Raviteja Vemulapalli

TL;DR: In this paper, an end-to-end trainable frame-recurrent video super-resolution framework was proposed that uses the previously inferred HR estimate to super-resolve the subsequent frame.

TL;DR: This work uses rolling maps for recognizing human actions from 3D skeletal data and unwrap the action curves onto the Lie algebra so3 × ... × so3 (which is a vector space) by combining the logarithm map with rolling maps, and perform classification in the Liegebra.

TL;DR: A simple and effective contrastive learning-based training strategy in which the network is pretrain the network using a pixel-wise, label-based contrastive loss, and then fine-tune it using the cross-entropy loss, which increases intra-class compactness and inter-class separability, thereby resulting in a better pixel classifier.

TL;DR: A novel deep network, which is referred to as Gaussian Mean Field (GMF) network, whose layers perform mean field inference over a Gaussian CRF, which outperforms various recent semantic segmentation approaches that combine CNNs with discrete CRF models.