D 3 TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation
Computer Vision and Pattern Recognition, pp. 3546-3555, 2019.
We address weakly supervised action alignment and segmentation in videos, where only the order of occurring actions is available during training. We propose Discriminative Differentiable Dynamic Time Warping (D3TW), the first discriminative model using weak ordering supervision. The key technical challenge for discriminative modeling with...More
PPT (Upload PPT)