5 papers
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…
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…
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…
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…
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…