Salvato in:
Dettagli Bibliografici
Autori principali: Alkanat, Tunc, Akdag, Erkut, Bondarev, Egor, De With, Peter H. N.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2403.06616
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917610474438656
author Alkanat, Tunc
Akdag, Erkut
Bondarev, Egor
De With, Peter H. N.
author_facet Alkanat, Tunc
Akdag, Erkut
Bondarev, Egor
De With, Peter H. N.
contents Temporal localization of driving actions plays a crucial role in advanced driver-assistance systems and naturalistic driving studies. However, this is a challenging task due to strict requirements for robustness, reliability and accurate localization. In this work, we focus on improving the overall performance by efficiently utilizing video action recognition networks and adapting these to the problem of action localization. To this end, we first develop a density-guided label smoothing technique based on label probability distributions to facilitate better learning from boundary video-segments that typically include multiple labels. Second, we design a post-processing step to efficiently fuse information from video-segments and multiple camera views into scene-level predictions, which facilitates elimination of false positives. Our methodology yields a competitive performance on the A2 test set of the naturalistic driving action recognition track of the 2022 NVIDIA AI City Challenge with an F1 score of 0.271.
format Preprint
id arxiv_https___arxiv_org_abs_2403_06616
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Density-Guided Label Smoothing for Temporal Localization of Driving Actions
Alkanat, Tunc
Akdag, Erkut
Bondarev, Egor
De With, Peter H. N.
Computer Vision and Pattern Recognition
Temporal localization of driving actions plays a crucial role in advanced driver-assistance systems and naturalistic driving studies. However, this is a challenging task due to strict requirements for robustness, reliability and accurate localization. In this work, we focus on improving the overall performance by efficiently utilizing video action recognition networks and adapting these to the problem of action localization. To this end, we first develop a density-guided label smoothing technique based on label probability distributions to facilitate better learning from boundary video-segments that typically include multiple labels. Second, we design a post-processing step to efficiently fuse information from video-segments and multiple camera views into scene-level predictions, which facilitates elimination of false positives. Our methodology yields a competitive performance on the A2 test set of the naturalistic driving action recognition track of the 2022 NVIDIA AI City Challenge with an F1 score of 0.271.
title Density-Guided Label Smoothing for Temporal Localization of Driving Actions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.06616