Institution
Delhi Technological University
Education•New Delhi, India•
About: Delhi Technological University is a education organization based out in New Delhi, India. It is known for research contribution in the topics: Computer science & Control theory. The organization has 4427 authors who have published 6761 publications receiving 71035 citations. The organization is also known as: Delhi College of Engineering & DTU.
Topics: Computer science, Control theory, Artificial neural network, Photovoltaic system, Deep learning
Papers published on a yearly basis
Papers
More filters
••
TL;DR: The results of experiments conducted using clinical patient samples reveal that this nucleic acid sensor can be used to distinguish CML positive and the negative control samples and has a shelf life of about 6 weeks.
69 citations
••
TL;DR: In this article, a detailed discussion on mechanical (tensile, compressive, flexural, impact strength) and tribological properties (friction and specific wear rate) have been reported.
69 citations
••
TL;DR: A new hybrid technique based on the combination of evolutionary algorithm, that is, grey-wolf optimisation (GWO) and artificial neural network (ANN), abbreviated as ANN-GWO model, can estimate the maximum settlement of GRSF under service loads in a reliable and intelligent way and can be deployed as a predictive tool for the preliminary design of G RSF.
68 citations
••
01 Jan 2019TL;DR: In this paper, a self-supervised learning method is proposed to jointly reason about spatial and temporal context for video recognition, where multiple video frames are divided into grids of patches and trained a network to solve jigsaw puzzles on these patches from multiple frames.
Abstract: We propose a self-supervised learning method to jointly reason about spatial and temporal context for video recognition. Recent self-supervised approaches have used spatial context [9, 34] as well as temporal coherency [32] but a combination of the two requires extensive preprocessing such as tracking objects through millions of video frames [59] or computing optical flow to determine frame regions with high motion [30]. We propose to combine spatial and temporal context in one self-supervised framework without any heavy preprocessing. We divide multiple video frames into grids of patches and train a network to solve jigsaw puzzles on these patches from multiple frames. So the network is trained to correctly identify the position of a patch within a video frame as well as the position of a patch over time. We also propose a novel permutation strategy that outperforms random permutations while significantly reducing computational and memory constraints. We use our trained network for transfer learning tasks such as video activity recognition and demonstrate the strength of our approach on two benchmark video action recognition datasets without using a single frame from these datasets for unsupervised pretraining of our proposed video jigsaw network.
68 citations
••
TL;DR: A model which validates the veracity of image text by exploring it on web and then checking the credibility of the top 15 Google search results by subsequently calculating the reality parameter (Rp), which if exceeds a threshold value, an event is classified as real else fake.
68 citations
Authors
Showing all 4530 results
Name | H-index | Papers | Citations |
---|---|---|---|
Shaji Kumar | 111 | 1265 | 53237 |
Lars A. Buchhave | 105 | 408 | 46100 |
Anil Kumar | 99 | 2124 | 64825 |
Bansi D. Malhotra | 75 | 375 | 19419 |
C. P. Singh | 68 | 337 | 17448 |
Ramesh Chandra | 66 | 620 | 16293 |
Rajiv S. Mishra | 64 | 591 | 22210 |
William W. Craig | 58 | 316 | 14311 |
S.G. Deshmukh | 56 | 183 | 11566 |
Jay Singh | 51 | 301 | 8655 |
Neeraj Kumar | 50 | 207 | 7670 |
Erling Halfdan Stenby | 50 | 285 | 8500 |
Devendra Singh | 49 | 314 | 10386 |
Federico Calle-Vallejo | 46 | 113 | 11239 |
Rajesh Singh | 46 | 692 | 10339 |