Immersive & Creative Technologies Lab
  • Home
  • About
  • People
  • Publications
  • Courses
  • Contact
Sign in Subscribe

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

Charalambos (Charis) Poullis

Sep 5, 2023
Strategic Incorporation of Synthetic Data for Performance Enhancement in Deep Learning: A Case Study on Object Tracking Tasks

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.

Sign up for more like this.

Enter your email
Subscribe
Depth-Aware Scoring and Hierarchical Alignment for Multiple Object Tracking

Depth-Aware Scoring and Hierarchical Alignment for Multiple Object Tracking

The paper 'Depth-Aware Scoring and Hierarchical Alignment for Multiple Object Tracking' by Milad Khanchi, Maria Amer, and Charalambos Poullis has been accepted for publication in IEEE International Conference on Image Processing (ICIP) 2025. TL;DR: DepthMOT is a cutting-edge multiple object tracking framework that enhances object association by
Jun 10, 2025 1 min read
DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation
Featured

DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation

The paper 'DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation' by Amin Karimi and Charalambos Poullis has been accepted for publication in IEEE/CVF Computer Vision and Pattern Recognition (CVPR) 2025. TL;DR: The paper introduces DSV-LFS, a framework that boosts few-shot semantic segmentation
Apr 8, 2025 1 min read
Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagery
Featured

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
Dec 20, 2024 1 min read
Immersive & Creative Technologies Lab © 2025
  • Sign up
Powered by Ghost