Research Experience

  • CVIT, IIIT-Hyderabad
    • Research Fellow (August’19 – January’20); Guide: Prof. C.V. Jawahar
    • Accomplished an improved word accuracy by 1.4% for Hindi and 1.8% for Telugu by merging text hypotheses and deep embeddings.
    • Proposed techniques like Naive Merge, Query Expansion for improving word retrieval by 11.12% for the Hindi language.
    • Created an OCR for Hindi, Tamil and Telugu. Worked on a semi-supervised training technique for Convolutional Recurrent Neural Network (using CTC loss). Reported an improved word accuracy by 2.5% and character accuracy by 5%.
  • IIT Gandhinagar
    • Project page
    • Research Intern (March’19 – August’19); Guide: Shanmuganathan Raman
    • Worked on the project titled "Cultural Heritage Preservation and Restoration using Digital 3D Models", under Prof. Shanmuganathan Raman. The project was supported by NVIDIA and IMPRINT (Impacting Research Innovation and Technology) an initiative of the Government of India.
    • Major contributions:
      • Data collection in form of point clouds using Faro Focus 3D laser scanner.
      • Point Cloud Alignment using ICP.
      • Developed an algorithm for Point Cloud Completion using Fully-Connected Auto-Encoder.
  • Meditab Software Inc.
    • Project page / Paper
    • Artificial Intelligence Intern (September’18 – March’19)
    • Successful in generating optimal facility layouts, by implementing ELOPE (Evolutionary Layout Optimization and Evaluator) and using it with the Genetic Algorithm, this led to a decrease in travelling time by 75% for the DosePacker robots leading to more efficient DosePacker system.
    • Created an automatic log file analyzer capable of predicting a possible machine breakdown, leading to a 70% decrease in maintenance time of the DosePacker system and saving on maintenance costs.
  • Bennett University
    • Project page / Video(YouTube)
    • Artificial Intelligence Research Intern (June’18 – July’18); Guide: Dr. Gaurav Singal
    • Collected dataset of footprints from 180 volunteers, using a paper scanner at 600dpi.
    • Developed a deep learning algorithm for classifying humans based on the shape and size of their footprints. The network was trained on the data collected earlier.
  • Bioscan Research
    • Data Analyst Intern (June’18 – July’18)
    • Worked on analysing data from an onsite detection tool for instantaneous scanning of intracranial bleeding.
    • Developed a software capable of tracking patients using Python and SQLite, leading to better workflow for the people working on collecting the brain scans.
    • Successful in extracting data from the noisy signal (coming from a brain scan using a near-infrared laser scanner), by implementing an signal extractor using Python.

Education

(April ’23 - Present)

University of Bristol, United Kingdom

PhD in Computer Science

Advisor: Prof. Dima Damen

 

(January ’20 - March ’23)

International Institute of Information Technology, Hyderabad (IIIT-H), India

Master of Science (MS) by Research in Computer Science (CGPA: 9.2/10.0)

Thesis Title: I-Do, You-Learn: Techniques for Unsupervised Procedure Learning using Egocentric Videos

Advisors: Prof. C.V. Jawahar and Prof. Chetan Arora

 

(June ’15 – July ’19)

Vishwakarma Government Engineering College, Ahmedabad, India

Bachelor of Engineering (BE) (CPI: 8.01/10.0)

Automatic Garbage Detection and Collection (paper): One of the top 4% projects selected by the Government of India under the Student Startup and Innovation Policy (SSIP) for full-funding.