Pattern Recognition is the official journal of the Pattern Recognition Society. The Society was formed to fill a need for information exchange among research workers in the pattern recognition field. Up to now, we ''pattern-recognitionophiles'' have been tagging along in computer science, information theory, optical processing techniques, and other miscellaneous fields. Because this work in pattern recognition presently appears in widely spread articles and as isolated lectures in conferences in many diverse areas, the purpose of the journal Pattern Recognition is to give all of us an opportunity to get together in one place to publish our work. The journal will thereby expedite communication among research scientists interested in pattern recognition.

We consider pattern recognition in the broad sense, and we assume that the journal will be read by people with a common interest in pattern recognition but from many diverse backgrounds. These include biometrics, target recognition, biological taxonomy, meteorology, space science, classification methods, character recognition, image processing, industrial applications, neural computing, and many others.

The publication policy is to publish (1) new original articles that have been appropriately reviewed by competent scientific people, (2) reviews of developments in the field, and (3) pedagogical papers covering specific areas of interest in pattern recognition. Various special issues will be organized from time to time on current topics of interest to Pattern Recognition.

Special Issue on Fine-grained object retrieval, matching and ranking
Submission Date: 2021-10-10

Aims and Topics:

Fine-grained object retrieval is a fundamental problem in pattern recognition and computer vision. Recently, it has begun to attract more attention owing to the practical demand for fine-grained semantic representation learning and matching in images and videos, for applications in fashion retrieval, object re-identification, place recognition, product checkout, and species prediction, etc. Compared to traditional retrieval tasks, fine-grained retrieval involves multi-level semantics which makes it more challenging as it requires robust visual features and efficient similarity metrics, especially for in the case of unlabeled data or novel domains.

The goal of this special issue is to gather the latest advances in fine-grained object retrieval, fine-grained feature matching, and image ranking. Papers which focus on new theory and new applications of fine-grained retrieval are also extremely welcome. Possible topics include, but are not limited to:
- Fine-grained object retrieval in image, video, and cross-media data
- Adversarial and generative models for robust fine-grained image and video representation learning
- Efficient indexing and matching for large-scale fine-grained object retrieval
- Self-supervised learning, meta learning, and unsupervised learning for adaptively transferring knowledge to unlabeled fine-grained objects or unseen fine-grained classes
- Manifold learning and graph neural networks for complex semantic representations of fine-grained objects