BEGIN:VCALENDAR VERSION:2.0 PRODID:-//wp-events-plugin.com//7.2.3.1//EN TZID:America/New_York X-WR-TIMEZONE:America/New_York BEGIN:VEVENT UID:0-8239@eng.ufl.edu DTSTART;TZID=America/New_York:20260312T130000 DTEND;TZID=America/New_York:20260312T140000 DTSTAMP:20260219T204726Z URL:https://www.eng.ufl.edu/news-events/events/ece-seminar-series/ SUMMARY:ECE Seminar Series DESCRIPTION:Title: Texture-Aware Representation Learning for Remote Sensing Image Classification and 3D Scene Reconstruction \n\nAbstract: Texture cu es play a central role in visual understanding\, yet modern deep learning models often struggle to preserve both fine-scale and global structural in formation across diverse tasks. This talk presents recent advances in text ure-aware representation learning that improve visual understanding across remote sensing image classification and 3D scene reconstruction. First\, we introduce Neighborhood Feature Pooling (NFP)\, a lightweight architectu ral layer that enhances texture modeling by explicitly capturing local rel ational structure within feature representations. Easily integrated into e xisting deep networks\, NFP improves remote sensing image classification b y emphasizing subtle spatial patterns as well as improving class compactne ss and separability. Second\, we present a wavelet-enhanced 3D Gaussian Sp latting framework that addresses the challenge of reconstructing high-freq uency detail under sparse or challenging imaging conditions. By incorporat ing Discrete Wavelet Transform–based supervision\, the approach encourag es representations that better preserve edges and structural geometry duri ng reconstruction. Together\, these works demonstrate how texture-aware le arning principles can bridge recognition and reconstruction tasks\, pointi ng toward richer texture-driven representations for remote sensing and bey ond. \n\nBio: Dr. Joshua Peeples is an Assistant Professor in the Departm ent of Electrical and Computer Engineering at Texas A&\;M University. D r. Peeples received his Bachelor of Science degree in electrical engineeri ng with a minor in mathematics from the University of Alabama at Birmingha m. He earned his Ph.D. in the Department of Electrical and Computer Engine ering at the University of Florida. Dr. Peeples has developed and refined novel deep learning methods for texture characterization\, segmentation\, and classification of images. His current research seeks to extend this wo rk and explore new aspects such as developing algorithms for explainable a rtificial intelligence and various real-world applications in several doma ins. These methods can then be applied toward automated image understandin g\, object detection\, and classification. Dr. Peeples has been recognized with several awards and positions\, including the National Science Founda tion Graduate Research Fellowship\, United States Air Force Summer Faculty Fellowship\, Massachusetts Institute of Technology Lincoln Laboratory Sum mer Visiting Scientist\, and Joint Appointee at Los Alamos National Labora tory as a Guest Scientist in the Space Remote Sensing and Data Science gro up. He also serves as the Coordinator for the undergraduate machine learni ng course in the TAMU ECE Department and is an inaugural TAMU Honors Acade my Honors Aggie Core Values Faculty Fellow. In addition to research and te aching\, Dr. Peeples is dedicated to service and advocacy for students at the university and in the community. \n\n CATEGORIES:Seminars LOCATION:MALA 7200\, 1889 Museum Rd.\; 5000 Malachowsky Hall\; PO Box 11620 0 \, Gainesville \, FL\, 32611-6200\, United States X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=1889 Museum Rd. 5000 Malach owsky Hall PO Box 116200 \, Gainesville \, FL\, 32611-6200\, United States ;X-APPLE-RADIUS=100;X-TITLE=MALA 7200:geo:0,0 END:VEVENT BEGIN:VTIMEZONE TZID:America/New_York X-LIC-LOCATION:America/New_York BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 TZNAME:EDT END:DAYLIGHT END:VTIMEZONE END:VCALENDAR