|
 Professor Phalguni Gupta, Indian Institute of Technology Kanpur, India
Challenges in Biometric System Development Personal authentication plays an important role in the society. It requires at least some level of security to assure the identity. Security can be realized through one of the three levels. Possession is the Level 1 security where the user possesses something which is required to be produced at the time of authentication. The second level of security is the knowledge of the user who knows something and it is used for authentication. In case of level 3 security, one makes use of biometrics characteristics for authentication. A biometrics based authentication system is better than the traditional possession or knowledge based system because of several reasons such as impossible to loosing or misplacing biometric characteristics, need of physical presence, uniqueness, hard to spoof. Any biometric trait can be used in the authentication system provided the trait makes the system more reliable, user-friendly and cost effective. Hence, the trait should possess the characteristics like Universality, Uniqueness, Performance, Permanence, Collectability, Acceptability, Measurability and Circumvention. But it can be observed that none of the well known biometrics can provide 100% all the characteristics required in an authentication system. In this talk some biometric systems along with their challenges will be discussed.
Brief Bio Phalguni Gupta did his Ph D from IIT Kharagpur and started his carrier In 1983 by joining in Space Applications Centre (ISRO) Ahmedabad, India as a Scientist. He was involved in the development of software for correcting satellite images of the first Indian Remote Sensing Satellite (IRS-1A). In 1987, he joined the Department of Computer Science and Engineering, Indian Institute of Technology Kanpur, India. Currently he is a Professor in the department. He works in the field of Data Structures, Sequential Algorithms, Parallel algorithms, On-line Algorithms, Image Analysis, Biometrics. He has published about 350 papers in International Journals and Conferences. He has dealt with several sponsored and consultancy projects which are funded by the Government of India. Some of these projects are in the area of Biometrics, System Solver, Grid Computing, Image Processing, Mobile Computing, and Network Flow.
|
|
 Professor Ramesh Jain, University of California, Irvine, USA
Cybernetic Health A person’s health is the result of her genetics, lifestyle, and environment. Cybernetic approach may help people manage lifestyle and environment for many chronic conditions, such as Diabetes. Advances in smart phones, sensors, and wearable technology are now making it possible to analyze and understand an individual’s life style from mostly passively collected objective data streams to build her model and predict important health events in her life. Three major components in building such systems are: building individual model, using diverse observations for estimating individuals current health state, and guiding people through lifestyle and environment for best results. Different types of images and video play key role in observations that are essential in building models and understanding states. Obviously computer vision and image processing techniques are essential building block in developing these systems. We will discuss effectiveness and challenges based on the systems that we are building.
Brief Bio Ramesh Jain is an entrepreneur, researcher, and educator. He is a Donald Bren Professor in Information & Computer Sciences at University of California, Irvine where he is doing research in Event Web and experiential computing. Earlier he served on faculty of Georgia Tech, University of California at San Diego, The university of Michigan, Ann Arbor, Wayne State University, and Indian Institute of Technology, Kharagpur. He is a Fellow of AAAS, ACM, IEEE, AAAI, IAPR, and SPIE. His current research interests are in processing massive number of geo-spatial heterogeneous data streams for building Smart Social System, particularly systems for Future Health of people. He is the recipient of several awards including the ACM SIGMM Technical Achievement Award 2010. Ramesh co-founded several companies, managed them in initial stages, and then turned them over to professional management. These companies include PRAJA, Virage, and ImageWare. Currently he is working with Krumbs, a situation aware computing company. He has also been advisor to several other companies including some of the largest companies in media and search space. Currently he is passionate about the Institute for Future Health at University of California, Irvine.
|
|
 Professor C. V. Jawahar, International Institute of Information Technology Hyderabad, India
Vision and Language In this talk, we discuss some of the recent advances in bridging the gap between vision and language. Recent years have seen active research and impressive results in many problems that overlap with vision, language and learning. This advancement also demonstrate our superior understanding of the visual world, and how human friendly explanation of this understanding is getting generated. Here, we look at how tools and techniques are evolving in this space, and getting used across and within these domains. This development opens up a new class of problems and application domains. Some of these directions are also briefly discussed.
Brief Bio C. V. Jawahar is a professor at IIIT Hyderabad, India. He received his PhD from IIT Kharagpur and has been with IIIT Hyderabad since Dec. 2000. At IIIT Hyderabad, Jawahar leads a group focusing on computer vision, machine learning and multimedia systems. In the recent years, he has been looking into a set of problems that overlap with vision, language and text. He is also interested in large scale multimedia systems with special focus on retrieval. He has more than 50 publications in top tier conferences in computer vision, robotics and document image processing. He has served as a chair for previous editions of ACCV, WACV, IJCAI, ICCV and ICVGIP. Presently, he is an area editor of CVIU and an associate editor of IEEE PAMI. He is also a program co-chair for ICDAR 2017 and ACCV 2018.
|
|
 Professor Prem K. Kalra, Indian Institute of Technology Delhi, India
Reshaping of human figures in images and videos using 3D morphable models In this talk an approach capable of changing shapes of humans in images and monocular video sequences is presented. The basic approach relies on techniques that arise from confluence of computer vision and computer graphics. A 3D morphable model is derived or statistically learnt from an example set of 3D models. 3D morphable models have shown impressive results for synthesis of 3D human faces and analysis of facial expressions. In the context of reshaping of a human figure in an image, a 3D whole-body morphable model is used for guiding the changes in a single image, which are obtained through image warping. The reshaping is parameterized such that increasing or decreasing height or weight of human figures can result in the semantically corresponding changes in the model maintaining a global consistency. The approach needs to preserve the background without distortions, which can be obtained by separating the human figure from the background. Reshaping of human figures in videos maintaining spatio-temporal consistency is also discussed. Spatio-temporal consistency is achieved through the combination of automatic pose fitting and body-aware frame warping. Motion retargeting makes the approach produce semantically more consistent results like, the motion of a taller human should have bigger step size. The talk is based on the collection of recent research from the literature and some related work done at the vision-graphics group in the department of computer science and engineering at IIT Delhi.
