no code implementations • 3 Dec 2020 • Xu Guo, Han Yu, Boyang Li, Hao Wang, Pengwei Xing, Siwei Feng, Zaiqing Nie, Chunyan Miao
In this paper, we propose the FedHumor approach for the recognition of humorous content in a personalized manner through Federated Learning (FL).
no code implementations • 30 Jan 2020 • Siwei Feng, Han Yu
Federated learning (FL) is a privacy-preserving paradigm for training collective machine learning models with locally stored data from multiple participants.
no code implementations • 25 Sep 2019 • Marco F. Duarte, Siwei Feng
While variable selection in statistics aims to distinguish between true and false predictors, feature selection in machine learning aims to reduce the dimensionality of the data while preserving the performance of the learning method.
no code implementations • 25 Mar 2019 • Siwei Feng, Marco F. Duarte
The proposed few-shot human activity recognition method leverages a deep learning model for feature extraction and classification while knowledge transfer is performed in the manner of model parameter transfer.
no code implementations • 5 Aug 2018 • Siwei Feng, Han Yu, Marco F. Duarte
In this paper, we propose a metric for the relevance between a source sample and the target samples.
no code implementations • 7 Jan 2018 • Siwei Feng, Marco F. Duarte
Feature selection is a dimensionality reduction technique that selects a subset of representative features from high dimensional data by eliminating irrelevant and redundant features.
no code implementations • 3 Jan 2017 • Yuki Itoh, Siwei Feng, Marco F. Duarte, Mario Parente
This paper proposes a new hyperspectral unmixing method for nonlinearly mixed hyperspectral data using a semantic representation in a semi-supervised fashion, assuming the availability of a spectral reference library.
no code implementations • 11 Feb 2016 • Siwei Feng, Yuki Itoh, Mario Parente, Marco F. Duarte
Hyperspectral signature classification is a quantitative analysis approach for hyperspectral imagery which performs detection and classification of the constituent materials at the pixel level in the scene.