STAP: Spatial-temporal attention-aware pooling for action recognition

TV Nguyen, Z Song, S Yan - … on Circuits and Systems for Video …, 2014 - ieeexplore.ieee.org
Human action recognition is valuable for numerous practical applications, eg, gaming, video
surveillance, and video search. In this paper we hypothesize that the classification of actions …

Spatial–temporal pooling for action recognition in videos

J Wang, Z Shao, X Huang, T Lu, R Zhang, X Lv - Neurocomputing, 2021 - Elsevier
Recently, deep convolutional neural networks have demonstrated great effectiveness in
action recognition with both RGB and optical flow in the past decade. However, existing …

STA-CNN: Convolutional spatial-temporal attention learning for action recognition

H Yang, C Yuan, L Zhang, Y Sun, W Hu… - … on Image Processing, 2020 - ieeexplore.ieee.org
Convolutional Neural Networks have achieved excellent successes for object recognition in
still images. However, the improvement of Convolutional Neural Networks over the …

Unified spatio-temporal attention networks for action recognition in videos

D Li, T Yao, LY Duan, T Mei… - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
Recognizing actions in videos is not a trivial task because video is an information-intensive
media and includes multiple modalities. Moreover, on each modality, an action may only …

LgNet: A local-global network for action recognition and beyond

J Zhou, Z Fu, Q Huang, Q Liu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
This work addresses the task of action recognition in video sequences. In real world
applications, this task is quite challenging due to the complex background of video content …

Spatio-temporal adaptive network with bidirectional temporal difference for action recognition

Z Li, J Li, Y Ma, R Wang, Z Shi… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Action Recognition is a fundamental task in computer vision field, with a wide range of
applications in autonomous driving, security monitoring, etc. However, previous action …

Attention-based temporal weighted convolutional neural network for action recognition

J Zang, L Wang, Z Liu, Q Zhang, G Hua… - … and Innovations: 14th IFIP …, 2018 - Springer
Research in human action recognition has accelerated significantly since the introduction of
powerful machine learning tools such as Convolutional Neural Networks (CNNs). However …

Nuta: Non-uniform temporal aggregation for action recognition

X Li, C Liu, B Shuai, Y Zhu, H Chen… - Proceedings of the …, 2022 - openaccess.thecvf.com
In the world of action recognition research, one primary focus has been on how to construct
and train networks to model the spatial-temporal volume of an input video. These methods …

AGPN: Action granularity pyramid network for video action recognition

Y Chen, H Ge, Y Liu, X Cai… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Video action recognition is a fundamental task for video understanding. Action recognition in
complex spatio-temporal contexts generally requires fusing of different multi-granularity …

Shuffle-invariant network for action recognition in videos

Q Shi, HB Zhang, Z Li, JX Du, Q Lei, JH Liu - ACM Transactions on …, 2022 - dl.acm.org
The local key features in video are important for improving the accuracy of human action
recognition. However, most end-to-end methods focus on global feature learning from …