P
Prathosh Ap
Researcher at Indian Institute of Technology Delhi
Publications - 28
Citations - 121
Prathosh Ap is an academic researcher from Indian Institute of Technology Delhi. The author has contributed to research in topics: Generative model & Prior probability. The author has an hindex of 5, co-authored 26 publications receiving 68 citations.
Papers
More filters
Journal ArticleDOI
Guided Weak Supervision for Action Recognition with Scarce Data to Assess Skills of Children with Autism
TL;DR: In this paper, a technique called Guided Weak Supervision is proposed to automate the response measurement through video recording of the scene following the use of deep neural models for human action recognition from videos.
Posted Content
Target-Independent Domain Adaptation for WBC Classification using Generative Latent Search
TL;DR: A method in which a latent-variable generative model based on variational inference is used to simultaneously sample and find the ‘closest-clone’ from the source distribution through an optimization procedure in the latent space is proposed.
Book ChapterDOI
Unsupervised Domain Adaptation for Semantic Segmentation of NIR Images Through Generative Latent Search.
TL;DR: In this article, the authors cast the skin segmentation problem as that of target-independent unsupervised domain adaptation (UDA) where they used the data from the Red-channel of the visible-range to develop skin segmentations algorithm on NIR images.
Proceedings ArticleDOI
Detection of Glottal Closure Instants from Raw Speech using Convolutional Neural Networks
TL;DR: GCI detection is cast as a supervised multi-task learning problem solved using a deep convolutional neural network jointly optimizing a classification and regression cost and the results compare well with the state-of-the-art algorithms while performing better in the case of presence of real-world non-stationary noise.
Posted Content
Unsupervised Domain Adaptation for Semantic Segmentation of NIR Images through Generative Latent Search
TL;DR: The existence of 'nearest-clone' is proved and a method to find it through an optimization algorithm over the latent space of a Deep generative model based on variational inference is proposed.