About

Himanshu Pahadia is a first-year graduate student at Arizona State University, majoring in Computer Science. He is passionate about the interdisciplinary field of artificial intelligence and his research interests lie at the intersection of machine learning, deep learning, and human-computer interaction. Currently, he is working on developing Deep Learning models that enable 3D object detection from monocular RGB images. Himanshu completed his undergrad from IIIT Delhi, India in Computer Science and Engineering. He also has an interest in developing extended reality solutions, mainly enhanced experiences in the virtual world using AI and computer vision. Himanshu has 4.95 years of relevant experience in the field of AI and computer vision. Currently, Himanshu is working as a Research Assistant at Active Perception Group (Dr. Yezhou Yang), ASU. He is researching Monocular 3D object detection using deep learning and geometry. Prior to this, he worked as a Graduate Teaching Assistant at Arizona State University for CSE 598: Introduction to Deep Learning (Dr. Eduardo Blanco). Himanshu has also worked as a Data Scientist at Hitachi, where he was a member of the AI team in Insights and Analytics COP. He researched and developed solutions in Deep Learning, Computer Vision, and Extended Reality. He won second prize in the nation-wide hackathon - Bengalathon - among 2500 participants. He designed and developed a solution - Smart Roads - aimed to improve road safety, road surveillance, and intelligent analytics for the government. The solution was designed to incorporate all the 5Es of road safety - Engineering, Education, Enforcement, Emergency service, and Evaluation - using computer vision and artificial intelligence. Himanshu was the lead architect for Virtual Experience Platform, which aims to provide an end-to-end solution for immersive training creation, training assignment, and analytics on various parameters during training. He won the HiLife award for outstanding performance in the project. He also worked on ExtractAI - a comprehensive entities extraction tool that extracts entities from documents like forms, receipts, invoices, etc. He designed and developed several modules for the tool, including image pre-processing pipeline, entity-extraction module based on spatial proximity, contextual OCR correction, complex entity extraction, table extraction, and validation. Himanshu's tech stack includes Research Scientist, Deep Learning, Computer Vision, Object detection, Object Detection, AI, ML, Data Scientist, and Senior Software Engineer.