Extreme low resolution action recognition with spatial-temporal multi-head self-attention and knowledge distillation

D Purwanto… - Proceedings of the …, 2019 - openaccess.thecvf.com
This paper proposes a two-stream network with a novel spatial-temporal multi-head self-
attention mechanism for action recognition in extreme low resolution (LR) videos. The new …

Improved Seagull Optimization Driven Hybrid System for Enhanced Human Activity Recognition and Feature Selection

M Kamble, R Bichkar - Traitement du Signal, 2024 - search.proquest.com
Human activity recognition (HAR) plays a crucial role in various domains, including
surveillance systems, human-computer interactions, and healthcare monitoring. This paper …

Deep positional attention-based bidirectional RNN with 3D Convolutional video descriptors for human action recognition

N Srilakshmi, N Radha - IOP Conference Series: Materials …, 2021 - iopscience.iop.org
This article presents the Joints and Trajectory-pooled 3D-Deep Positional Attention-based
Bidirectional Recurrent convolutional Descriptors (JTPADBRD) for recognizing the human …

DEEP POSITIONAL ATTENTION-BASED HIERARCHICAL BIDIRECTIONAL RNN WITH CNNBASED VIDEO DESCRIPTORS FOR HUMAN ACTION RECOGNITION

N Srilakshmi, N Radha - 2022 - dspaceir.psgrkcw.com
Human Action Recognition (HAR) is a highly notable area of study in contemporary
computer vision. Many investigations focused on recognizing a person's actions from video …

Low rank theory-based interframe forgery detection for blurry video

L Lin, T Huang, W Huang, H Pu… - Journal of Electronic …, 2019 - spiedigitallibrary.org
It is difficult to extract appropriate features of blurry digital video because of the low quality
image for which traditional forgery detection methods are not effective. The video is often …