Saved in:
Bibliographic Details
Main Authors: Shen, Yiqing, Li, Chenjia, Xiong, Fei, Jeong, Jeong-O, Wang, Tianpeng, Latman, Michael, Unberath, Mathias
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.18816
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910967207559168
author Shen, Yiqing
Li, Chenjia
Xiong, Fei
Jeong, Jeong-O
Wang, Tianpeng
Latman, Michael
Unberath, Mathias
author_facet Shen, Yiqing
Li, Chenjia
Xiong, Fei
Jeong, Jeong-O
Wang, Tianpeng
Latman, Michael
Unberath, Mathias
contents Reasoning Segmentation (RS) aims to delineate objects based on implicit text queries, the interpretation of which requires reasoning and knowledge integration. Unlike the traditional formulation of segmentation problems that relies on fixed semantic categories or explicit prompting, RS bridges the gap between visual perception and human-like reasoning capabilities, facilitating more intuitive human-AI interaction through natural language. Our work presents the first comprehensive survey of RS for image and video processing, examining 26 state-of-the-art methods together with a review of the corresponding evaluation metrics, as well as 29 datasets and benchmarks. We also explore existing applications of RS across diverse domains and identify their potential extensions. Finally, we identify current research gaps and highlight promising future directions.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18816
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reasoning Segmentation for Images and Videos: A Survey
Shen, Yiqing
Li, Chenjia
Xiong, Fei
Jeong, Jeong-O
Wang, Tianpeng
Latman, Michael
Unberath, Mathias
Computer Vision and Pattern Recognition
Reasoning Segmentation (RS) aims to delineate objects based on implicit text queries, the interpretation of which requires reasoning and knowledge integration. Unlike the traditional formulation of segmentation problems that relies on fixed semantic categories or explicit prompting, RS bridges the gap between visual perception and human-like reasoning capabilities, facilitating more intuitive human-AI interaction through natural language. Our work presents the first comprehensive survey of RS for image and video processing, examining 26 state-of-the-art methods together with a review of the corresponding evaluation metrics, as well as 29 datasets and benchmarks. We also explore existing applications of RS across diverse domains and identify their potential extensions. Finally, we identify current research gaps and highlight promising future directions.
title Reasoning Segmentation for Images and Videos: A Survey
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.18816