In this talk, we will first quickly review the impact of Deep Learning on Computer Vision, with baseline architectures on Object Recognition, Detection and Segmentation. Next, we will introduce applications that motivate human centered vision tasks such as Face recognition, Facial expression recognition, Facial Landmarks, Head pose, Body Joint location estimation, Action and Gesture recognition. Applications include Skill Assessment and Feedback, Human Agent Interaction, Surveillance and Sign Language Recognition and Synthesis.

Dr. Dinesh Babu Jayagopi is an Assistant Professor at IIIT Bangalore since Dec 2013, where he heads the Multimodal Perception Lab. His research interests are in Audio-Visual Signal Processing, Machine Learning, and Social Computing. He obtained his doctorate from Ecole Polytechnic Federale Lausanne (EPFL), Switzerland, beginning of 2011, Masters from Indian Institute of Science (2003) and Btech from MIT (2001), Anna University. He has worked as a Senior Research Engineer at Mercedes Benz India for 3 years. He received the Outstanding paper award in the International Conference on Multimodal Interaction (ICMI), 2012, Idiap Best PhD student research award for the year 2009. More recently, his PhD student's work was nominated for Best student paper in ICMI 2016 Tokyo, Japan and another work received Best student paper award at MedPRAI 2018. He also received Department of Science and Technology (DST) Young Scientist Start up Grant in 2016. In the past, he has successfully collaborated and executed sponsored research projects with CAIR, DRDO (Defence Research and Development Organization) and NI Systems.

In this talk, I will first give a brief introduction about the power of artificial intelligence, in particular, the role of computer vision in modern day human life. Later on, I will focus on the challenges in computer vision and an overview of the traditional approaches to it. Followed to it, I will speak about the NN fundamentals and in particular about the Convolutional Neural Networks. In the final slides of my talk, I will focus on brief details about image classification, object detection, and semantic segmentation methodologies.

Dr. Dhiraj Sangwan is currently employed as Scientist at CSIR-Central Electronics Engineering Research Institute (CEERI), a premier institute of Govt. of India working in the field of Electronics Engineering Research since 1953. He is a member of Cognitive Computing Group under Cyber-Physical Systems Area. He is involved in various projects related to different applications of Computer Vision and Machine Learning in the capacity of both Project Leader and Team Member. Prior, to joining CSIR-CEERI, he was working as Assitant Professor in Electronics & Communications Engg. Deptt of a premier Deemed University for Girls in Rajasthan. He is actively involved in the area of academics and research for the past 14 years. His research interests are in Machine Learning, Computer Vision, Artificial Intelligence, Human-Computer Interaction, High-Speed reconfigurable systems, Evolutionary Algorithms. etc. He has completed his Ph.D. in the field of "Evolutionary Algorithms for VLSI Applications". He is also serving as Assistant Professor in Academy of Science and Innovative Research (AcSIR) where he teaches Advanced Image Processing to Post Graduate Students. He has published numerous research articles in prestigious journals and Conferences. He is also a member of various Professional bodies and Societies such as IETE, ISTE, IACSIT, IAENG, IE.