Research Output
Publications
Full publication record for Vajira Lasantha Thambawita on Google Scholar — covering medical imaging, cardiac AI, reproductive medicine, sports analytics, and generative AI.
Scholar Metrics
Citation Statistics
Statistics sync weekly via GitHub Actions. Last updated: 2025-03-25. View live on Google Scholar →
Impact Areas
Research Highlights
Large-Scale Datasets
Created and co-created multiple widely-used benchmark datasets for gastrointestinal endoscopy, sperm analysis, and cardiac imaging.
Generative AI for Medicine
Pioneered use of GANs and diffusion models to generate synthetic medical data, addressing data scarcity in healthcare AI.
Cardiac AI
Developed DeepFake ECG technology using GANs to address privacy in cardiac data sharing, with broad impact on medical privacy research.
Reproductive Medicine AI
Advanced AI methods for sperm analysis and fertility prediction, including tracking, morphology assessment, and ICSI procedure automation.
Most Cited
Top Cited Publications
Ordered by citation count, synced weekly from Google Scholar.
-
1
-
2
-
3
-
4
-
5
-
6
-
7
-
8
-
9
-
10
Complete Record
All Publications
96 papers grouped by year. Includes journal articles, conference papers, datasets, and preprints.
2024
5 publications-
Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge
-
Advancing sleep detection by modelling weak label sets: A novel weakly supervised learning approach
-
Advancing Multimedia Retrieval in Medical, Social Media and Content Recommendation Applications with ImageCLEF 2024
-
SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset
-
MediaEval 2023: Multimedia Benchmark Workshop 2023, Working Notes Proceedings of the MediaEval 2023 Workshop Amsterdam, The Netherlands and Online, 1-2 February 2024
2023
14 publications-
VISEM-Tracking, a human spermatozoa tracking dataset
-
GridHTM: Grid-Based Hierarchical Temporal Memory for Anomaly Detection in Videos
-
ScopeSense: An 8.5-month sport, nutrition, and lifestyle lifelogging dataset
-
ImageCLEF 2023 Highlight: Multimedia Retrieval in Medical, Social Media and Content Recommendation Applications
-
Multimedia datasets: challenges and future possibilities
-
Mask-conditioned latent diffusion for generating gastrointestinal polyp images
-
Usefulness of Heat Map Explanations for Deep-Learning-Based Electrocardiogram Analysis
-
RePolyp: A Framework for Generating Realistic Colon Polyps with Corresponding Segmentation Masks using Diffusion Models
-
An objective validation of polyp and instrument segmentation methods in colonoscopy through Medico 2020 polyp segmentation and MedAI 2021 transparency challenges
-
Overview of imageclefmedical 2023–medical visual question answering for gastrointestinal tract
-
Overview of ImageCLEF 2023: Multimedia retrieval in medical, socialmedia and recommender systems applications
-
Cellular, a cell autophagy imaging dataset
-
Working Notes Proceedings of the MediaEval 2022 Workshop
-
An Open-Access Dataset of Hospitalized Cardiac-Arrest Patients: Machine-Learning-Based Predictions Using Clinical Documentation
2022
25 publications-
On evaluation metrics for medical applications of artificial intelligence
-
SinGAN-Seg: Synthetic training data generation for medical image segmentation
-
Meta-learning with implicit gradients in a few-shot setting for medical image segmentation
-
MMSys' 22 Grand Challenge on AI-based Video Production for Soccer
-
# ESHREjc report: on the road to preconception and personalized counselling with machine learning models
-
PolypConnect: Image inpainting for generating realistic gastrointestinal tract images with polyps
-
Segmentation Consistency Training: Out-of-Distribution Generalization for Medical Image Segmentation
-
Grid HTM: Hierarchical Temporal Memory for Anomaly Detection in Videos
-
Synthesizing a talking child avatar to train interviewers working with maltreated children
-
Chapter 4 Smittestopp analytics: Analysis of position data
-
P-108 Real-time deep learning based multi object tracking of spermatozoa in fresh samples
-
P-272 Automatic Tracking of the ICSI procedure using Deep Learning
-
P-243 Automating tracking of cell division for human embryo development in time lapse videos
-
Njord: a fishing trawler dataset
-
Reproducibility Companion Paper: Focusing on Persons: Colorizing Old Images Learning from Modern Historical Movies
-
Automating tracking of cell division for human embryo development in time lapse videos
-
Real-time deep learning based multi object tracking of spermatozoa in fresh samples
-
Automatic Tracking of the ICSI procedure using Deep Learning
-
MLC at HECKTOR 2022: The Effect and Importance of Training Data When Analyzing Cases of Head and Neck Tumors Using Machine Learning
-
Poster Session 1Baseline filtering alleviates generalization issues for neural networks for electrocardiogram analysis
-
Biomedical image analysis competitions: The state of current participation practice
-
Medico multimedia task at mediaeval 2022: Transparent tracking of spermatozoa
-
Automatic Unsupervised Clustering of Videos of the Intracytoplasmic Sperm Injection (ICSI) Procedure
-
On evaluation metrics for medical applications of artificial intelligence.
