Given an untrimmed video, repetitive actions counting aims to estimate the number of repetitions of class-agnostic actions. To handle the various length of videos and repetitive actions, also optimization challenges in end-to-end video model training, down-sampling is commonly utilized in recent state-of-the-art methods, leading to ignorance of several repetitive samples. In this paper, we attempt to understand repetitive actions from a full temporal resolution view, by combining offline feature extraction and temporal convolution networks. The former step enables us to train repetition counting network without down-sampling while preserving all repetitions regardless of the video length and action frequency, and the later network models all frames in a flexible and dynamically expanding temporal receptive field to retrieve all repetitions with a global aspect. Besides, temporal self-similarity matrix is used in our model to represent the correlation of action, which contains much cycle information in time series. We experimentally demonstrate that our method achieves better or comparable performance in three public datasets, i.e., TransRAC, UCFRep and QUVA. We expect this work will encourage our community to think about the importance of full temporal resolution.
Full Resolution Repetition Counting
Lect.Notes Computer
International Conference on Intelligent Robotics and Applications ; 2023 ; Hangzhou, China July 05, 2023 - July 07, 2023
2023-10-21
12 pages
Article/Chapter (Book)
Electronic Resource
English
Repetition counting , Temporal convolution networks , Full temporal resolution , Temporal self-similarity matrix Artificial Intelligence , Software Engineering/Programming and Operating Systems , Computer Applications , Computer Science , Special Purpose and Application-Based Systems , Computer Communication Networks , User Interfaces and Human Computer Interaction
Full Resolution Repetition Counting
TIBKAT | 2023
|CORRESPONDENCE - Doppler Ambiguity Resolution Using Optimal Multiple Pulse Repetition Frequencies
Online Contents | 1999
|High Time Resolution Photon Counting 3D Imaging Sensors
British Library Conference Proceedings | 2016
|