Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yu, Zifan, Tavakoli, Erfan Bank, Chen, Meida, You, Suya, Rao, Raghuveer, Agarwal, Sanjeev, Ren, Fengbo
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2311.02535
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910315557421056
author Yu, Zifan
Tavakoli, Erfan Bank
Chen, Meida
You, Suya
Rao, Raghuveer
Agarwal, Sanjeev
Ren, Fengbo
author_facet Yu, Zifan
Tavakoli, Erfan Bank
Chen, Meida
You, Suya
Rao, Raghuveer
Agarwal, Sanjeev
Ren, Fengbo
contents The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patterns caused by both objects and camera movement. In this paper, we introduce TokenMotion (TMNet), which employs a transformer-based model to enhance VCOD by extracting motion-guided features using a learnable token selection. Evaluated on the challenging MoCA-Mask dataset, TMNet achieves state-of-the-art performance in VCOD. It outperforms the existing state-of-the-art method by a 12.8% improvement in weighted F-measure, an 8.4% enhancement in S-measure, and a 10.7% boost in mean IoU. The results demonstrate the benefits of utilizing motion-guided features via learnable token selection within a transformer-based framework to tackle the intricate task of VCOD.
format Preprint
id arxiv_https___arxiv_org_abs_2311_02535
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection
Yu, Zifan
Tavakoli, Erfan Bank
Chen, Meida
You, Suya
Rao, Raghuveer
Agarwal, Sanjeev
Ren, Fengbo
Computer Vision and Pattern Recognition
The area of Video Camouflaged Object Detection (VCOD) presents unique challenges in the field of computer vision due to texture similarities between target objects and their surroundings, as well as irregular motion patterns caused by both objects and camera movement. In this paper, we introduce TokenMotion (TMNet), which employs a transformer-based model to enhance VCOD by extracting motion-guided features using a learnable token selection. Evaluated on the challenging MoCA-Mask dataset, TMNet achieves state-of-the-art performance in VCOD. It outperforms the existing state-of-the-art method by a 12.8% improvement in weighted F-measure, an 8.4% enhancement in S-measure, and a 10.7% boost in mean IoU. The results demonstrate the benefits of utilizing motion-guided features via learnable token selection within a transformer-based framework to tackle the intricate task of VCOD.
title TokenMotion: Motion-Guided Vision Transformer for Video Camouflaged Object Detection Via Learnable Token Selection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.02535