S
Snehasis Mukherjee
Researcher at Indian Institutes of Information Technology
Publications - 61
Citations - 1026
Snehasis Mukherjee is an academic researcher from Indian Institutes of Information Technology. The author has contributed to research in topics: Convolutional neural network & Deep learning. The author has an hindex of 11, co-authored 56 publications receiving 582 citations. Previous affiliations of Snehasis Mukherjee include Shiv Nadar University & National Institute of Standards and Technology.
Papers
More filters
BookDOI
Computer Vision, Graphics, and Image Processing
Snehasis Mukherjee,Suvadip Mukherjee,Dipti Prasad Mukherjee,Jayanthi Sivaswamy,Suyash Awate,Srirangaraj Setlur,Anoop M. Namboodiri,Santanu Chaudhury +7 more
TL;DR: A novel intelligent multiple watermarking techniques are proposed that has reduced the amount of data to be embedded and consequently improved perceptual quality of the watermarked image.
Journal ArticleDOI
Impact of fully connected layers on performance of convolutional neural networks for image classification
TL;DR: Shabbeersh et al. as mentioned in this paper tried to find the relationship between Fully Connected (FC) layers with some of the characteristics of the datasets, and performed experiments with four CNN architectures having different depths.
Journal ArticleDOI
diffGrad: An Optimization Method for Convolutional Neural Networks
Shiv Ram Dubey,Soumendu Chakraborty,Swalpa Kumar Roy,Snehasis Mukherjee,Satish K. Singh,Bidyut B. Chaudhuri +5 more
TL;DR: A novel optimizer is proposed based on the difference between the present and the immediate past gradient, diffGrad, which shows that diffGrad outperforms other optimizers and performs uniformly well for training CNN using different activation functions.
Proceedings ArticleDOI
Spontaneous Facial Micro-Expression Recognition using 3D Spatiotemporal Convolutional Neural Networks
TL;DR: Two 3D-CNN methods are proposed: MicroExpSTCNN and MicroExpFuseNet, for spontaneous facial micro-expression recognition by exploiting the spatiotemporal information in CNN framework, which outperforms the state-of-the-art methods.
Journal ArticleDOI
Recognizing Human Action at a Distance in Video by Key Poses
TL;DR: A graph theoretic technique for recognizing human actions at a distance in a video by modeling the visual senses associated with poses and introduces a “meaningful” threshold on centrality measure that selects key poses for each action type.