Aims and Topics:
Fine-grained object retrieval is a fundamental problem of pattern recognition and computer vision. Recently, it attracts more and more attentions owing to the practical demands for fine-grained semantic representation and matching in images and videos, such as fashion retrieval, object re-identification, place recognition, product checkout, and species protections, etc. Compared to tradi-tional retrieval tasks, fine-grained object retrieval involves multi-level seman-tics, which makes it more challenging to explore robust visual features and ef-ficient similarity measure, especially for unlabeled data or unseen domain.
The goal of this special issue is to gather the latest advances in fine-grained object retrieval, as well as feature matching and image ranking. Papers which focus on new theories and new applications of fine-grained retrieval are ex-tremely welcomed. Possible topics include but are not limited to:
o Fine-grained object retrieval in image, video and cross-media
o Adversarial and generative model for robust fine-grained image and video representation
o Efficient indexing and matching for large-scale fine-grained object retrieval
o Self-supervised learning, meta learning and unsupervised learning for adaptively knowledge transferring to unlabeled fine-grained objects or un-seen fine-grained classes
o Manifold learning and graph neural networks for complex semantic repre-sentations of fine-grained objects
o New datasets and evaluation metrics for fine-grained object retrieval
o Paper submission due: October 10, 2021
o First notification: January 10, 2022
o Revision due: March 10, 2022
o Acceptance notification: April 10, 2022
Ying Li, Nanjing Normal University, China
Xiu-Shen Wei, Nanjing University of Science and Technology, China
Fumin Shen, University of Electronic Science and Technology, China
Oisin Mac Aodha, University of Edinburgh, United Kingdom
Guo-Jun Qi, University of Central Florida, United States
Longin Jan Latecki, Temple University, United States
Dr. Ying Li
Email: [email protected]; [email protected]
School of Computer and Electronic Information
Nanjing Normal University, China
The submission system will be open around one week before the first paper comes in. When submitting your manuscript please select the article type “VSI: Fine-grained object”. 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.
Please see an example here: https://www.sciencedirect.com/journal/science-of-the-total-environment/special-issue/10SWS2W7VVV
Please ensure you read the Guide for Authors before writing your manuscript. The Guide for Authors and the link to submit your manuscript is available on the Journal’s homepage.