Reasoning Segmentation for Images and Videos: A Survey
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _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 |