publications

2021

1. CODS-COMAD

   Model Agnostic Information Biasing for VQA

   Shah, Nikhil, Singhal, Apoorve, Singh, Chinmay, and Khandelwal, Yash

   In 8th ACM IKDD CODS and 26th COMAD 2021

   Abs

   VQA involves generating information rich features from given images and questions based on them. Here we have explored the use of inducing biases and structuring of multi-modal latent spaces using fusion loss regularization. Our loss based strategy is aimed at making the multi-modal representation of the student branch (Image+Question) to be those like that of the teacher branch (Image+Answer), made with the same model. Our main contribution is that we explore a model agnostic approach based on creation of a homogeneous multimodal latent space for image with question and image with answer’s representation. To our best knowledge this is the only work exploring the use of latent space fusion using regularization for VQA.

2019

1. IVPAI

   Real-time lane detection, fitting and navigation for unstructured environments

   Singhal, Apoorve, Mohta, Vibhakar, Jha, Arvind, Khandelwal, Yash, Agrawal, Deepank, Kowshik, Shreyas, Agarwal, Siddhant, Shrivastava, Shrey, Lodhi, Vaibhav, and Chakravarty, Debashish

   In 2019 International Conference on Image and Video Processing, and Artificial Intelligence 2019

   PDF
2. ICCRT

   A Prototype of an Intelligent Ground Vehicle for Constrained Environment: Design and Development

   Singhal, Apoorve, Mohta, Vibhakar, Khandelwal, Yash, Patnaik, Adarsh, Patel, Manthan, Godbole, Jaydeep, Priya, Shruti, Dey, Sombit, Shrivastava, Shrey, Jhunjhunwala, Anand, Kowshik, Shreyas, Agrawal, Deepank, Agarwal, Siddhant, Jha, Arvind, Singh, Rishabh, Raj, Kousshik, Sahoo, Shubham, Singh, Ashutosh, Mallik, Ritwik, Lodhi, Vaibhav, and Chakravarty, Debashish

   In Proceedings of the 2019 2nd International Conference on Control and Robot Technology 2019

   PDF