A
Ashish Mishra
Researcher at Indian Institute of Technology Madras
Publications - 31
Citations - 1517
Ashish Mishra is an academic researcher from Indian Institute of Technology Madras. The author has contributed to research in topics: Autoencoder & Generative model. The author has an hindex of 13, co-authored 31 publications receiving 1085 citations. Previous affiliations of Ashish Mishra include Indian Institute of Technology Kanpur.
Papers
More filters
Proceedings ArticleDOI
Generalized Zero-Shot Learning via Synthesized Examples
TL;DR: This work presents a generative framework for generalized zero-shot learning where the training and test classes are not necessarily disjoint, and can generate novel exemplars from seen/unseen classes, given their respective class attributes.
Proceedings ArticleDOI
A Generative Model for Zero Shot Learning Using Conditional Variational Autoencoders
TL;DR: In this paper, a conditional variational autoencoder (CVAE) is used to generate the samples from the given attributes and use the generated samples for classification of the unseen classes.
Posted Content
A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders
TL;DR: In this paper, a conditional variational autoencoder (CVAE) is used to generate the samples from the given attributes and use the generated samples for classification of the unseen classes.
Book ChapterDOI
A Zero-Shot Framework for Sketch Based Image Retrieval
TL;DR: Experiments on this new benchmark created from the “Sketchy” dataset demonstrate that the performance of these generative models is significantly better than several state-of-the-art approaches in the proposed zero-shot framework of the coarse-grained SBIR task.
Proceedings ArticleDOI
A Generative Approach to Zero-Shot and Few-Shot Action Recognition
TL;DR: A generative framework for zero-shot action recognition where some of the possible action classes do not occur in the training data, based on modeling each action class using a probability distribution whose parameters are functions of the attribute vector representing that action class.