- This event has passed.
CDS Seminar – 5 Aug (Mon): Human Sensing: the Past, Present and the Future by Dr. Arjun Jain
Mon, 05 Aug 19 @ 11:00 AM -- 12:00 PM
This talk will focus on deep learning based algorithms for the problem of unconstrained, articulated pose estimation of humans, which constitutes inferring the positions of joints, such as neck, elbow, wrist etc, from still images and videos. Surveillance, graphics, and human computer interface are some of the applications of this body of work. I will present an overview of my prior work focused towards this problem in the last decade. This will include the algorithms used in the pre-deep learning era, followed by deep learning based algorithms that can exploit richer geometric and structural constraints and relationships between body joint locations for close to human performance in-the-wild settings. Exploring and exploiting the aforementioned pose semantics has formed the major body of my work on human pose estimation. Finally, I will talk about my current research direction in which I am working towards semi-supervised and unsupervised learning to tackle large dataset challenge of deep-learning based methods.
Arjun Jain is the co-founder and CEO of Perceptive Code LLC, a silicon valley startup that builds intelligence into automobiles. At the same time, he was also an Adjunct Assistant Professor at IIT Bombay, where he taught Computer Vision from 2016-2019. Before that he was a post-doctoral researcher at the Computer Science department at New York University’s Courant Institute where he worked with Turing award winner Yann LeCun. 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 for several companies, including Yahoo! in Bangalore, Weta Digital in New Zealand and Apple in Cupertino. He has been especially active in the human sensing related industries. Arjun served as a developer for Weta Digital’s motion capture system. This system has been used in many feature films, and Arjun was credited for his work in Steven Spielberg’s, The Adventures of Tintin (2011). Arjun’s work has resulted in several academic publications, patents, 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.