Transrac: Encoding multi-scale temporal correlation with transformers for repetitive action counting

H Hu, S Dong, Y Zhao, D Lian, Z Li… - Proceedings of the …, 2022 - openaccess.thecvf.com
Counting repetitive actions are widely seen in human activities such as physical exercise.
Existing methods focus on performing repetitive action counting in short videos, which is …

Real-time monitoring for manual operations with machine vision in smart manufacturing

P Lou, J Li, YH Zeng, B Chen, X Zhang - Journal of Manufacturing Systems, 2022 - Elsevier
Online real-time production process monitoring is the basis for intelligent manufacturing
refinement management. This paper proposes a contactless monitoring framework with …

Repetitive activity counting by sight and sound

Y Zhang, L Shao, CGM Snoek - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
This paper strives for repetitive activity counting in videos. Different from existing works,
which all analyze the visual video content only, we incorporate for the first time the …

Automatic repetitive action counting for construction worker ergonomic assessment

X Chen, Y Yu - Automation in Construction, 2024 - Elsevier
Work-related musculoskeletal disorders are the primary cause of nonfatal occupational
injuries in the construction industry. Accurate ergonomic assessment is essential to reduce …

Poserac: Pose saliency transformer for repetitive action counting

Z Yao, X Cheng, Y Zou - arxiv preprint arxiv:2303.08450, 2023 - arxiv.org
This paper presents a significant contribution to the field of repetitive action counting through
the introduction of a new approach called Pose Saliency Representation. The proposed …

Repetitive Action Counting with Hybrid Temporal Relation Modeling

K Li, X Peng, D Guo, X Yang… - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
Repetitive Action Counting (RAC) aims to count the number of repetitive actions occurring in
videos. In the real world, repetitive actions have great diversity and bring numerous …

Deep learning approaches for workout repetition counting and validation

B Ferreira, PM Ferreira, G Pinheiro, N Figueiredo… - Pattern Recognition …, 2021 - Elsevier
The study of the human body motion throughout different activities is one of the most
challenging and long-standing problems in Computer Vision. With the recent advances in …

Learning periodic tasks from human demonstrations

J Yang, J Zhang, C Settle, A Rai… - … on Robotics and …, 2022 - ieeexplore.ieee.org
We develop a method for learning periodic tasks from visual demonstrations. The core idea
is to leverage periodicity in the policy structure to model periodic aspects of the tasks. We …

How severe is benchmark-sensitivity in video self-supervised learning?

FM Thoker, H Doughty, P Bagad… - European Conference on …, 2022 - Springer
Despite the recent success of video self-supervised learning models, there is much still to be
understood about their generalization capability. In this paper, we investigate how sensitive …

View-agnostic Human Exercise Cataloging with Single MmWave Radar

A Liu, YT Lin, K Sundaresan - Proceedings of the ACM on Interactive …, 2024 - dl.acm.org
Advances in mmWave-based sensing have enabled a privacy-friendly approach to pose
and gesture recognition. Yet, providing robustness with the sparsity of reflected signals has …