公开(公告)号：US11908345B2

公开(公告)日：2024-02-20

申请号：US16234255

申请日：2018-12-27

Applicant: Intel Corporation

Inventor： Nese Alyuz Civitci ,  Cagri Cagatay Tanriover ,  Sinem Aslan ,  Eda Okur Kavil ,  Asli Arslan Esme ,  Ergin Genc

IPC: G09B19/00 ,  G09B5/08 ,  G06V40/16 ,  G06F18/25

CPC classification number: G09B5/08 ,  G06F18/256 ,  G06V40/161 ,  G06V40/171 ,  G06V40/172 ,  G06V40/176 ,  G09B19/00

Abstract: Various systems and methods for engagement dissemination. A face detector detects a face in video data. A context filterer determines a student is on-platform and a section type. An appearance monitor selects an emotional and a behavioral classifiers. Emotional and behavioral components are classified based on the detected face. A context-performance monitor selects an emotional and a behavioral classifiers specific to the section type, Emotional and behavioral components are classified based on the log data. A fuser combines the emotional components into an emotional state of the student based on confidence values of the emotional components. The fuser combines the behavioral components a behavioral state of the student based on confidence values of the behavioral components. The user determine an engagement level of the student based on the emotional state and the behavioral state of the student.

公开(公告)号：US20230298322A1

公开(公告)日：2023-09-21

申请号：US18325436

申请日：2023-05-30

Applicant: Intel Corporation

Inventor： Ibrahima Ndiour ,  Nilesh Ahuja ,  Ranganath Krishnan ,  Mahesh Subedar ,  Omesh Tickoo ,  Ergin Genc

IPC: G06V10/77 ,  G06V10/82 ,  G06V10/80

CPC classification number: G06V10/7715 ,  G06V10/82 ,  G06V10/80

Abstract: Features extracted from one or more layers of a trained deep neural network (DNN) are used to detect out-of-distribution (OOD) data, such as anomalies. An OOD detection process includes transforming a feature output from a layer of the DNN from a relatively high-dimensional feature space to a lower-dimensional space, and then performing a reverse transformation back to the higher-dimensional feature space, resulting in a reconstructed feature. A feature reconstruction error is calculated based on a difference between the reconstructed feature and the original feature output from the DNN. The OOD detection process may further include calculating a score based on the feature reconstruction error and generating a visual representation of the feature reconstruction error.