Unsupervised Feature Learning from Temporal Data
This work addresses the need for unsupervised learning methods in video analysis, offering an incremental improvement over existing supervised approaches.
The paper tackles the problem of unsupervised feature learning from 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.