Charalambos Poullis

Latest — Dec 13, 2024

Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagery

The paper 'Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagery' by Yeshwanth Kumar Adimoolam, Charalambos Poullis, and Melinos Averkiou has been accepted for publication in IEEE/CVF WACV 2025. TL;DR: This work introduces Pix2Poly, an attention-based, end-to-end trainable, and differentiable

More issues

From data to action in flood forecasting leveraging graph neural networks and digital twin visualization

The paper "From data to action in flood forecasting leveraging graph neural networks and digital twin visualization" by Naghmeh Shafiee Roudbari, Shubham Rajeev Punekar, Zachary Patterson, Ursula Eicker, and Charalambos Poullis has been accepted for publication in Scientific Reports. Le Devoir published an article about the work in

HydroVision: LiDAR-Guided Hydrometric Prediction with Vision Transformers and Hybrid Graph Learning

The paper "HydroVision: LiDAR-Guided Hydrometric Prediction with Vision Transformers and Hybrid Graph Learning" by Naghmeh Shafiee Roudbari, Ursula Eicker, Charalambos Poullis, Zachary Patterson has been accepted for publication in 19th International Symposium on Visual Computing (ISVC), 2024. TL:DR: A hybrid graph learning model using LiDAR terrain elevation

Transductive meta‑learning with enhanced feature ensemble for few‑shot semantic segmentation

The paper "Transductive Meta-Learning with Enhanced Feature Ensemble for Few-shot Semantic Segmentation" by Amin Karimi and Charalambos Poullis has been accepted for publication in Scientific Reports. TL;DR: We propose two-pass end-to-end method for few-shot semantic segmentation. The approach leverages an ensemble of visual features learned from pretrained

TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecasting

The paper "TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecasting" by Naghmeh Shafiee Roudbari, Charalambos Poullis, Zachary Patterson, and Ursula Eicker, has been accepted for publication in the International Conference on Machine Learning and Applications (ICMLA), 2023. TL;DR: The hydrometric prediction of

Strategic Incorporation of Synthetic Data for Performance Enhancement in Deep Learning: A Case Study on Object Tracking Tasks

The paper "Strategic Incorporation of Synthetic Data for Performance Enhancement in Deep Learning: A Case Study on Object Tracking Tasks" by Jatin Katyal and Charalambos Poullis has been accepted for publication in the 18th International Symposium on Visual Computing (ISVC), 2023. TL;DR: Obtaining training data for machine

Tracking and Identification of Ice Hockey Players

The paper "Tracking and Identification of Ice Hockey Play" by Qiao Chen and Charalambos Poullis has been accepted for publication in the International Conference on Computer Vision Systems (ICVS), 2023. TL;DR: Due to the rapid movement of players, ice hockey is a high-speed sport that poses significant

Enabling Saccadic Redirection Through Real-time Saccade Prediction

The paper Enabling Saccadic Redirection Through Real-time Saccade Prediction by Yashas Joshi and Charalambos Poullis has been accepted for publication in the Computer Games and Virtual Worlds journal. A provisional patent has been issued for this technology (Licensing contact: Axelys). A short video presentation of the technique is shown below.

Data leakage and Duplication in Benchmark Dataset

In a recent comprehensive analysis, we have uncovered substantial data leakage, duplication, and annotation discrepancies in the popular CrowdAI Mapping Challenge benchmark dataset, which has been extensively utilized for developing semantic segmentation and footprint extraction algorithms of buildings from satellite imagery. This revelation may call into question the validity of

Tractable Large-Scale Deep Reinforcement Learning

The paper Tractable Large-Scale Deep Reinforcement Learning by Nima Sarang and Charalambos Poullis has been accepted for publication in the Computer Vision and Image Understanding journal. The code is publicly available at https://github.com/nsarang/road-extraction-rl. Some results are shown below. TL;DR: We frame the problem of road