Effective Action Recognition with Embedded Key Point Shifts

08/26/2020
by   Haozhi Cao, et al.
0

Temporal feature extraction is an essential technique in video-based action recognition. Key points have been utilized in skeleton-based action recognition methods but they require costly key point annotation. In this paper, we propose a novel temporal feature extraction module, named Key Point Shifts Embedding Module (KPSEM), to adaptively extract channel-wise key point shifts across video frames without key point annotation for temporal feature extraction. Key points are adaptively extracted as feature points with maximum feature values at split regions, while key point shifts are the spatial displacements of corresponding key points. The key point shifts are encoded as the overall temporal features via linear embedding layers in a multi-set manner. Our method achieves competitive performance through embedding key point shifts with trivial computational cost, achieving the state-of-the-art performance of 82.05 Something-Something-v1, and HMDB51 datasets.

READ FULL TEXT

page 21

page 27

page 28

research
03/23/2021

Learning Comprehensive Motion Representation for Action Recognition

For action recognition learning, 2D CNN-based methods are efficient but ...
research
10/18/2022

Compact multi-scale periocular recognition using SAFE features

In this paper, we present a new approach for periocular recognition base...
research
05/06/2020

Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition

Temporal feature extraction is an important issue in video-based action ...
research
09/25/2020

Online Learnable Keyframe Extraction in Videos and its Application with Semantic Word Vector in Action Recognition

Video processing has become a popular research direction in computer vis...
research
11/24/2022

Video Test-Time Adaptation for Action Recognition

Although action recognition systems can achieve top performance when eva...
research
07/11/2021

Interpretable Deep Feature Propagation for Early Action Recognition

Early action recognition (action prediction) from limited preliminary ob...
research
11/24/2014

Beyond Gaussian Pyramid: Multi-skip Feature Stacking for Action Recognition

Most state-of-the-art action feature extractors involve differential ope...

Please sign up or login with your details

Forgot password? Click here to reset