Towards Open-Vocabulary Video Semantic Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929627818098688 |
|---|---|
| author | Li, Xinhao Liu, Yun Sun, Guolei Wu, Min Zhang, Le Zhu, Ce |
| author_facet | Li, Xinhao Liu, Yun Sun, Guolei Wu, Min Zhang, Le Zhu, Ce |
| contents | Semantic segmentation in videos has been a focal point of recent research. However, existing models encounter challenges when faced with unfamiliar categories. To address this, we introduce the Open Vocabulary Video Semantic Segmentation (OV-VSS) task, designed to accurately segment every pixel across a wide range of open-vocabulary categories, including those that are novel or previously unexplored. To enhance OV-VSS performance, we propose a robust baseline, OV2VSS, which integrates a spatial-temporal fusion module, allowing the model to utilize temporal relationships across consecutive frames. Additionally, we incorporate a random frame enhancement module, broadening the model's understanding of semantic context throughout the entire video sequence. Our approach also includes video text encoding, which strengthens the model's capability to interpret textual information within the video context. Comprehensive evaluations on benchmark datasets such as VSPW and Cityscapes highlight OV-VSS's zero-shot generalization capabilities, especially in handling novel categories. The results validate OV2VSS's effectiveness, demonstrating improved performance in semantic segmentation tasks across diverse video datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_09329 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Open-Vocabulary Video Semantic Segmentation Li, Xinhao Liu, Yun Sun, Guolei Wu, Min Zhang, Le Zhu, Ce Multimedia Artificial Intelligence Semantic segmentation in videos has been a focal point of recent research. However, existing models encounter challenges when faced with unfamiliar categories. To address this, we introduce the Open Vocabulary Video Semantic Segmentation (OV-VSS) task, designed to accurately segment every pixel across a wide range of open-vocabulary categories, including those that are novel or previously unexplored. To enhance OV-VSS performance, we propose a robust baseline, OV2VSS, which integrates a spatial-temporal fusion module, allowing the model to utilize temporal relationships across consecutive frames. Additionally, we incorporate a random frame enhancement module, broadening the model's understanding of semantic context throughout the entire video sequence. Our approach also includes video text encoding, which strengthens the model's capability to interpret textual information within the video context. Comprehensive evaluations on benchmark datasets such as VSPW and Cityscapes highlight OV-VSS's zero-shot generalization capabilities, especially in handling novel categories. The results validate OV2VSS's effectiveness, demonstrating improved performance in semantic segmentation tasks across diverse video datasets. |
| title | Towards Open-Vocabulary Video Semantic Segmentation |
| topic | Multimedia Artificial Intelligence |
| url | https://arxiv.org/abs/2412.09329 |