S
Sanchit Gupta
Researcher at Indraprastha Institute of Information Technology
Publications - 5
Citations - 47
Sanchit Gupta is an academic researcher from Indraprastha Institute of Information Technology. The author has contributed to research in topics: Facial recognition system & 3D single-object recognition. The author has an hindex of 4, co-authored 5 publications receiving 29 citations. Previous affiliations of Sanchit Gupta include Microsoft.
Papers
More filters
Journal ArticleDOI
InSight: Monitoring the State of the Driver in Low-Light Using Smartphones
TL;DR: InSight is presented, a windshield-mounted smartphone-based system that can be retrofitted to the vehicle to monitor the state of the driver, specifically driver fatigue ( based on frequent yawning and eye closure) and driver distraction (based on their direction of gaze).
Proceedings ArticleDOI
Cross-spectral cross-resolution video database for face recognition
Maneet Singh,Shruti Nagpal,Nikita Gupta,Sanchit Gupta,Soumyadeep Ghosh,Richa Singh,Mayank Vatsa +6 more
TL;DR: It is asserted that this dataset can help researchers develop robust face recognition algorithms to handle real world surveillance scenarios and is presented to present baseline results with two commercial matchers for two experimental scenarios, where very low performance of both the matchers is observed.
Patent
Systems and methods for monitoring driver state
Akshay Uttama Nambi Srirangam Narashiman,Venkata N. Padmanabhan,Ishit Mehta,Shruthi Bannur,Sanchit Gupta +4 more
TL;DR: In this article, a system and techniques for monitoring driver state are described, which is adapted to receive a set of color images of a person, such as image of a driver of a vehicle with varying levels of illumination in the images.
Proceedings ArticleDOI
FaceSurv: A Benchmark Video Dataset for Face Detection and Recognition Across Spectra and Resolutions
Sanchit Gupta,Nikita Gupta,Soumyadeep Ghosh,Maneet Singh,Shruti Nagpal,Mayank Vatsa,Richa Singh +6 more
TL;DR: The proposed FaceSurv database contains over 142K face images, spread across videos captured in both visible and near-infrared spectra, offering a plethora of challenges common to surveillance settings.
Cross-spectral cross-resolution face recognition in videos
TL;DR: This research presents a video database which can be utilized to benchmark face recognition algorithms addressing crossspectral and cross-resolution matching and proposes an algorithm FaceFinder, which addresses shortcomings of existing face detectors by making use of human body segmentation results of a trained Convolutional Neural Network model specifically designed for semantic segmentation.