A unified framework for multi-modal federated learning
Authors:
- Baochen XiongBXBaochen Xiong
- Xiaoshan YangXYXiaoshan Yang
- Fan QiFQFan Qi
- Changsheng XuCXChangsheng Xu
Top Cited Papers
- 22 January 2022
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 480, 110-118
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (61720106006, 61721004, 61872424, 62072455, U1705262, U1836220)
- Beijing Natural Science Foundation
- National Key Research and Development Program of China (2018AAA0100604)
This publication has 20 references indexed in Scilit:
- Deep Temporal Multimodal Fusion for Medical Procedure Monitoring Using Wearable SensorsIEEE Transactions on Multimedia, 2017
- Egocentric activity recognition by leveraging multiple mid-level representations2016
- Deep Residual Learning for Image Recognition2016
- Rethinking the Inception Architecture for Computer Vision2016
- Going Deeper into First-Person Activity Recognition2016
- Multimodal Multi-Stream Deep Learning for Egocentric Activity Recognition2016
- VQA: Visual Question Answering2015
- Privacy Aware LearningJournal of the ACM, 2014
- Real-life events in multimedia: detection, representation, retrieval, and applicationsMultimedia Tools and Applications, 2013
- Canonical Correlation Analysis: An Overview with Application to Learning MethodsNeural Computation, 2004