In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

We present a catalog of 138,665 radio sources derived from the initial 1550 deg2 of the FIRST survey. The survey parameters are reviewed, and a map depicting the coverage for the first two observing sessions is presented. We then describe in detail our algorithm for radio source detection and parameterization, as well as our procedures for constructing the final catalog. The results of extensive tests for astrometric and photometric accuracy, as well as for uncertainties in source extent and morphological characterization, are presented. Source positions are all good to better than 1'', and the flux density scale is accurate to 5%; our elliptical Gaussian fitting procedure is shown both to provide a high-fidelity representation of source morphology for most objects and to characterize correctly bright sources extended on scales down to ~ the synthesized beam size of 54. We use the catalog to construct a log N-log S relation for 20 cm radio sources over four decades of flux density, finding excellent agreement with previous determinations from smaller surveys. As one example of the catalog's utility, we present comparisons with the Guide Star Catalog, the IRAS Faint Source catalog, and the ROSAT WGA catalog, identifying radio counterparts to thousands of the objects. Complete instructions for access to this FIRST catalog and subsequent updates thereto are provided.

https://iopscience.iop.org/article/10.1086/303564/pdf

A Catalog of 1.4 GHz Radio Sources from the FIRST Survey

The 2 Micron All-Sky Survey (2MASS)will observe over one-million galaxies and extended Galactic sources covering the entire sky at wavelenghts between 1 and 2 m. Most of these galaxies, from 70 to 80%, will be newly catalogued objetcs.

https://iopscience.iop.org/article/10.1086/301330/pdf

2MASS Extended Source Catalog: Overview and Algorithms

https://www.qrg.northwestern.edu/papers/Files/macfac91%28searchable%29.pdf

MAC/FAC: A model of similarity-based retrieval☆

With the rapid proliferation of Internet technologies and applications, misuse of online messages for inappropriate or illegal purposes has become a major concern for society. The anonymous nature of online-message distribution makes identity tracing a critical problem. We developed a framework for authorship identification of online messages to address the identity-tracing problem. In this framework, four types of writing-style features (lexical, syntactic, structural, and content-specific features) are extracted and inductive learning algorithms are used to build feature-based classification models to identify authorship of online messages. To examine this framework, we conducted experiments on English and Chinese online-newsgroup messages. We compared the discriminating power of the four types of features and of three classification techniques: decision trees, backpropagation neural networks, and support vector machines. The experimental results showed that the proposed approach was able to identify authors of online messages with satisfactory accuracy of 70 to 95p. All four types of message features contributed to discriminating authors of online messages. Support vector machines outperformed the other two classification techniques in our experiments. The high performance we achieved for both the English and Chinese datasets showed the potential of this approach in a multiple-language context. © 2006 Wiley Periodicals, Inc.

A framework for authorship identification of online messages: Writing-style features and classification techniques

A central task underlying many of the activities of attorneys is inferring the legal consequences of a given set of facts. GREBE (GeneratoR of Exemplar-Based Explanations) is a system that uses detailed knowledge of the facts and reasoning of specific past cases, together with legal rules and common-sense knowledge, to determine and justify the legal consequences of new cases. GREBE can apply either rule-based reasoning or case-based reasoning to goals at any level of its analysis. GREBE uses an approach to case-based reasoning in which new cases are compared with the smallest collections of precedent facts that justified an individual inference step in the explanation of a precedent case. This enables knowledge of the interactions among individual inference steps in a precedent to be used in case comparison. Case comparison is also assisted by an expressive semantic network representation of case facts. Techniques are presented for retrieving and comparing cases represented in this formalism. GREBE's output is a memorandum that justifies a legal conclusion in terms of the applicable precedents and legal rules.

Building explanations from rules and structured cases

This paper proposes a model ofratio decidendi as a justification structure consisting of a series of reasoning steps, some of which relate abstract predicates to other abstract predicates and some of which relate abstract predicates to specific facts. This model satisfies an important set of characteristics ofratio decidendi identified from the jurisprudential literature. In particular, the model shows how the theory under which a case is decided controls its precedential effect. By contrast, a purely exemplar-based model ofratio decidendi fails to account for the dependency of precedential effect on the theory of decision.

A computational model of ratio decidendi

Stratified case-based reasoning is a technique in which abstract solutions produced during hierarchical problem solving are used to assist case-based retrieval, matching, and adaptation. We describe the motivation for the integration of case-based reasoning with hierarchical problem solving, exemplify its benefits, detail a set of algorithms that implement our approach, and present their comparative empirical evaluation on a path planning task. Our results show that stratified case-based reasoning significantly decreases the computational expense required to retrieve, match, and adapt cases, leading to performance superior both to simple case-based reasoning and to hierarchical problem solving ab initio.

https://ijcai.org/Proceedings/95-1/Papers/051.pdf

Stratified case-based reasoning: reusing hierarchical problem solving episodes

Reasoning with portions of precedents

This paper describes a model of the complementarity of rules and precedents in the classification task. Under this model, precedents assist rule-based reasoning by operationalizing abstract rule antecedents. Conversely, rules assist case-based reasoning through case elaboration, the process of inferring case facts in order to increase the similarity between cases, and term reformulation, the process of replacing a term whose precedents only weakly match a case with terms whose precedents strongly match the case. Fully exploiting this complementarity requires a control strategy characterized by impartiality, the absence of arbitrary ordering restrictions on the use of rules and precedents. An impartial control strategy was implemented in GREBE in the domain of Texas worker's compensation law. In a preliminary evaluation, GREBE's performance was found to be as good or slightly better than the performance of law students on the same task.

L. Karl Branting

Papers

Building explanations from rules and structured cases

A computational model of ratio decidendi

Stratified case-based reasoning: reusing hierarchical problem solving episodes

Reasoning with portions of precedents

Rules and precedents as complementary warrants