Special Issue "Representation Learning for Computer Vision and Pattern Recognition"
Deadline for manuscript submissions: 28 February 2024 | Viewed by 5267
Interests: machine learning; pattern recognition; learning-based vision problems
Special Issues, Collections and Topics in MDPI journals
Interests: artificial intelligence and its applications to computer vision
Representation learning has always been an important research area in Computer Vision and Pattern Recognition. A good representation of practical data is critical to achieve satisfactory performance. Broadly speaking, such presentation can be an "intra-data representation" or an "inter-data representation". Intra-data representation focuses on extracting or refining the raw feature of a data point itself. Representative methods range from early stage hand-crafted feature design (e.g., SIFT, LBP, HoG, etc.) to feature extraction (e.g., PCA, LDA, LLE, etc.) and feature selection (e.g., sparsity-based and submodularity-based methods) established in the past two decades, until the recent development of deep neural networks (e.g., CNN, RNN, GNN, GAN, etc.). Inter-data representation characterizes the relationship between different data points or the structure carried out by the dataset. For example, metric learning, kernel learning and causality reasoning investigate the spatial or temporal relationships among different examples, while subspace learning, manifold learning and clustering discover the underlying structural property inherited by the dataset.
The above analysis reflects that representation learning covers a wide range of research topics related to pattern recognition. On one hand, many new algorithms on representation learning are put forward every year to cater to the needs of processing and understanding various practical multimedia data. On the other hand, massive problems regarding representation learning still remain unsolved, especially for big data and noisy data. Thereby, the objective of this Special Issue is to provide a stage for researchers all over the world to publish their latest and original results on representation learning.
Topics include but are not limited to:
- Metric learning and kernel learning;
- Multi-view/Multi-modal learning;
- Robust representation and coding;
- Domain transfer learning ;
- Learning under low-quality media data;
- Efficient vision Transformer;
- Deep learning and its applications.
Dr. Guangwei Gao
Dr. Juncheng Li
Dr. Zhi Li
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
- representation learning
- computer vision
- pattern recognition
- metric learning and kernel learning
- multi-view/multi-modal learning
- robust representation and coding
- domain transfer learning
- learning under low-quality media data
- efficient vision Transformer
- deep learning and its applications