R
Ravi Kiran Sarvadevabhatla
Researcher at International Institute of Information Technology, Hyderabad
Publications - 81
Citations - 1188
Ravi Kiran Sarvadevabhatla is an academic researcher from International Institute of Information Technology, Hyderabad. The author has contributed to research in topics: Computer science & Sketch. The author has an hindex of 15, co-authored 67 publications receiving 899 citations. Previous affiliations of Ravi Kiran Sarvadevabhatla include Indian Institutes of Information Technology & Honda.
Papers
More filters
Proceedings ArticleDOI
DeLiGAN: Generative Adversarial Networks for Diverse and Limited Data
TL;DR: DeLiGAN as mentioned in this paper reparameterizes the latent generative space as a mixture model and learns the mixture models parameters along with those of GAN, which can generate images of handwritten digits, objects and hand-drawn sketches.
Posted Content
DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data
TL;DR: The proposed DeLiGAN can generate images of handwritten digits, objects and hand-drawn sketches, all using limited amounts of data, and introduces a modified version of inception-score, a measure which has been found to correlate well with human assessment of generated samples.
Journal ArticleDOI
A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
Suraj Srinivas,Ravi Kiran Sarvadevabhatla,Konda Reddy Mopuri,Nikita Prabhu,Srinivas S S Kruthiventi,R. Venkatesh Babu +5 more
TL;DR: A recipe-style survey of one form of deep networks widely used in computer vision - convolutional neural networks (CNNs) is considered and it is hoped that this guide will serve as a guide, particularly for novice practitioners intending to use deep-learning techniques for computer vision.
Journal ArticleDOI
A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
Suraj Srinivas,Ravi Kiran Sarvadevabhatla,Konda Reddy Mopuri,Nikita Prabhu,Srinivas S S Kruthiventi,R. Venkatesh Babu +5 more
TL;DR: In this paper, a survey of deep learning techniques for computer vision is presented, focusing on one form of deep networks widely used in computer vision -convolutional neural networks (CNNs).
Proceedings ArticleDOI
Learning together: ASIMO developing an interactive learning partnership with children
TL;DR: Promissory evidence shows that learning styles and general features matter especially for younger children, and which features in robots led to changes in learning and behavior is determined.