Our paper TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecasting has been published as a conference paper at the International Conference on Machine Learning and Applications (ICMLA), 2023. The work is co-authored by Naghmeh Shafiee Roudbari, Charalambos Poullis, Zachary Patterson, and Ursula Eicker.
Our paper Strategic Incorporation of Synthetic Data for Performance Enhancement in Deep Learning: A Case Study on Object Tracking Tasks has been published as a conference paper at the 18th International Symposium on Visual Computing (ISVC), 2023. The work is co-authored by Jatin Katyal and Charalambos Poullis.
Our paper Enabling saccadic redirection through real-time saccade prediction has been published as a journal paper in Computer Animation and Virtual World 2023. The work is co-authored by Yashas Joshi and Charalambos Poullis. Link to the paper: https://onlinelibrary.wiley.com/doi/10.1002/cav.2167 Gameplay: Here's a video
Congratulations to Bodhiswatta Chatterjee for being awarded the FRQNT Doctoral Research Scholarship! The FRQNT Doctoral Research Scholarship is a highly competitive and prestigious award, reflecting the excellent quality of his research and academic potential. As a graduate from the Immersive and Creative Technologies Lab, Bodhi has already demonstrated strong skills
Our paper Tractable Large-Scale Deep Reinforcement Learning has been accepted for publication as a journal paper by Computer Vision and Image Understanding. The work is co-authored by Nima Sarang and Charalambos Poullis. A preprint is available at https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4121080 Abstract: Reinforcement learning
Our paper Analysis of Error Rate in Hierarchical Menu Selection in Immersive Augmented Reality has been accepted for publication at SPIE AR|VR|MR, 2023. The work is co-authored by Majid Pourmemar and Charalambos Poullis. Abstract: The emergence of new immersive AR/VR headsets recently resulted in major improvements in
Our paper Motion Estimation for Large Displacements and Deformations has been accepted for publication as a journal paper by Scientific Reports. The work is co-authored by Qiao Chen and Charalambos Poullis. The camera-ready paper is now available: https://www.nature.com/articles/s41598-022-21987-7 Abstract: Large displacement optical flow is an
Our paper "End-to-End Multi-View Structure-from-Motion with Hypercorrelation Volumes" has been accepted as a conference paper at the IEEE International Conference on Signal Processing, Sensors, and Intelligent Systems (SPSIS), 2022. The paper is co-authored by Qiao Chen, and Charalambos Poullis. Abstract: Image-based 3D reconstruction is one of the most important tasks
Our paper "Simpler is better: Multilevel Abstraction with Graph Convolutional Recurrent Neural Network Cells for Traffic Prediction" has been accepted as a conference paper at the IEEE Computational Intelligence In Vehicles And Transportation Systems (CIVTS), 2022. The paper is co-authored by Naghmeh Shafiee Roudbari, Zachary Patterson, Ursula Eicker, and Charalambos
Our work on "Unsupervised Structure-Consistent Image-to-Image Translation " has been accepted as a conference paper at the 17th International Symposium on Visual Computing (ISVC), 2022. The paper is co-authored by Shima Shahfar and Charalambos Poullis. Abstract: The Swapping Autoencoder achieved state-of-the-art performance in deep image manipulation and image-to-image translation. We improve
The paper titled Predicting Human Performance in Vertical Hierarchical Menu Selection in Immersive AR Using Hand-gesture and Head-gaze authored by Majid Pourmemar, Yashas Joshi and Charalambos Poullis will be presented at the 15th Conference on Human System Interaction, 2022. Abstract: There are currently limited guidelines on designing user interfaces (UI)
Our work on "Adaptive Memory Management for Video Object Segmentation" has been accepted as a conference paper at 19th Conference on Robots and Vision (CRV), 2022. The paper is co-authored by Ali Pourganjalikhan, Charalambos Poullis. Abstract: Matching-based networks have achieved state-of-the-art performance for video object segmentation (VOS) tasks by storing
A US Patent was issued for the technology presented in the IEEE Access journal and the ACM SIGGRAPH poster on redirected walking by Yashas Joshi and Charalambos Poullis. Abstract Navigation of a virtual environment (VE) can mean navigating a VE that is spatially larger than the available Physical Tracked Space