SpringerBriefs in Computer Science
5 total works
Robust Recognition via Information Theoretic Learning
by Ran He, Baogang Hu, Xiaotong Yuan, and Liang Wang
This Springer Brief represents a comprehensive review of information theoretic methods for robust recognition. A variety of information theoretic methods have been proffered in the past decade, in a large variety of computer vision applications; this work brings them together, attempts to impart the theory, optimization and usage of information entropy.
The authors resort to a new information theoretic concept, correntropy, as a robust measure and apply it to solve robust face recognition and object recognition problems. For computational efficiency, the brief introduces the additive and multiplicative forms of half-quadratic optimization to efficiently minimize entropy problems and a two-stage sparse presentation framework for large scale recognition problems. It also describes the strengths and deficiencies of different robust measures in solving robust recognition problems.
Heterogeneous Facial Analysis and Synthesis
by Yi Li, Huaibo Huang, Ran He, and Tieniu Tan
This book presents a comprehensive review of heterogeneous face analysis and synthesis, ranging from the theoretical and technical foundations to various hot and emerging applications, such as cosmetic transfer, cross-spectral hallucination and face rotation. Deep generative models have been at the forefront of research on artificial intelligence in recent years and have enhanced many heterogeneous face analysis tasks. Not only has there been a constantly growing flow of related research papers, but there have also been substantial advances in real-world applications. Bringing these together, this book describes both the fundamentals and applications of heterogeneous face analysis and synthesis. Moreover, it discusses the strengths and weaknesses of related methods and outlines future trends.
Offering a rich blend of theory and practice, the book represents a valuable resource for students, researchers and practitioners who need to construct face analysis systems with deep generative networks.
Context-Aware Collaborative Prediction
by Shu Wu, Qiang Liu, Liang Wang, and Tieniu Tan
This book presents two collaborative prediction approaches based on contextual representation and hierarchical representation, and their applications including context-aware recommendation, latent collaborative retrieval and click-through rate prediction. The proposed techniques offer significant improvements over current methods, the key determinants being the incorporated contextual representation and hierarchical representation. To provide a background to the core ideas presented, it offers an overview of contextual modeling and the theory of contextual representation and hierarchical representation, which are constructed for the joint interaction of entities and contextual information.
The book offers a rich blend of theory and practice, making it a valuable resource for students, researchers and practitioners who need to construct systems of information retrieval, data mining and recommendation systems with contextual information.
Feature Coding for Image Representation and Recognition
by Yongzhen Huang and Tieniu Tan
Although deep learning models have achieved great progress in vision, speech, language, planning, control, and many other areas, there still exists a large performance gap between deep learning models and the human cognitive system. Many researchers argue that one of the major reasons accounting for the performance gap is that deep learning models and the human cognitive system process visual information in very different ways.
To mimic the performance gap, since 2014, there has been a trend to model various cognitive mechanisms from cognitive neuroscience, e.g., attention, memory, reasoning, and decision, based on deep learning models. This book unifies these new kinds of deep learning models and calls them deep cognitive networks, which model various human cognitive mechanisms based on deep learning models. As a result, various cognitive functions are implemented, e.g., selective extraction, knowledge reuse, and problem solving, for more effective information processing.
This book first summarizes existing evidence of human cognitive mechanism modeling from cognitive psychology and proposes a general framework of deep cognitive networks that jointly considers multiple cognitive mechanisms. Then, it analyzes related works and focuses primarily but not exclusively, on the taxonomy of four key cognitive mechanisms (i.e., attention, memory, reasoning, and decision) surrounding deep cognitive networks. Finally, this book studies two representative cases of applying deep cognitive networks to the task of image-text matching and discusses important future directions.