Impact Score 15.18
Due to the explosive growth of user-generated multi-modal data (e.g., images, videos, texts, audio clips, etc.) on the Internet, together with the urgent requirement of joint understanding the heterogeneous data, cross-media analysis and reasoning over multi-modal data has become an active research field and attracted a huge amount research interest from multiple communities in recent years. Especially, the cross-media reasoning (CMR) has been a key research direction towards Artificial Intelligence (AI). The goal of CMR is to understand physical objects and symbolic concepts, infer the relationships between different entities extracted from multimedia events, and then explore semantic/visual relations from multi-modal unstructured data for the solving of increasingly challenging real-world visual computing problems, such as visual question answering image/video captioning, and visual grounding. By endowing an AI machine with the ability of CMR, the machine is expected to be able to “think” like a human and then make explainable and trustable decisions.
Although considerable improvement has been made in the research of CMR for intelligent visual computing problems, it is still in the early research stage and requires further exploration by the community. It usually involves the high-level understanding of intrinsic attributes of entities extracted from cross-media contents and their association with other interactive entities using commonsense knowledge, where graph-like structures are usually utilized to perform joint relation reasoning. Reasoning of the high-order relations between cross-modal data types is quite difficult and remains underexplored. In short, CMR is a relatively high-level and difficult task in cross-media understanding. In recent years, there are several emerging research trends, including Knowledge-driven CMR, Neuro-Symbolic CMR, Visual Commonsense Reasoning, and Causality-inspired CMR, that may greatly improve the ability of CMR for intelligent visual computing tasks and thus attract increasing attention from worldwide researchers in multiple communities.
This special issue of Neurocomputing JOURNAL aims to bring together researchers interested in defining new and innovative solutions that will advance the research of CMR over multimedia data. The goal of the special issue is to solicit high-quality, high-impact and original papers on recent advances about the emerging research topics of CMR in the field of intelligent visual computing, as well as their applications in specific domains. We are interested in submissions covering topics of particular interest include, but are not limited to the following:
Prospective authors are invited to submit their manuscripts electronically according to the "Instructions for Authors" guidelines of “Neurocomputing” outlined at the journal website https://www.elsevier.com/journals/neurocomputing/0925-2312/guide-for-authors. Please submit your papers through the online system (https://www.editorialmanager.com/neucom/default.aspx) and be sure to select the special issue. Manuscripts should not be published or currently submitted for publication elsewhere. The review process will comply with the standard review process of the Neurocomputing journal. Each paper well receives at least two reviews from experts in the field.
● Submission deadline: October 1, 2021
● First-round decision notification: December 1 , 2021
● Revised manuscript due: January 1, 2022
● Final decision notification: February 1 , 2022
● Camera-ready version: March 1, 2022
● Online publication: TBD
Dr. Xun Yang, Research Fellow, National University of Singapore, Singapore, [email protected]
Dr. Linchao Zhu, Lecturer, University of Technology Sydney, Australia, [email protected]
Dr. Erkun Yang, Research Associate, The University of North Carolina at Chapel Hill, USA, [email protected]
Dr. Morteza Saberi, Lecturer, University of Technology Sydney, Australia, [email protected]
Dr. Meng Wang, Professor, Hefei University of Technology, China, [email protected]