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. †

No abstract

No abstract

Anatomic, dynamic, and perfusion imaging using contrast-enhanced CT allows characterization of left ventricular anatomy and 3D scar and BZ substrate. Integration of reconstructed 3D data sets into clinical mapping systems supplements information of voltage mapping and may enable new image approaches for substrate-guided ventricular tachycardia ablation.

We found that PET/CT fusion imaging is able to accurately assess left ventricular scar and its border zone. The integration of a 3D scar map into a clinical mapping system is feasible and may allow supplementary scar characterization that is not available from voltage maps. This technique could significantly facilitate substrate-based VT ablations.