Search results
Enter terms
268 results found.
Section: Publications & Resources
Publication: IEEE Open Journal of Signal Processing
The objective of meta-learning is to exploit knowledge obtained from observed tasks to improve adaptation to unseen tasks. Meta-learners are able to generalize better when they are trained with a larger number of observed tasks and with a larger amount of data per task. Given the amount of resources that are needed, it is generally difficult to expect the tasks, their respective data, and the necessary computational capacity to be available at a single central location.
Section: Publications & Resources
Dr. Sanjit K. Mitra, Distinguished Professor Emeritus of Electrical and Computer Engineering at University of California, Santa Barbara, has been elected recently to the Engineering Academy of Japan (EAJ) as a foreign associate. EAJ is composed of leading experts from academia, industry, and government institutions who possess a wide range of knowledge and have made outstanding contributions in engineering and technological sciences, and closely related fields...
Section: Publications & Resources
Dr. Sanjit K. Mitra, Distinguished Professor Emeritus of Electrical and Computer Engineering at University of California, Santa Barbara, has been elected recently to the Engineering Academy of Japan (EAJ) as a foreign associate. EAJ is composed of leading experts from academia, industry, and government institutions who possess a wide range of knowledge and have made outstanding contributions in engineering and technological sciences, and closely related fields...
Section: Publications & Resources
In this paper, the joint state and fault estimation problem is investigated for a class of discrete-time complex networks with measurement saturations and stochastic nonlinearities. The difference between the actual measurement and the saturated measurement is regarded as an unknown input and the system is thus re-organized as a singular system. An appropriate estimator is designed for each node which aims to estimate the system states and the loss of the actuator effectiveness simultaneously.
Section: Publications & Resources
Due to their effectiveness in capturing similarities between different entities, graphical models are widely used to represent datasets that reside on irregular and complex manifolds. Graph signal processing offers support to handle such complex datasets. In this paper, we propose a novel graph filter design method for semi-supervised data classification.
Section: Publications & Resources
Given a sequence of random (directed and weighted) graphs, we address the problem of online monitoring and detection of changes in the underlying data distribution. Our idea is to endow sequential change-point detection (CPD) techniques with a graph representation learning substrate based on the versatile Random Dot Product Graph (RDPG) model. We consider efficient, online updates of a judicious monitoring function, which quantifies the discrepancy between the streaming graph observations and the nominal RDPG.
Section: Publications & Resources
Decentralized stochastic gradient descent (SGD) is a driving engine for decentralized federated learning (DFL). The performance of decentralized SGD is jointly influenced by inter-node communications and local updates. In this paper, we propose a general DFL framework, which implements both multiple local updates and multiple inter-node communications periodically, to strike a balance between communication efficiency and model consensus.
Section: Publications & Resources
Publication: IEEE Signal Processing Letters
In this paper, we propose an enhancing steganographic scheme by random generation and ensemble stego selection. Different from existing steganography that only focuses on distortion function designing, our scheme considers both distortion model and optimized stego generation. In specific, for given cover, we firstly train an universal steganalyzer to calculate its gradient map, which is referenced to randomly adjust cost distribution of this cover.
Section: Publications & Resources
Publication: IEEE Signal Processing Letters
Audio-guided face reenactment aims to generate authentic target faces that have matched facial expression of the input audio, and many learning-based methods have successfully achieved this. However, most methods can only reenact a particular person once trained or suffer from the low-quality generation of the target images. Also, nearly none of the current reenactment works consider the model size and running speed that are important for practical use.
Section: Publications & Resources
Publication: IEEE Signal Processing Letters
Discriminative correlation filter (DCF)-based methods applied for UAV object tracking have received widespread attention due to their high efficiency. However, these methods are usually troubled by the boundary effect. Besides, the violent environment variations severely confuse trackers that neglect temporal environmental changes among consecutive frames, leading to unwanted tracking drift. In this letter, we propose a novel DCF-based tracking method to promote the insensitivity of the tracker under uncertain environmental changes.
