Saved in:
Bibliographic Details
Main Authors: Kalati, Mohammad Mohammadzadeh, Maleki, Farhad, McQuillan, Ian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.16183
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909748855570432
author Kalati, Mohammad Mohammadzadeh
Maleki, Farhad
McQuillan, Ian
author_facet Kalati, Mohammad Mohammadzadeh
Maleki, Farhad
McQuillan, Ian
contents Predicting and tracking objects in real-world scenarios is a critical challenge in Video Object Segmentation (VOS) tasks. Unsupervised VOS (UVOS) has the additional challenge of finding an initial segmentation of salient objects, which affects the entire process and keeps a permanent uncertainty about the object proposals. Moreover, deformation and fast motion can lead to temporal inconsistencies. To address these problems, we propose Frequent Temporally Integrated Objects (FTIO), a post-processing framework with two key components. First, we introduce a combined criterion to improve object selection, mitigating failures common in UVOS--particularly when objects are small or structurally complex--by extracting frequently appearing salient objects. Second, we present a three-stage method to correct temporal inconsistencies by integrating missing object mask regions. Experimental results demonstrate that FTIO achieves state-of-the-art performance in multi-object UVOS. Code is available at: https://github.com/MohammadMohammadzadehKalati/FTIO
format Preprint
id arxiv_https___arxiv_org_abs_2508_16183
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FTIO: Frequent Temporally Integrated Objects
Kalati, Mohammad Mohammadzadeh
Maleki, Farhad
McQuillan, Ian
Computer Vision and Pattern Recognition
Predicting and tracking objects in real-world scenarios is a critical challenge in Video Object Segmentation (VOS) tasks. Unsupervised VOS (UVOS) has the additional challenge of finding an initial segmentation of salient objects, which affects the entire process and keeps a permanent uncertainty about the object proposals. Moreover, deformation and fast motion can lead to temporal inconsistencies. To address these problems, we propose Frequent Temporally Integrated Objects (FTIO), a post-processing framework with two key components. First, we introduce a combined criterion to improve object selection, mitigating failures common in UVOS--particularly when objects are small or structurally complex--by extracting frequently appearing salient objects. Second, we present a three-stage method to correct temporal inconsistencies by integrating missing object mask regions. Experimental results demonstrate that FTIO achieves state-of-the-art performance in multi-object UVOS. Code is available at: https://github.com/MohammadMohammadzadehKalati/FTIO
title FTIO: Frequent Temporally Integrated Objects
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.16183