Search results

Section: Events

Date: 14 December 2022 Time: 3:00 PM (Paris Time) Title: Subgraph-Based Networks for Expressive, Efficient, and Domain-Independent Graph Learning Registration | Full webinar details

Section: Events

Date: 6 December 2022 Time: 3:00 PM (Central European Time (CET)) Title: Artificial Intelligence for Applications in Neurology Registration | Full webinar details

Section: Events

Date: 13 December 2022 Time: 10:00 AM ET (New York Time) Title: Deep Learning for All-in-Focus Imaging Registration | Full webinar details

Section: Events

Submission Deadline: 6 January 2023 Call for Proposals Document

Section: Events

Submission Deadline: 3 January 2023 Call for Proposals Document

Section: Publications & Resources

Publication: IEEE Open Journal of Signal Processing

Reviewer Instructions for OJSP Reproducibility Reviews Author Instructions For OJSP Reproducibility Review Reviewer Instructions for OJSP Reproducibility Reviews-->ContextOJSP has initiated an enhanced reproducibility initiative for learning-based papers, i.e., papers where the primary results are obtained using a trained computational model, such as a deep neural network or a dictionary representation.

Section: Publications & Resources

Publication: IEEE Open Journal of Signal Processing

Reviewer Instructions for OJSP Reproducibility Reviews Author Instructions For OJSP Reproducibility Review -->Code Ocean is a cloud-based platform that facilitates reproducibility of computational research and supports reproducibility reviews. Authors can set up a private “compute capsule” on Code Ocean to which they can upload code and data and configure the computational environment required to run their code.

Section: Publications & Resources

We develop algorithms to analyzing facial expression by learning from the data. Since local characters of muscle movements play an important role in distinguishing facial expression by machines, we explore the local characters of facial expressions by introducing the attention mechanism in both supervised and self-supervised supervised manners. Our methods is experimentally shown to be effective on facial expression recognition with occlusions and facial action unit detection.

Section: Publications & Resources

We design a data-driven wavelet transform, called the empirical wavelet transform, which permits to extract very accurate time-frequency information from signals, or features from images.

Section: Publications & Resources

A brief introduction to state estimation in multi-object system that arises from applications where the number of objects and their states are unknown and vary randomly with time. State space model (SSM) is a fundamental concept in system theory that permeated through many fields of study.