About

I am a PhD candidate at the Stony Brook University, working with Prof. Michael S. Ryoo and Prof. Dimitris Samaras. I am interested in computer vision, particularly in the video domain, and work on improving parameter/compute efficiency, inference speed and label efficiency. Currently, I explore video representations with minimal supervision and token-based models in vision.

Prior to this, I worked as a Research Assistant at University of Moratuwa, Sri Lanka, under the supervision of Dr. Ranga Rodrigo. I received my BS specializing in Electronic & Telecommunication Engineering from University of Moratuwa.

Recent News

[Mar 2022] Our paper "MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection" was accepted at CVPR 2022.
[Feb 2022] I joined Robotics at Google as a Student Researcher.
[Dec 2021] I was a finalist (1/30) for the Adobe Research Fellowship 2022. Congratulations to all the winners!
[Dec 2021] Our paper "Swift: Adaptive Video Streaming with Layered Neural Codecs" was accepted at NSDI 2022.
[Nov 2021] Our recent papers "SWAT: Spatial Structure Within and Among Tokens" and "MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection" are now on arxiv.
[Sep 2021] I am officially a PhD candidate now!
[Aug 2021] I interned at Wormpex AI Research in Summer 2021, working on video representations with minimal supervision. Our paper "Self-supervised Pretraining with Classification Labels for Temporal Activity Detection" is now on arxiv.
[Mar 2021] Our paper "Coarse-Fine Networks for Temporal Activity Detection in Videos" was accepted at CVPR 2021.
[Aug 2020] Our paper "Exploiting the Redundancy in Convolutional Filters for Parameter Reduction" was accepted at WACV 2021.
[Jun 2020] Our paper"Feature-dependent Cross-Connections in Multi-Path Neural Networks" was accepted at ICPR 2020.
[May 2020] Our paper "On the Exact Outage Probability of 2x2 MIMO-MRC in Correlated Rician Fading" was presented at WCNC 2020.

Preprints

SWAT: Spatial Structure Within and Among Tokens
Kumara Kahatapitiya, Michael S. Ryoo
Self-supervised Pretraining with Classification Labels for Temporal Activity Detection
Kumara Kahatapitiya, Zhou Ren, Haoxiang Li, Zhenyu Wu, Michael S. Ryoo
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning
Jinghuan Shang, Kumara Kahatapitiya, Xiang Li, Michael S. Ryoo

Publications

MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
Rui Dai, Srijan Das, Kumara Kahatapitiya, Michael S. Ryoo, Francois Bremond
CVPR 2022
Swift: Adaptive Video Streaming with Layered Neural Codecs
Mallesham Dasari, Kumara Kahatapitiya, Samir Das, Aruna Balasubramanian, Dimitris Samaras
NSDI 2022
Coarse-Fine Networks for Temporal Activity Detection in Videos
Kumara Kahatapitiya, Michael S. Ryoo
CVPR 2021
Exploiting the Redundancy in Convolutional Filters for Parameter Reduction
Kumara Kahatapitiya, Ranga Rodrigo
WACV 2021
Feature-dependent Cross-Connections in Multi-Path Neural Networks
Dumindu Tissera, Kasun Vithanage, Rukshan Wijesinghe, Kumara Kahatapitiya, Subha Fernando, Ranga Rodrigo
ICPR 2020
On the Exact Outage Probability of 2x2 MIMO-MRC in Correlated Rician Fading
Prathapasinghe Dharmawansa, Kumara Kahatapitiya, Saman Atapattu, Chintha Tellambura
WCNC 2020
Context-Aware Automatic Occlusion Removal
Kumara Kahatapitiya, Dumindu Tissera, Ranga Rodrigo
ICIP 2019
Low-power Step Counting Paired with Electromagnetic Energy Harvesting for Wearables
Kumara Kahatapitiya, Chamod Weerasinghe, Jinal Jayawardhana, Hiranya Kuruppu, Kanchana Thilakarathna, Dileeka Dias
ISWC 2018

Open-source Projects

X3D-Multigrid [source]
A PyTorch implementation for "X3D: Expanding Architectures for Efficient Video Recognition models" [CVPR2020] with "A Multigrid Method for Efficiently Training Video Models" [CVPR2020]. In contrast to the original repository by FAIR, this repository provides a simpler, less modular and more familiar structure of implementation for faster and easier adoptation.
Optimal Transport in NumPy [source]
This repository contrains a few Optimal Transport Algorithms implemented using NumPy, including "A Direct O(1/epsilon) Iteration Parallel Algorithm for Optimal Transport" [NeurIPS2019], "Computational Optimal Transport: Complexity by Accelerated Gradient Descent is better than by Sinkhorn's Algorithm" [PMLR2018] and "Lightspeed Computation of Optimal Transport" [NeurIPS2013].

Teaching

CSE327: Computer Vision - TA (Spring 2020)
CSE215: Foundations of Computer Science - TA (Fall 2019)

Website template from Justin Johnson. Thanks!