MAE-GEBD:Winning the CVPR'2023 LOVEU-GEBD Challenge
This is an incremental improvement for video segmentation in computer vision.
The paper tackles the Generic Event Boundary Detection (GEBD) task by improving a previous method through adjustments in data processing, loss function, and segmentation alignment, achieving an F1 score of 86.03% on the Kinetics-GEBD test set, a 0.09% increase over their 2022 result.
The Generic Event Boundary Detection (GEBD) task aims to build a model for segmenting videos into segments by detecting general event boundaries applicable to various classes. In this paper, based on last year's MAE-GEBD method, we have improved our model performance on the GEBD task by adjusting the data processing strategy and loss function. Based on last year's approach, we extended the application of pseudo-label to a larger dataset and made many experimental attempts. In addition, we applied focal loss to concentrate more on difficult samples and improved our model performance. Finally, we improved the segmentation alignment strategy used last year, and dynamically adjusted the segmentation alignment method according to the boundary density and duration of the video, so that our model can be more flexible and fully applicable in different situations. With our method, we achieve an F1 score of 86.03% on the Kinetics-GEBD test set, which is a 0.09% improvement in the F1 score compared to our 2022 Kinetics-GEBD method.