3rd Place Solution for MOSE Track in CVPR 2024 PVUW workshop: Complex Video Object Segmentation
This is an incremental improvement for researchers in computer vision, specifically targeting complex video object segmentation scenarios.
The paper tackled video object segmentation on the MOSE dataset with complex occlusions, achieving a J&F score of 0.8139 and third place in a CVPR 2024 workshop competition.
Video Object Segmentation (VOS) is a vital task in computer vision, focusing on distinguishing foreground objects from the background across video frames. Our work draws inspiration from the Cutie model, and we investigate the effects of object memory, the total number of memory frames, and input resolution on segmentation performance. This report validates the effectiveness of our inference method on the coMplex video Object SEgmentation (MOSE) dataset, which features complex occlusions. Our experimental results demonstrate that our approach achieves a J\&F score of 0.8139 on the test set, securing the third position in the final ranking. These findings highlight the robustness and accuracy of our method in handling challenging VOS scenarios.