C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation
This work addresses video analysis for applications like surveillance or robotics, offering a flexible approach for both supervised and unsupervised learning, but it is incremental as it builds on existing encoder-decoder architectures.
The paper tackles temporal action segmentation in videos by proposing C2F-TCN, an encoder-decoder framework with a coarse-to-fine ensemble and temporal feature augmentation, achieving results comparable to fully supervised methods with only 40% labeled data in semi-supervised settings.
Temporal action segmentation tags action labels for every frame in an input untrimmed video containing multiple actions in a sequence. For the task of temporal action segmentation, we propose an encoder-decoder-style architecture named C2F-TCN featuring a "coarse-to-fine" ensemble of decoder outputs. The C2F-TCN framework is enhanced with a novel model agnostic temporal feature augmentation strategy formed by the computationally inexpensive strategy of the stochastic max-pooling of segments. It produces more accurate and well-calibrated supervised results on three benchmark action segmentation datasets. We show that the architecture is flexible for both supervised and representation learning. In line with this, we present a novel unsupervised way to learn frame-wise representation from C2F-TCN. Our unsupervised learning approach hinges on the clustering capabilities of the input features and the formation of multi-resolution features from the decoder's implicit structure. Further, we provide the first semi-supervised temporal action segmentation results by merging representation learning with conventional supervised learning. Our semi-supervised learning scheme, called ``Iterative-Contrastive-Classify (ICC)'', progressively improves in performance with more labeled data. The ICC semi-supervised learning in C2F-TCN, with 40% labeled videos, performs similar to fully supervised counterparts.