Call for paper (IF 18.6)：截止2024年1月30日

Transformer Models for Multi-source Visual Fusion and Understanding

Multi-source Visual Fusion and Understanding (MSVFU) has emerged as an important area for research and applications. It aims to transform data sensed from the environment into raw models of perceptual content and then build a broader understanding of the world. Transformer models have achieved great success in the past few years, especially on language and image-related tasks. When it comes to multi-source data, transformer may provide a flexible solution by adopting similar processing blocks to process the input of different modalities as well as their cross-modal interactions. This special issue seeks original contributions towards advancing the theory, architecture, and algorithmic design for transformer models in MSVFU, as well as their novel applications and use cases.

Topics of interest include (but are not limited to) transformer models with:

• novel multi-source data fusion architecture

• multimodal visual data representation

• multi-domain adaptive learning

• multi-view learning for MSVFU

• self-supervised learning for MSVFU

• supervised learning for MSVFU

• weakly supervised learning for MSVFU

• transfer learning for MSVFU

• multimodal visual data generation

• cross-modal adaptation

Guest editors:

Dr. Xiao Bai, PhD

Beihang University, Beijing, China. [email protected]

(Pattern Recognition; Computer Vision; Graph Learning)

Dr. Xin Ning, PhD

Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China. [email protected]

(Pattern Recognition; Multimodal Learning; Neural Networks)

Dr. Jun Zhou, PhD

Griffith University, Brisbane, Australia. [email protected]

(Spectral Imaging; Image Processing; Pattern Recognition)

Dr. Byung-Gyu Kim, PhD

Sookmyung Women's University, Seoul, South. Korea. [email protected]

(Computer Vision; Deep Learning; Pattern Recognition)

Dr. Prayag Tiwari, PhD

Halmstad University, Sweden. [email protected]

(Artificial Intelligence; Machine Learning; Health Informatics)

Dr. Yang Xiao, PhD

The University of Alabama, Tuscaloosa, USA. [email protected]

(Cyber-Physical Systems; Internet of Things; Wireless Networks)

Manuscript submission information:

The journal's submission platform (EditorialManager® https://www.editorialmanager.com/inffus/default2.aspx ) will be available for receiving submissions to this Special Issue from June 30th, 2023 . Please refer to the Guide for Authors to prepare your manuscript, and select the article type of “ VSI: MSVFU ” when submitting your manuscript online. Both the Guide for Authors and the submission portal could be found on the Journal Homepage: https://www.sciencedirect.com/journal/information-fusion

Timeline:

Submission Open Date * 30/06/2023

Final Manuscript Submission Deadline * 30/01/2024

Editorial Acceptance Deadline *30/03/2024

Keywords:

novel multi-source data fusion architecture; multimodal visual data representation; multi-domain adaptive learning; multi-view learning for MSVFU; transfer learning for MSVFU; multimodal visual data generation; cross-modal adaptation.

Information Fusion的CAR指数

2023年3月份科睿唯安官方一次性踢除35本SCI期刊，多数涉及学术诚信问题，让我们意识到学术期刊的“被踢”指数，也很重要。目前，对于期刊的 “被踢”指数 ，这里介绍一下： CAR指数 （关于C AR的 详 细介绍，请关注： www.jcarindex.com ） ，这是一种评价期刊学术诚信风险的指数， 指数 越高代表可能的风险越大。从数据看， Information Fusion 不管是2022年度，还是2023年度实时的CAR指数，都是比较低的。 当然， CAR指数仅供参考，期刊风险情况，需以科睿唯安或中科院预警等官方为准！

来源：www.jcarindex.com