Evaluating deep tracking models for player tracking in broadcast ice hockey video

no code implementations • 22 May 2022 • Kanav Vats, Mehrnaz Fani, David A. Clausi, John S. Zelek

Tracking and identifying players is an important problem in computer vision based ice hockey analytics.

Causal Discovery from Sparse Time-Series Data Using Echo State Network

no code implementations • 9 Jan 2022 • Haonan Chen, Bo Yuan Chang, Mohamed A. Naiel, Georges Younes, Steven Wardell, Stan Kleinikkink, John S. Zelek

Causal discovery between collections of time-series data can help diagnose causes of symptoms and hopefully prevent faults before they occur.

Causal Discovery regression +2

Ice hockey player identification via transformers and weakly supervised learning

no code implementations • 22 Nov 2021 • Kanav Vats, William McNally, Pascale Walters, David A. Clausi, John S. Zelek

Obtaining player identities is essential for analyzing the game and is used in downstream tasks such as game event recognition.

Optical Character Recognition Optical Character Recognition (OCR) +3

PixelBNN: Augmenting the PixelCNN with batch normalization and the presentation of a fast architecture for retinal vessel segmentation

no code implementations • 19 Dec 2017 • Henry A. Leopold, Jeff Orchard, John S. Zelek, Vasudevan Lakshminarayanan

Analysis of retinal fundus images is essential for eye-care physicians in the diagnosis, care and treatment of patients.

Image Registration Retinal Vessel Segmentation +1

Statistical Textural Distinctiveness for Salient Region Detection in Natural Images

no code implementations • CVPR 2013 • Christian Scharfenberger, Alexander Wong, Khalil Fergani, John S. Zelek, David A. Clausi

A novel statistical textural distinctiveness approach for robustly detecting salient regions in natural images is proposed.

Saliency Detection