activity
20192021
collaborators

5 papers

cs.CV2021

ShuffleBlock: Shuffle to Regularize Deep Convolutional Neural Networks

Sudhakar Kumawat, Gagan Kanojia, Shanmuganathan Raman

Deep neural networks have enormous representational power which leads them to overfit on most datasets. Thus, regularizing them is important in order to reduce overfitting and enha…

cs.CV2020

Learning to Sort Image Sequences via Accumulated Temporal Differences

Gagan Kanojia, Shanmuganathan Raman

Consider a set of n images of a scene with dynamic objects captured with a static or a handheld camera. Let the temporal order in which these images are captured be unknown. There…

cs.CV2019

Simultaneous Detection and Removal of Dynamic Objects in Multi-view Images

Gagan Kanojia, Shanmuganathan Raman

Consider a set of images of a scene consisting of moving objects captured using a hand-held camera. In this work, we propose an algorithm which takes this set of multi-view images…

cs.CV2019

Exploring Temporal Differences in 3D Convolutional Neural Networks

Gagan Kanojia, Sudhakar Kumawat, Shanmuganathan Raman

Traditional 3D convolutions are computationally expensive, memory intensive, and due to large number of parameters, they often tend to overfit. On the other hand, 2D CNNs are less…

cs.CV2019

Attentive Spatio-Temporal Representation Learning for Diving Classification

Gagan Kanojia, Sudhakar Kumawat, Shanmuganathan Raman

Competitive diving is a well recognized aquatic sport in which a person dives from a platform or a springboard into the water. Based on the acrobatics performed during the dive, di…