We present a method of leveraging known geographical separations to better estimate travel times by car between two points in a city, specifically New York City.
Implemented multiple modifications and techniques for improving the state-of-the-art TPMS system. Proposed and implemented an alternating optimization approach for completing the matrix of relevance scores between paper vectors and author vectors. Still in progress.
Developed a novel end-to-end interface that allows easy authoring of Augmented Reality experiences from natural language input, allowing visualization of any text in Augmented Reality. Patent is under consideration.
Aimed at utilising the emotional information present in images and audios to perform cross modal media retrieval. We propsed a hypothesis, and two methods, implemented them, and performed experiments to verify our claims.
Performed an extensive literature review on the existing methods of Neural Machine Translation using parallel and non-parallel corpora. Implemented the state-of-the-art work using non-parallel corpora on low resource language Catalan and performed analysis of results obtained to explain the possible differences arising on using a low resource language.
Implemented multiple modifications and techniques for improving the state-of-the-art TPMS system. Proposed and implemented an alternating optimization approach for completing the matrix of relevance scores between paper vectors and author vectors.
The project aimed at developing a machine learning model to assign an emotion to any chat message provided as input, in any of the top five languages common in Indian chat scenarios, although in the Latin Script.