Binghamton University

Search Results

technology+classifications+%3e+information+technology

3 Results Sort By:
BP4D+ Multimodal Emotion Dataset for Realistic AI Emotion Recognition

This invention introduces BP4D+, a large scale multimodal spontaneous emotion dataset integrating synchronized 3D facial dynamics, 2D video, thermal imaging, and physiological signals. Designed for real world affective computing, it enables accurate training and benchmarking of AI systems that recognize authentic human emotion. Background: Emotion...

Published: 3/26/2026 Updated: 8/4/2021 Inventor(s): Lijun Yin Keywords(s): #SUNYresearch, Technologies Category(s): Technology Classifications > Information Technology, Campus > Binghamton University
Semi-supervised Learning Based on Semiparametric Regularization

Semiparametric regularization based approach allows a family of algorithms to be developed based on various choices of the original RKHS and the loss function Technology Overview: Labeled data are often expensive to obtain since they require the efforts of experienced experts. Meanwhile, the unlabeled data are relatively easy to collect. Semiparametric...

Pattern Change Discovery Between High Dimensional Datasets

Pattern Change Discovery Between High Dimensional Datasets Background: This technology provides a powerful solution to the general problem of pattern change discovery between high-dimensional data sets. Current technologies either mainly focus on magnitude change detection of low-dimensional data sets or are under supervised frameworks. ...