1st Place Solution for MOSE Track in CVPR 2024 PVUW Workshop: Complex Video Object Segmentation
This work addresses video object segmentation in complex scenarios for computer vision applications, but it is incremental as it builds on existing methods to improve performance in a specific challenge.
The paper tackled the challenge of tracking and segmenting multiple objects in complex scenes with occlusions and ambiguous definitions by proposing a semantic embedding video object segmentation model that uses salient features as queries, achieving first place with 84.45% on the test set of the PVUW Challenge 2024.
Tracking and segmenting multiple objects in complex scenes has always been a challenge in the field of video object segmentation, especially in scenarios where objects are occluded and split into parts. In such cases, the definition of objects becomes very ambiguous. The motivation behind the MOSE dataset is how to clearly recognize and distinguish objects in complex scenes. In this challenge, we propose a semantic embedding video object segmentation model and use the salient features of objects as query representations. The semantic understanding helps the model to recognize parts of the objects and the salient feature captures the more discriminative features of the objects. Trained on a large-scale video object segmentation dataset, our model achieves first place (\textbf{84.45\%}) in the test set of PVUW Challenge 2024: Complex Video Object Segmentation Track.