Weakly Supervised Energy-Based Learning for Action Segmentation

Jun Li, Peng Lei, Sinisa Todorovic; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 6243-6251


This paper is about labeling video frames with action classes under weak supervision in training, where we have access to a temporal ordering of actions, but their start and end frames in training videos are unknown. Following prior work, we use an HMM grounded on a Gated Recurrent Unit (GRU) for frame labeling. Our key contribution is a new constrained discriminative forward loss (CDFL) that we use for training the HMM and GRU under weak supervision. While prior work typically estimates the loss on a single, inferred video segmentation, our CDFL discriminates between the energy of all valid and invalid frame labelings of a training video. A valid frame labeling satisfies the ground-truth temporal ordering of actions, whereas an invalid one violates the ground truth. We specify an efficient recursive algorithm for computing the CDFL in terms of the logadd function of the segmentation energy. Our evaluation on action segmentation and alignment gives superior results to those of the state of the art on the benchmark Breakfast Action, Hollywood Extended, and 50Salads datasets.

Related Material

[pdf] [video]
author = {Li, Jun and Lei, Peng and Todorovic, Sinisa},
title = {Weakly Supervised Energy-Based Learning for Action Segmentation},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}