Gihan Chanaka Jayatilaka


I am a third year Computer Science PhD student at the University of Maryalnd, College Park, USA. I am interested in Computer Vision (specifically, learning from unlabelled/sparsely-labelled data). Before graduate school, I completed a BS in Computer Engineering from the University of Peradeniya, Sri Lanka in 2020 and spent an year as a graduate research assistant in the Department of Electrical and Electronics Engineering, University of Peradeniya. I have also worked as a research intern at Singapore Management University in 2019 and Futurewei Technologies, USA in 2022 Summer.
News
  • [2025-02-25]: Our paper titled 'Unified Spatio-Temporal Tri-Perspective View Representation for 3D Semantic Occupancy Prediction' won the Best Paper Award at the Machine Learning for Autonomous Driving (ML4AD) Workshop, The 39th Annual AAAI Conference on Artificial Intelligence (AAAI) 2025
  • [2024-10-20]: Our manuscript titled 'Utilization of Neighbor Information for Generalized Category Discovery and Image Clustering'
  • [2022-08-26]: Completed my summer research internship at Futurewei Technologies, CA.
  • [2021-08-15]: Our paper titled 'Holistic Interpretation of Public Scenes Using Computer Vision and Temporal Graphs to Identify Social Distancing Violations' is accepted for MDPI Applied Sciences journal.
  • [2022-05-23]: I started my summer research internship at Futurewei Technologies, California, USA.
  • [2021-10-18]: Our paper titled "Hands Off: A Handshake Interaction Detection and Localization Model for COVID-19 Threat Control" is accepted for ICIIS 2021.
  • [2021-09-13]: Our book titled "A Handbook for Online Proctored Examinations" is public.
  • [2021-08-30]: I joined the University of Maryland as a Computer Science PhD student. (2021 fall)
  • [2021-08-21]: Our preprint titled 'A generalized forecasting solution to enable future insights of COVID-19 at sub-national level resolutions' is public.
  • [2021-05-21]: Our paper and codebase titled 'DeepLight: Robust & Unobtrusive Real-time Screen-Camera Communication for Real-World Displays' won the best artifact award (for reproducible code/data/results) at IPSN 2021.
  • [2021-05-20]: Our paper titled 'An optical physics inspired CNN approach for intrinsic image decomposition' accepted for ICIP 2021.
  • [2021-01-19]: Our paper titled 'DeepLight: Robust & Unobtrusive Real-time Screen-Camera Communication for Real-World Displays' accepted for IPSN 2021.
  • Older news
My Profiles: Facebook, Github, Scholar.

Institutional pages: University of Maryland, University of Peradeniya

Profiles that I don't use much: Twitter, Youtube, Linkedin, Hackerrank, Researchgate.



Quick links: OneNote

Current involvements: