A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908408956846080 |
|---|---|
| author | Xie, Guohuan Hesham, Syed Ariff Syed Guo, Wenya Li, Bing Cheng, Ming-Ming Sun, Guolei Liu, Yun |
| author_facet | Xie, Guohuan Hesham, Syed Ariff Syed Guo, Wenya Li, Bing Cheng, Ming-Ming Sun, Guolei Liu, Yun |
| contents | Video Scene Parsing (VSP) has emerged as a cornerstone in computer vision, facilitating the simultaneous segmentation, recognition, and tracking of diverse visual entities in dynamic scenes. In this survey, we present a holistic review of recent advances in VSP, covering a wide array of vision tasks, including Video Semantic Segmentation (VSS), Video Instance Segmentation (VIS), Video Panoptic Segmentation (VPS), as well as Video Tracking and Segmentation (VTS), and Open-Vocabulary Video Segmentation (OVVS). We systematically analyze the evolution from traditional hand-crafted features to modern deep learning paradigms -- spanning from fully convolutional networks to the latest transformer-based architectures -- and assess their effectiveness in capturing both local and global temporal contexts. Furthermore, our review critically discusses the technical challenges, ranging from maintaining temporal consistency to handling complex scene dynamics, and offers a comprehensive comparative study of datasets and evaluation metrics that have shaped current benchmarking standards. By distilling the key contributions and shortcomings of state-of-the-art methodologies, this survey highlights emerging trends and prospective research directions that promise to further elevate the robustness and adaptability of VSP in real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13552 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects Xie, Guohuan Hesham, Syed Ariff Syed Guo, Wenya Li, Bing Cheng, Ming-Ming Sun, Guolei Liu, Yun Computer Vision and Pattern Recognition Video Scene Parsing (VSP) has emerged as a cornerstone in computer vision, facilitating the simultaneous segmentation, recognition, and tracking of diverse visual entities in dynamic scenes. In this survey, we present a holistic review of recent advances in VSP, covering a wide array of vision tasks, including Video Semantic Segmentation (VSS), Video Instance Segmentation (VIS), Video Panoptic Segmentation (VPS), as well as Video Tracking and Segmentation (VTS), and Open-Vocabulary Video Segmentation (OVVS). We systematically analyze the evolution from traditional hand-crafted features to modern deep learning paradigms -- spanning from fully convolutional networks to the latest transformer-based architectures -- and assess their effectiveness in capturing both local and global temporal contexts. Furthermore, our review critically discusses the technical challenges, ranging from maintaining temporal consistency to handling complex scene dynamics, and offers a comprehensive comparative study of datasets and evaluation metrics that have shaped current benchmarking standards. By distilling the key contributions and shortcomings of state-of-the-art methodologies, this survey highlights emerging trends and prospective research directions that promise to further elevate the robustness and adaptability of VSP in real-world applications. |
| title | A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.13552 |