Unsupervised Learning of Spatiotemporally Coherent Metrics
This work addresses the problem of reducing reliance on labeled data for video analysis, but it is incremental as it builds on existing unsupervised learning techniques.
The paper tackles unsupervised feature learning from unlabeled video data by exploiting temporal coherence between adjacent frames, resulting in a trained encoder that defines a more temporally and semantically coherent metric.
Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity. We establish a connection between slow feature learning to metric learning and show that the trained encoder can be used to define a more temporally and semantically coherent metric.