M1.5

Instructional Activity Recognition Using A Transformer Network with Multi-Semantic Attention

Matthew Korban, Peter Youngs, University of Virginia, United States; Jonathan Foster, University at Albany, United States; Scott T. Acton, University of Virginia, United States
Session:
M1: Image/Video Analysis and Modeling I Lecture
Track:
Image and video indexing and retrieval
Location:
Lecture Room
Presentation Time:
Mon, 18 Mar, 10:05 - 10:20 MST (UTC -7)
Presentation
Discussion
Resources
No resources available.
Session M1
M1.1 Crime Detection from Pre-crime Video Analysis with Augmented Pose and Emotion Information
Sedat Kilic, Mihran Tuceryan, Indiana University - Purdue University - Indianapolis (IUPUI), United States
M1.2 OPTIMIZATION OF SWIM POSE ESTIMATION AND RECOGNITION WITH DATA AUGMENTATION
Jonathan Ouyang, Derrick Trinh, Chang Choo, San Jose State University, United States
M1.3 Illumination Correction For Unsupervised Person Re-Identification
Jiaqi Guo, Amy R. Reibman, Edward J. Delp, Purdue University, United States
M1.4 ULI-RI: A Benchmark For Person Re-Identification With Quantitative Annotations
Jiaqi Guo, Amy R. Reibman, Edward J. Delp, Purdue University, United States
M1.5 Instructional Activity Recognition Using A Transformer Network with Multi-Semantic Attention
Matthew Korban, Peter Youngs, University of Virginia, United States; Jonathan Foster, University at Albany, United States; Scott T. Acton, University of Virginia, United States
Resources
No resources available.