Green Video Camouflaged Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xinyu, Chen, Hong-Shuo, Zhou, Zhiruo, You, Suya, Madni, Azad M., Kuo, C. -C. Jay
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908190575165440
author Wang, Xinyu
Chen, Hong-Shuo
Zhou, Zhiruo
You, Suya
Madni, Azad M.
Kuo, C. -C. Jay
author_facet Wang, Xinyu
Chen, Hong-Shuo
Zhou, Zhiruo
You, Suya
Madni, Azad M.
Kuo, C. -C. Jay
contents Camouflaged object detection (COD) aims to distinguish hidden objects embedded in an environment highly similar to the object. Conventional video-based COD (VCOD) methods explicitly extract motion cues or employ complex deep learning networks to handle the temporal information, which is limited by high complexity and unstable performance. In this work, we propose a green VCOD method named GreenVCOD. Built upon a green ICOD method, GreenVCOD uses long- and short-term temporal neighborhoods (TN) to capture joint spatial/temporal context information for decision refinement. Experimental results show that GreenVCOD offers competitive performance compared to state-of-the-art VCOD benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2501_10914
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Green Video Camouflaged Object Detection
Wang, Xinyu
Chen, Hong-Shuo
Zhou, Zhiruo
You, Suya
Madni, Azad M.
Kuo, C. -C. Jay
Computer Vision and Pattern Recognition
Camouflaged object detection (COD) aims to distinguish hidden objects embedded in an environment highly similar to the object. Conventional video-based COD (VCOD) methods explicitly extract motion cues or employ complex deep learning networks to handle the temporal information, which is limited by high complexity and unstable performance. In this work, we propose a green VCOD method named GreenVCOD. Built upon a green ICOD method, GreenVCOD uses long- and short-term temporal neighborhoods (TN) to capture joint spatial/temporal context information for decision refinement. Experimental results show that GreenVCOD offers competitive performance compared to state-of-the-art VCOD benchmarks.
title Green Video Camouflaged Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.10914