Collection
S.I. Open-domain Image Retrieval in the Wild
- Submission status
- Closed
We are now living in a large-scale image data era. Facing the explosive growth of image samples in the real world, it is urgently needed to explore new methods for efficient image retrieval. However, existing works on content-based image retrieval are typically devoted to closed-domain scenarios, where all the classes are pre-defined and trained in a single-task fashion. In fact, in many open-domain applications (e.g. recommendation for online shopping and person re-identification in a security scenario), the data distributions are complex, dynamic, or even unpredictable. This poses a major challenge and new research topics for open-domain image retrieval in the wild. Since there has not been enough discussion about overcoming this challenge, this special issue aims to capture state-of-the-art research works being focused particularly on open-domain image retrieval tasks, where the model enables to (1) retrieve novel and unseen classes with no access to their labels in a zero-shot transfer fashion; (2) continually learn a sequence of new tasks instead of one fixed task; (3) perform multi-modal retrieval between images and other modalities (e.g. sketch, text, audio), as well as their emerging applications in fashion recommendation, biometrics and social media.
Numerous image retrieval works have appeared in top conferences and journals. Nevertheless, there has been yet no special issue to systematically collect mature research and to boost future work in the area of open-domain image retrieval. This special issue provides a venue for researchers and practitioners from different fields (in particular, multimedia and computer vision) to present high-quality research work and to provide a cross-fertilization ground for stimulating discussions on the next steps in this important research area.
Topics of Interest
This special issue advances new theories, algorithms, applications and benchmarks on open-domain image retrieval. It invites submissions related to the broad topic area of open-domain image retrieval, including but not limited to the following topic areas:
• Open-domain image retrieval with few-/zero-shot learning methods
• Open-domain image retrieval with continual/incremental learning methods
• Open-domain image retrieval with self-supervised learning methods
• Open-domain image retrieval with domain adaptation/generalization methods
• Open-domain image retrieval with fast, efficient and scalable algorithms
• Open-domain image retrieval with new datasets or task designs
• Their emerging application areas such as ecommerce search and recommendation systems
Important Dates:
Open for Submissions: December 20, 2022
Paper Submission Deadline: January 31, 2023
First Notification: March 31, 2023
Paper Revisions Deadline: May 31, 2023
Final Notification: July 1, 2023
Tentative Publication: Fall, 2023
Submission Guidelines: Authors should prepare their manuscript according to the Instructions for Authors available from the International Journal of Multimedia Information Retrieval website. Authors should submit through the online submission site at International Journal of Multimedia Information Retrieval and select “S.I. Open-domain Image Retrieval in the Wild" when they reach the “Article Type” step in the submission process. Submitted papers should present original, unpublished work, relevant to the topics of the special issue. All submitted papers will be evaluated on the basis of relevance, significance of contribution, technical quality, scholarship, and quality of presentation, by at least three independent reviewers. It is the policy of the journal that no submission, or substantially overlapping submission, be published or be under review at another journal or conference at any time during the review process. Final decisions on all papers are made by the Editor in Chief.
Editors
-
Yu Liu ,
Yu Liu
Yu Liu, Dalian University of Technology, China - liuyu8824@dlut.edu.cn
-
Yanming Guo
Yanming Guo, Hunan Institute of Advanced Technology
-
Yusuke Matsui
Yusuke Matsui, The University of Tokyo
Articles (12 in this collection)
-
-
Ornament image retrieval using few-shot learning
Authors
- Sk Maidul Islam
- Subhankar Joardar
- Arif Ahmed Sekh
- Content type: Regular Paper
- Published: 31 August 2023
- Article: 30
-
DELIGHT-Net: DEep and LIGHTweight network to segment Indian text at word level from wild scenic images
Authors
- Shilpa Mahajan
- Rajneesh Rani
- Karan Trehan
- Content type: Regular Paper
- Published: 24 August 2023
- Article: 29
-
Neural style transfer generative adversarial network (NST-GAN) for facial expression recognition
Authors
- Faten Khemakhem
- Hela Ltifi
- Content type: Regular Paper
- Published: 23 August 2023
- Article: 26
-
CoCoOpter: Pre-train, prompt, and fine-tune the vision-language model for few-shot image classification
Authors (first, second and last of 6)
- Jie Yan
- Yuxiang Xie
- Xidao Luan
- Content type: Regular Paper
- Published: 23 August 2023
- Article: 27
-
Detecting abnormal behavior in megastore for crime prevention using a deep neural architecture
Authors
- Mohd. Aquib Ansari
- Dushyant Kumar Singh
- Vibhav Prakash Singh
- Content type: Regular Paper
- Published: 10 August 2023
- Article: 25
-
An improved customized CNN model for adaptive recognition of cerebral palsy people’s handwritten digits in assessment
Authors
- K. Muthureka
- U. Srinivasulu Reddy
- B. Janet
- Content type: Regular Paper
- Published: 09 August 2023
- Article: 23
-
An interactive attribute-preserving fashion recommendation with 3D image-based virtual try-on
Authors
- Ahmad Alzu’bi
- Lojin Bani Younis
- Alia Madain
- Content type: Regular Paper
- Published: 09 August 2023
- Article: 24
-
Content-based image retrieval using handcraft feature fusion in semantic pyramid
Authors
- Fatemeh Taheri
- Kambiz Rahbar
- Ziaeddin Beheshtifard
- Content type: Regular Paper
- Published: 09 August 2023
- Article: 21
-
Modal interaction-enhanced prompt learning by transformer decoder for vision-language models
Authors (first, second and last of 4)
- Mingyue Liu
- Honggang Zhao
- Mingyong Li
- Content type: Regular Paper
- Published: 03 August 2023
- Article: 19
-
Recognition of student engagement in classroom from affective states
Authors
- Sandeep Mandia
- Kuldeep Singh
- Rajendra Mitharwal
- Content type: Regular Paper
- Published: 31 July 2023
- Article: 18
-
Deep adversarial multi-label cross-modal hashing algorithm
Authors (first, second and last of 5)
- Xiaohan Yang
- Zhen Wang
- Nannan Wu
- Content type: Regular Paper
- Published: 29 July 2023
- Article: 16