Skip to Main content Skip to Navigation
Conference papers

Attention-Based Temporal Weighted Convolutional Neural Network for Action Recognition

Abstract : Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs). However, effective and efficient methods for incorporation of temporal information into CNNs are still being actively explored in the recent literature. Motivated by the popular recurrent attention models in the research area of natural language processing, we propose the Attention-based Temporal Weighted CNN (ATW), which embeds a visual attention model into a temporal weighted multi-stream CNN. This attention model is simply implemented as temporal weighting yet it effectively boosts the recognition performance of video representations. Besides, each stream in the proposed ATW frame- work is capable of end-to-end training, with both network parameters and temporal weights optimized by stochastic gradient descent (SGD) with backpropagation. Our experiments show that the proposed attention mechanism contributes substantially to the performance gains with the more discriminative snippets by focusing on more relevant video segments.
Document type :
Conference papers
Complete list of metadata

Cited literature [48 references]  Display  Hide  Download
Contributor : Hal Ifip <>
Submitted on : Friday, June 22, 2018 - 11:45:00 AM
Last modification on : Wednesday, June 10, 2020 - 10:00:04 AM
Long-term archiving on: : Tuesday, September 25, 2018 - 12:52:33 PM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License



Jinliang Zang, Le Wang, Ziyi Liu, Qilin Zhang, Gang Hua, et al.. Attention-Based Temporal Weighted Convolutional Neural Network for Action Recognition. 14th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2018, Rhodes, Greece. pp.97-108, ⟨10.1007/978-3-319-92007-8_9⟩. ⟨hal-01821048⟩



Record views


Files downloads