-
Overview of the ImageCLEF 2022: Multimedia retrieval in medical, social media and nature applications
2021
29 publications-
Kvasir-Capsule, a video capsule endoscopy dataset
-
Htad: A home-tasks activities dataset with wrist-accelerometer and audio features
-
Kvasir-instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy
-
Explaining deep neural networks for knowledge discovery in electrocardiogram analysis
-
The EndoTect 2020 challenge: evaluation and comparison of classification, segmentation and inference time for endoscopy
-
A comprehensive analysis of classification methods in gastrointestinal endoscopy imaging
-
Fr615 impact of image resolution on convolutional neural networks performance in gastrointestinal endoscopy
-
ID: 3523524 Data augmentation using generative adversarial networks for creating realistic artificial colon polyp images: validation study by endoscopists
-
Few-shot segmentation of medical images based on meta-learning with implicit gradients
-
DeepSynthBody: the beginning of the end for data deficiency in medicine
-
Divergentnets: Medical image segmentation by network ensemble
-
Using 3D convolutional neural networks for real-time detection of soccer events
-
A self-learning teacher-student framework for gastrointestinal image classification
-
P–029 Identification of spermatozoa by unsupervised learning from video data
-
Multimodal virtual avatars for investigative interviews with children
-
Pyramidal segmentation of medical images using adversarial training
-
Identification of spermatozoa by unsupervised learning from video data
-
Reproducibility companion paper: Norm-in-norm loss with faster convergence and better performance for image quality assessment
-
Medai: Transparency in medical image segmentation
-
Artificial Intelligence in Medicine: Gastroenterology
-
DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine
-
Impact of image resolution on deep learning performance in endoscopy image classification: An experimental study using a large dataset of endoscopic images
-
Ai-based video clipping of soccer events
-
Automated event detection and classification in soccer: The potential of using multiple modalities
-
Automated clipping of soccer events using machine learning
-
Emotional Mario Task at MediaEval 2021.
-
Medico Multimedia Task at MediaEval 2021: Transparency in Medical Image Segmentation.
-
Cise Midoglu, Evi Zouganeli, Dag Johansen, Michael Alexander Riegler, and Pål Halvorsen. 2021. Automated Event Detection and Classification in Soccer: The Potential of Using Multiple Modalities
-
Impact of image resolution on convolutional neural networks performance in gastrointestinal endoscopy
2020
9 publications-
HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy
-
Pmdata: a sports logging dataset
-
Psykose: A motor activity database of patients with schizophrenia
-
Toadstool: A dataset for training emotional intelligent machines playing Super Mario Bros
-
An extensive study on cross-dataset bias and evaluation metrics interpretation for machine learning applied to gastrointestinal tract abnormality classification
-
ACM multimedia biomedia 2020 grand challenge overview
-
Pyramid-focus-augmentation: medical image segmentation with step-wise focus
-
Real-time detection of events in soccer videos using 3D convolutional neural networks
-
Vid2Pix-A Framework for Generating High-Quality Synthetic Videos
2019
5 publications-
Unsupervised preprocessing to improve generalisation for medical image classification
-
GANEx: A complete pipeline of training, inference and benchmarking GAN experiments
-
Machine learning-based analysis of sperm videos and participant data for male fertility prediction
-
Extracting temporal features into a spatial domain using autoencoders for sperm video analysis
-
Stacked dense optical flows and dropout layers to predict sperm motility and morphology
2018
3 publications-
The medico-task 2018: Disease detection in the gastrointestinal tract using global features and deep learning
-
Using preprocessing as a tool in medical image detection
-
CEUR WORKSHOP PROCEEDINGS
2016
2 publications-
An optimized Parallel Failure-less Aho-Corasick algorithm for DNA sequence matching
-
To use or not to use: CPUs' cache optimization techniques on GPGPUs
2014
1 publication-
To use or not to use: Graphics processing units (GPUs) for pattern matching algorithms
2013
1 publication-
Graphics Processing Units: To Use or Not to Use?
2011
2 publications-
Low Cost Telepresence Robot
-
BUILDING A LOW-COST TELEPRESENCE ROBOT WITH GENERIC HARDWARE