Description and Topics
The success of machine learning and in-depth explorations of deep neural networks have facilitated the advances in understanding the high-level semantic of visual contents. Deep relational learning aims to provide a fine-grained modelling of the relationships and interactions of visual content, including visual relationship detection, scene graph generation, and knowledge graph extraction. The progress of deep relational learning can also improve the down-stream tasks that requires fine-grained visual understanding—e.g., visual question answering, referring expression, and visual captioning.
This special issue aims to demonstrate on 1; 1) how machine learning algorithms and deep neural network models have contributed, and are contributing, to new theories, models, and datasets related to the topic of deep relational learning; and 2) how deep relational learning can facilitate other task like visual recognition, understanding, and reasoning. The editors hope to collect a group of research results to report the recent developments in the related research topics. In addition, researchers can exchange their innovative ideas on the topic of deep relational learning in visual recognition, understanding, and reasoning by submitting manuscripts to this special issue. To summarize, this special issue prefers a large scope of submissions, which develop and adopt new progress for these topics. We are especially interested in 1) theoretical advances and algorithm developments in deep relational learning; 2) useful applications and system creations of deep relational learning in visual recognition, understanding, and reasoning; and 3) new datasets and benchmarks for new progress. Topics of interest include, but are not limited to:
Supervised, weakly-supervised and unsupervised deep models for relational learning
Graph learning, adversarial learning and transfer learning for relation analysis
Multi-modal knowledge network representation and reasoning
Visual relationship detection and scene graph generation
Human action and human-object interactions recognition
Visual recognition, detection and segmentation with relational learning
Visual question answering, visual captioning and referring expression
Data-driven and knowledge-driven visual reasoning models
New datasets and benchmarks related to the aforementioned topics
The submission system will be open around one week before the first paper comes in. When submitting your manuscript please select the article type “SI: Deep relational learning”. Please submit your manuscript before the submission deadline.
All submissions deemed suitable to be sent for peer review will be reviewed by at least two independent reviewers. Once your manuscript is accepted, it will go into production, and will be simultaneously published in the current regular issue and pulled into the online Special Issue. Articles from this Special Issue will appear in different regular issues of the journal, though they will be clearly marked and branded as Special Issue articles.
Submission portal open date: May 1st. 2020
Paper submission due: Jul. 1st. 2020
First review notification: Sept. 1st. 2020
Revision submission: Nov. 1st. 2020
Acceptance notification: Jan. 1st. 2021
Jun Yu Hangzhou Dianzi University China, email@example.com
Fionn Murtagh University of Huddersfield
Yuanyan Tang University of Macau
Dacheng Tao University of Sydney Australia