Please use this identifier to cite or link to this item:
Title: Towards cumulative race time regression in sports: I3D ConvNet transfer learning in ultra-distance running events
Authors: Freire-Obregón, David 
Lorenzo-Navarro, Javier 
Santana, Oliverio J. 
Hernández-Sosa, Daniel 
Castrillon-Santana, Modesto 
UNESCO Clasification: 33 Ciencias tecnológicas
Issue Date: 2022
Publisher: IEEE
Journal: Proceedings - International Conference on Pattern Recognition 
Conference: 22nd International Conference on Pattern Recognition (ICPR) 
Abstract: Predicting an athlete's performance based on short footage is highly challenging. Performance prediction requires high domain knowledge and enough evidence to infer an appropriate quality assessment. Sports pundits can often infer this kind of information in real-time. In this paper, we propose regressing an ultra-distance runner cumulative race time (CRT), i.e., the time the runner has been in action since the race start, by using only a few seconds of footage as input. We modified the I3D ConvNet backbone slightly and trained a newly added regressor for that purpose. We use appropriate pre-processing of the visual input to enable transfer learning from a specific runner. We show that the resulting neural network can provide a remarkable performance for short input footage: 18 minutes and a half mean absolute error in estimating the CRT for runners who have been in action from 8 to 20 hours. Our methodology has several favorable properties: it does not require a human expert to provide any insight, it can be used at any moment during the race by just observing a runner, and it can inform the race staff about a runner at any given time.
ISBN: 9781665490627
ISSN: 1051-4651
DOI: 10.1109/ICPR56361.2022.9956174
Source: Proceedings - International Conference on Pattern Recognition[ISSN 1051-4651],v. 2022-August, p. 805-811, (Enero 2022)
Appears in Collections:Actas de congresos
Show full item record

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.