 - ieeexplore.ieee.org
Many believe that the successes of deep learning on image understanding problems can be
replicated in the realm of video understanding. However, due to the scale and temporal …
replicated in the realm of video understanding. However, due to the scale and temporal …
Improved human activity recognition using majority combining of reduced-complexity sensor branch classifiers
Human activity recognition (HAR) employs machine learning for the automated recognition
of motion and has widespread applications across healthcare, daily-life and security spaces …
of motion and has widespread applications across healthcare, daily-life and security spaces …
A novel hybrid deep learning approach with GWO–WOA optimization technique for human activity recognition
Abstract The effectiveness of Human Activity Recognition (HAR) models can be largely
attributed to the components derived from domain expertise. The classification system swiftly …
attributed to the components derived from domain expertise. The classification system swiftly …
A study on deep learning spatiotemporal models and feature extraction techniques for video understanding
M Suresha, S Kuppa, DS Raghukumar - International Journal of …, 2020 - Springer
Video understanding requires abundant semantic information. Substantial progress has
been made on deep learning models in the image, text, and audio domains, and notable …
been made on deep learning models in the image, text, and audio domains, and notable …