Login
Talks & Seminars
Title: Data-Driven Content Creation and Human Pose Estimation
Dr. Arjun Jain, Arjun Jain is a post-doctoral researcher at the Computer Science department at New York University's Courant Institute.
Date & Time: October 29, 2014 11:00
Venue: Conference Room, 1st floor, Kanwal Rekhi Building
Abstract:
This talk will address two areas in computer graphics and vision: artistic content creation tools and human pose estimation. First, software tools for creating and manipulating visual content are often difficult to use and demand both artistic talent and technical expertise. However, at the same time, a vast corpus of existing visual content, including Flickr, YouTube, and Google 3D Warehouse, is now available and easily accessible. I will show how I worked towards ameliorating two conflicting constraints that have emerged from the mismatch between the software and the users by addressing: 1) the need to produce high-quality content while maintaining a user interface that is intuitive and easy to learn, even for novice users, and 2) the need for increased automaticity while still allowing the user to have precise and flexible control. Secondly, I will talk about the problem of unconstrained, articulated pose estimation of humans, which includes inferring the positions of joints, such as the neck, elbow, and wrist, in images and videos. Security, intelligence, graphics, and human computer interface are only a few of the applications of this work. I will present a novel data-creation algorithm that can extend existing training sets and allows explicit, on-demand control of the pose and shape variations of generated training samples. Leveraging the data-creation algorithm, I will also present the most recent and best performing algorithm for the task of articulated pose estimation, which I developed using principles of deep learning.
Speaker Profile:
Arjun Jain is a post-doctoral researcher at the Computer Science department at New York University's Courant Institute. He received his Ph.D. in Computer Science from the Max-Planck Institute for Informatics in Germany. Broadly, his research lies at the interface of computer graphics, computer vision, and machine learning, with a focus on human pose estimation and data-driven artistic content creation tools. Arjun has worked as a developer for several companies, including Yahoo! in Bangalore and Weta Digital in New Zealand. He has been especially active in the visual effects industry. Arjun served as a developer for Weta Digitalâs motion capture system. This system has been used in many feature films, and Arjun was credited for his work in Steven Spielbergâs, The Adventures of Tintin. Arjunâs work has resulted in several academic publications, a patent, and has been featured by mainstream media, including in the magazines: New Scientist, Discovery, BCC, Vogue, Wired, India Today, and The Hollywood Reporter, among other outlets.
List of Talks

Webmail

Username:
Password:
Faculty CSE IT
Forgot Password
    [+] Sitemap     Feedback