Towards Open-Vocabulary Video Semantic Segmentation
This addresses the challenge of segmenting novel categories in videos for computer vision applications, but it appears incremental as it builds on existing segmentation methods with enhancements for open-vocabulary settings.
The paper tackles the problem of semantic segmentation in videos for unfamiliar categories by introducing the Open Vocabulary Video Semantic Segmentation (OV-VSS) task and proposing OV2VSS, a baseline model that integrates spatial-temporal fusion and video text encoding, achieving improved performance on benchmark datasets like VSPW and Cityscapes.
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.