Listing 1 - 10 of 2482 | << page >> |
Sort by
|
Choose an application
Deep Learning through Sparse Representation and Low-Rank Modeling bridges classical sparse and low rank models—those that emphasize problem-specific Interpretability—with recent deep network models that have enabled a larger learning capacity and better utilization of Big Data. It shows how the toolkit of deep learning is closely tied with the sparse/low rank methods and algorithms, providing a rich variety of theoretical and analytic tools to guide the design and interpretation of deep learning models. The development of the theory and models is supported by a wide variety of applications in computer vision, machine learning, signal processing, and data mining. This book will be highly useful for researchers, graduate students and practitioners working in the fields of computer vision, machine learning, signal processing, optimization and statistics. Combines classical sparse and low-rank models and algorithms with the latest advances in deep learning networks Shows how the structure and algorithms of sparse and low-rank methods improves the performance and interpretability of Deep Learning models Provides tactics on how to build and apply customized deep learning models for various applications
Choose an application
Das Verstehen menschlichen Verhaltens ist essenziell für intelligente technische Systeme in menschlichen Umgebungen. Diese Arbeit befasst sich mit der videobasierten Aktivitätsanalyse. Dazu werden zwei Methoden der Merkmalsextraktion untersucht: ein markerloses dreidimensionales Körpertracking mit einem evolutionären Algorithmus und ein modellfreies Tracking dynamischer Videomerkmale. Anschließend erfolgt eine Modellierung und Klassifikation von Aktivitäten auf Basis der gewonnenen Merkmale. Understanding human behavior is crucial for intelligent technical systems in human environments. In this work, methods for human activity recognition based on video data are developed. Two approaches of feature extraction are pursued: a method of markerless articulated pose estimation using an evolutionary algorithm and a model-free feature tracking method. The resulting motion representations are then used for modeling and classifying different activities.
Choose an application
Choose an application
Choose an application
Choose an application
Choose an application
Choose an application
Choose an application
Choose an application
Listing 1 - 10 of 2482 | << page >> |
Sort by
|