Pushkar Shukla
University of California, Santa Barbara
18 Papers
41 Citations
Pushkar Shukla is an academic researcher from University of California, Santa Barbara. The author has contributed to research in topics: Computer science & Gesture recognition. The author has an hindex of 9, co-authored 18 publications. Previous affiliations of Pushkar Shukla include Indian Institute of Technology Roorkee & University of California.
Chat about Author
Papers
A Deep Learning Frame-Work for Recognizing Developmental Disorders
Pushkar Shukla,Tanu Gupta,Aradhya Saini,Priyanka Singh,Raman Balasubramanian +4 more
- 24 Mar 2017
TL;DR: A novel framework to detect developmental disorders from facial images based on Deep Convolutional Neural Networks for feature extraction and results indicate that the model performs better than average human intelligence in terms of differentiating amongst different disabilities.
77
Automatic Cricket Highlight Generation Using Event-Driven and Excitement-Based Features
Pushkar Shukla,Hemant Sadana,Apaar Bansal,Deepak Verma,Carlos Elmadjian,Balasubramanian Raman,Matthew Turk +6 more
- 18 Jun 2018
TL;DR: A model capable of automatically generating sports highlights with a focus on cricket is proposed that considers both event-based and excitement-based features to recognize and clip important events in a cricket match.
•Posted Content
Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
Keerthiram Murugesan,Mattia Atzeni,Pavan Kapanipathi,Pushkar Shukla,Sadhana Kumaravel,Gerald Tesauro,Kartik Talamadupula,Mrinmaya Sachan,Murray Campbell +8 more
TL;DR: This paper designs a new text-based gaming environment called TextWorld Commonsense (TWC) for training and evaluating RL agents with a specific kind of commonsense knowledge about objects, their attributes, and affordances, and shows that agents which incorporate Commonsense knowledge in TWC perform better, while acting more efficiently.
58
3D gaze estimation in the scene volume with a head-mounted eye tracker
Carlos Elmadjian,Pushkar Shukla,Antonio Diaz Tula,Carlos H. Morimoto +3 more
- 15 Jun 2018
TL;DR: This work exposes the limitations of widely used techniques for PoR estimation in 3D and proposes a new calibration procedure using an uncalibrated head-mounted binocular eye tracker coupled with an RGB-D camera to track 3D gaze within the scene volume.
38
•Posted Content
Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge.
Keerthiram Murugesan,Mattia Atzeni,Pushkar Shukla,Mrinmaya Sachan,Pavan Kapanipathi,Kartik Talamadupula +5 more
TL;DR: This paper presents one such instantiation of agents that use commonsense knowledge from ConceptNet to show promising performance on two text-based environments.
27