TA5b.4

Multi-Modal Transformer Networks for Classroom Instruction Analysis

Matthew Korban, Peter Youngs, Scott Acton, University of Virginia, United States
Session:
TA5b: Visual Content Analysis and Applications Lecture
Track:
Speech, Image and Video Processing
Location:
Toyon
Presentation Time:
Tue, 28 Oct, 11:30 - 11:55 PT (UTC -7)
Presentation
Discussion
Resources
No resources available.
Session TA5b
TA5b.1: Seeing Heat with Color - RGB-Only Wildfire Temperature Inference from SAM-Guided Multimodal Distillation using Radiometric Ground Truth
Michael Marinaccio, Fatemeh Afghah, Clemson University, United States
TA5b.2: Universal Adversarial Perturbations for Two-Stage Black-Box Object Detectors
Peng Wu, Northeastern University, United States; Amidu Kamara, U.S. Department of Homeland Security, United States; Mohsen Imani, University of California, Irvine, United States; Nathaniel D. Bastian, Mahdi Imani, United States Military Academy, United States
TA5b.3: Detecting Duplicate Videos Via Perceptual Hashing
Nicholas Chenevey, Jane Zhang, California Polytechnic State U, United States
TA5b.4: Multi-Modal Transformer Networks for Classroom Instruction Analysis
Matthew Korban, Peter Youngs, Scott Acton, University of Virginia, United States
Contacts