Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation
This work addresses the need for automatic video understanding without costly frame-level annotations, though it is incremental as it builds on existing clustering techniques.
The paper tackles the problem of unsupervised action segmentation in videos by proposing a temporally-weighted hierarchical clustering algorithm that groups semantically consistent frames without requiring training or annotations, achieving significant performance improvements over existing unsupervised methods on five challenging datasets.
Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks. For this and other video understanding tasks, supervised approaches have achieved encouraging performance but require a high volume of detailed frame-level annotations. We present a fully automatic and unsupervised approach for segmenting actions in a video that does not require any training. Our proposal is an effective temporally-weighted hierarchical clustering algorithm that can group semantically consistent frames of the video. Our main finding is that representing a video with a 1-nearest neighbor graph by taking into account the time progression is sufficient to form semantically and temporally consistent clusters of frames where each cluster may represent some action in the video. Additionally, we establish strong unsupervised baselines for action segmentation and show significant performance improvements over published unsupervised methods on five challenging action segmentation datasets. Our code is available at https://github.com/ssarfraz/FINCH-Clustering/tree/master/TW-FINCH