R-Clustering for Egocentric Video Segmentation
This addresses the challenge of accurate temporal segmentation for egocentric videos, which is incremental as it combines existing techniques to improve performance.
The paper tackles the problem of oversegmentation in egocentric video temporal segmentation by integrating a statistical change detector (ADWIN) with agglomerative clustering in an energy-minimization framework, resulting in a method that outperforms state-of-the-art clustering methods on datasets of over 13,000 images.
In this paper, we present a new method for egocentric video temporal segmentation based on integrating a statistical mean change detector and agglomerative clustering(AC) within an energy-minimization framework. Given the tendency of most AC methods to oversegment video sequences when clustering their frames, we combine the clustering with a concept drift detection technique (ADWIN) that has rigorous guarantee of performances. ADWIN serves as a statistical upper bound for the clustering-based video segmentation. We integrate both techniques in an energy-minimization framework that serves to disambiguate the decision of both techniques and to complete the segmentation taking into account the temporal continuity of video frames descriptors. We present experiments over egocentric sets of more than 13.000 images acquired with different wearable cameras, showing that our method outperforms state-of-the-art clustering methods.