Recognition of action phases from spatio-temporal intermediate representations in amateur sports competition videos
Authors:
- Lazhar BouachaLBLazhar Bouacha
- Thierry MagnienTMThierry Magnien
- Laurent WendlingLWLaurent Wendling
- Camille KurtzCKCamille Kurtz
Open Access
- 13 April 2026
- journal article
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 268
Abstract
No abstract availableFunding Information
- Association Nationale de la Recherche et de la Technologie
This publication has 21 references indexed in Scilit:
- Make Your ViT-Based Multi-view 3D Detectors Faster via Token Compression2024
- MobileNetV4: Universal Models for the Mobile Ecosystem2024
- A fully automatic method for segmentation of soccer playing fieldsScientific Reports, 2023
- Continual 3D Convolutional Neural Networks for Real-time Processing of Videos2022
- RAFT: Recurrent All-Pairs Field Transforms for Optical Flow2020
- A Closer Look at Spatiotemporal Convolutions for Action Recognition2018
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- Deep Residual Learning for Image Recognition2016
- Dense Trajectories and Motion Boundary Descriptors for Action RecognitionInternational Journal of Computer Vision, 2013