Brief Bio Prem K Kalra is a professor in Department of Computer Science and Engineering at Indian Institute of Technology Delhi. He joined IIT Delhi in Dec 1997. Earlier to that he worked at University of Geneva, Switzerland (1994-1997). He has also been a Visiting Faculty to Dayalbagh Educational Institute, Agra, University of Geneva, Swiss Federal Institute of Technology Lausanne (EPFL), Switzerland, Max-Planck Institute, Germany, and University of Texas Austin, USA. He did his PhD in Computer Science from Swiss Federal Institute of Technology Lausanne (EPFL), Switzerland in 1993, MS (Computer Science) from University of New Brunswick, Canada in 1988, MTech (Industrial Engg) from IIT Delhi in 1985 and BSc Engineering (Mechanical Engg) from Dayalbagh Educational Institute, Agra in 1983. His research interests are in Computer Graphics and Animation, Visual Computing, Multimedia Processing, Computer Vision based Intelligent Systems. He has published over 80 papers in reputed international journals and conferences. He is in the editorial board of the international journal, The Visual Computer, and has been a member of many program committees of international conferences, e.g., ICCV, CVPR, CGI, Eurographics Worskshops, ICVGIP. He is a member of ACM, Computer Graphics Society and Systems Society of India.
|
|
 Professor Mohan S Kankanhalli, National University of Singapore, Singapore
Perception of Visual Sentiment: From Experimental Psychology to Computational Modeling A picture is worth a thousand words. Visual representation is one of the dominant forms of social media. The emotions that viewers feel when observing a visual content is often referred to as the content's visual sentiment. Analysis of visual sentiment has become increasingly important due to the huge volume of online visual data generated by users of social media. Automatic assessment of visual sentiment has many applications, such as monitoring the mood of the population in social media platforms (e.g., Twitter, Facebook), facilitating advertising, and understanding user behavior. However, in contrast to the extensive research on predicting textual sentiment, relatively less work has been done on sentiment analysis of visual content. In contrast to textual sentiment, visual sentiment is more subjective and implicit. There exists significant semantic gap between high-level visual perception and low-level computational attributes.
In this talk, we argue that these challenges can be addressed by combining the findings from the psychology and cognitive science domain. We will show that a deeper understanding of human perception helps create better computational models. To support that thesis, we will first briefly overview our human-centric research framework, which focuses on applying the paradigms and methodologies from experimental psychology to computer science: First, we collect visual data with human perception through online or lab-controlled psychophysics studies. Then we use inferential statistics to analyze the psychophysics data and model human perception empirically. We then design computational models based on the empirical findings.
We will present four research projects on visual sentiment in our lab, guided by this research framework. In our first project, we aim to understand human visual perception in a holistic way. We first fuse various partially overlapping datasets with human emotion. We build an empirical model of human visual perception, which suggests that six different types of visual perception (i.e., familiarity, aesthetics, dynamics, oddness, naturalness, spaciousness) significantly contribute to human's positive sentiment (i.e., liking) of a visual scene.
In our second project, we investigate the relation between human attention and visual sentiment. We build a unique emotional eye fixation dataset with object and scene-level human annotations, and exploit comprehensively how human attention is affected by emotional properties of images. Further, we train a deep convolutional neural network for human attention prediction on our dataset. Results demonstrate that efficient encoding of image sentiment information helps boost its performance.
Our third project explores how human attention influences visual sentiment. We experimentally disentangle effects of focal information and contextual information on human emotional reactions, then we incorporate related insights into computational models. On two benchmark datasets, the proposed computational models demonstrate superior performance compared to the state-of-the-art methods on visual sentiment prediction.
In the fourth project, we focus on our current work on video sentiment and explore the contribution of dynamics in sentiment perception. We will end with future research direction on visual sentiment analysis. Our studies highlight the importance of understanding human cognition for interpreting the latent sentiments behind visual scenes.
Brief Bio Mohan Kankanhalli is Provost's Chair Professor of Computer Science at the National University of Singapore (NUS). He is also the Dean of NUS School of Computing. Before becoming the Dean in July 2016, he was the NUS Vice Provost (Graduate Education) during 2014-2016 and Associate Provost during 2011-2013. Mohan obtained his BTech from IIT Kharagpur and MS & PhD from the Rensselaer Polytechnic Institute.
His current research interests are in Multimedia Computing, Information Security & Privacy, Image/Video Processing and Social Media Analysis. He directs the SeSaMe (Sensor-enhanced Social Media) Centre which does fundamental exploration of social cyber-physical systems which has applications in social sensing, sensor analytics and smart systems. He is on the editorial boards of several journals including the ACM Transactions on Multimedia, Springer Multimedia Systems Journal, Pattern Recognition Journal and Springer Multimedia Tools & Applications Journal. He is a Fellow of IEEE.
|
