I am a PhD student at School of Computing, National University of Singapore, working with Mohan Kankanhalli in Multimedia Analysis and Synthesis Lab. I am also a part of SeSaMe research center. My PhD dissertation is focused on enhancing photography experience of users utilizing social media and camera sensors. It is centered around computational media aesthetics and analysis of social media images for photography. My research interests lie in the intersection of Machine Learning, Big Data, Social Computing, Image and Video Processing, and Multimedia Computing. Media Analysis. Before joining NUS in summer 2012, I was working at Mentor Graphics, India, (2009-2012) with Praveen Shukla where I worked in the Veloce Emulation team. I obtained my BTech degree in Computer Science and Engineering from Indian Institute of Technology, IIT-BHU, Varanasi in 2009. I am a Table Tennis enthusiast and have won many medals in this sport. Apart from this, I like painting and drawing sketches.

[Link to CV]

Education and Professional Career

Recent Publications

Last updated 2016-09-13 (06:42pm)

Full publication list

Projects

Last updated 2016-09-13 (06:42pm)

ConTagNet: Exploiting user context for tag prediction.

In recent years, deep convolutional neural networks have shown great success in single-label image classification. However, images usually have multiple labels associated with them which may correspond to different objects or actions present in the image. In addition, a user assigns tags to a photo not merely based on the visual content but also the context in which the photo has been captured. Inspired by this, we propose a deep neural network which can predict multiple tags for an image based on the content as well as the context in which the image is captured. The proposed model can be trained end-to-end and solves a multi-label classification problem.

Control System

Publication

More details

Socialized group photography

Visual balance is considered as one of the important factors in defining the aesthetic quality of visual arts. In this work, we propose a novel method to obtain visual balance in a layout with dynamic visual elements. We use the idea of spring-electric graph model and augment it with the concept of color energy from the literature of visual arts. We also present an interesting application of the proposed model in photography assistance. We mainly focus on group photography and utilize social media images along with proposed spring-electric model for providing a recommendation to the user. The proposed method can provide real-time feedback to the user regarding the arrangement of people, their position and relative size on the image frame.



Control System

Publication

More details

ClickSmart: Viewpoint recommendation for photography


In this work we developed ClickSmart, a viewpoint recommendation system which can assist a user in capturing high quality photographs at well known tourist locations. ClickSmart can provide real-time viewpoint recommendation based on the preview on user’s camera, current time and user’s geo-location. It makes use of publicly available geo-tagged images along with associated meta data for learning a recommendation model. We define view-cells, macro blocks in geo-space, and propose the concepts of popularity, quality and uniqueness of view-cells from the viewpoint perspective. Viewpoint recommendation is generated at the granularity of a view-cell and is based on its popularity, quality and uniqueness, which are estimated using social media cues associated with images.

Control System

Publications

More details

Utilizing social media and camera sensors for photography assistance


In this work we developed a photography model based on machine learning which can assist a user in capturing high quality photographs. As scene composition and camera parameters play a vital role in aesthetics of a captured image, the proposed method addresses the problem of learning photographic composition and camera parameters. Further, we observe that context is an important factor from a photography perspective, we therefore augment the learning with associated contextual information. The proposed method utilizes publicly available photographs along with social media cues and associated meta information in photography learning.

Control System

Publications

More details

Academic Services

Last updated 2016-09-11

Teaching Assistant

Reviewer