DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 19998-20008
Abstract
Human action recognition has recently become one of the popular research topics in the computer vision community. Various 3D-CNN based methods have been presented to tackle both the spatial and temporal dimensions in the task of video action recognition with competitive results. However, these methods have suffered some fundamental limitations such as lack of robustness and generalization, e.g., how does the temporal ordering of video frames affect the recognition results? This work presents a novel end-to-end Transformer-based Directed Attention (Direc-Former) framework 1 1 The implementation of DirecFormer is available at https://github.com/uark-cviu/DirecFormer for robust action recognition. The method takes a simple but novel perspective of Transformer-based approach to understand the right order of sequence actions. Therefore, the contributions of this work are three-fold. Firstly, we introduce the problem of ordered temporal learning issues to the action recognition problem. Secondly, a new Directed Attention mechanism is introduced to understand and provide attentions to human actions in the right order. Thirdly, we introduce the conditional dependency in action sequence modeling that includes orders and classes. The proposed approach consistently achieves the state-of-the-art (SOTA) results compared with the recent action recognition methods [4, 18, 72, 74]. on three standard large-scale benchmarks, i.e. Jester, Kinetics-400 and Something-Something-V2.Keywords
All Related Versions
Funding Information
- Arkansas Biosciences Institute (ABI) Grant Program
This publication has 36 references indexed in Scilit:
- Rethinking the Inception Architecture for Computer Vision2016
- Convolutional Two-Stream Network Fusion for Video Action Recognition2016
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- Going deeper with convolutions2015
- Large-Scale Video Classification with Convolutional Neural Networks2014
- Action Recognition with Improved Trajectories2013
- Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis2011
- A Spatio-Temporal Descriptor Based on 3D-Gradients2008
- An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector2008
- Long Short-Term MemoryNeural Computation, 1997