The Experts below are selected from a list of 147000 Experts worldwide ranked by ideXlab platform

Shihfu Chang - One of the best experts on this subject based on the ideXlab platform.

  • Learning Component level sparse representation using histogram information for image classification
    International Conference on Computer Vision, 2011
    Co-Authors: Chen-kuo Chiang, Chih-hsueh Duan, Shang-hong Lai, Shihfu Chang
    Abstract:

    A novel Component-level dictionary Learning framework which exploits image group characteristics within sparse coding is introduced in this work. Unlike previous methods, which select the dictionaries that best reconstruct the data, we present an energy minimization formulation that jointly optimizes the Learning of both sparse dictionary and Component level importance within one unified framework to give a discriminative representation for image groups. The importance measures how well each feature Component represents the image group property with the dictionary by using histogram information. Then, dictionaries are updated iteratively to reduce the influence of unimportant Components, thus refining the sparse representation for each image group. In the end, by keeping the top K important Components, a compact representation is derived for the sparse coding dictionary. Experimental results on several public datasets are shown to demonstrate the superior performance of the proposed algorithm compared to the-state-of-the-art methods.

  • ICCV - Learning Component-level sparse representation using histogram information for image classification
    2011 International Conference on Computer Vision, 2011
    Co-Authors: Chen-kuo Chiang, Chih-hsueh Duan, Shang-hong Lai, Shihfu Chang
    Abstract:

    A novel Component-level dictionary Learning framework which exploits image group characteristics within sparse coding is introduced in this work. Unlike previous methods, which select the dictionaries that best reconstruct the data, we present an energy minimization formulation that jointly optimizes the Learning of both sparse dictionary and Component level importance within one unified framework to give a discriminative representation for image groups. The importance measures how well each feature Component represents the image group property with the dictionary by using histogram information. Then, dictionaries are updated iteratively to reduce the influence of unimportant Components, thus refining the sparse representation for each image group. In the end, by keeping the top K important Components, a compact representation is derived for the sparse coding dictionary. Experimental results on several public datasets are shown to demonstrate the superior performance of the proposed algorithm compared to the-state-of-the-art methods.

Anette Weisbecker - One of the best experts on this subject based on the ideXlab platform.

  • Reading and Learning - Component-Based Software Engineering Methods for Systems in Document Recognition, Analysis, and Understanding
    Lecture Notes in Computer Science, 2004
    Co-Authors: Oliver Höß, Oliver Strauß, Anette Weisbecker
    Abstract:

    Modern systems in the field of document recognition, document analysis and document understanding have to be built in a short amount of time, with a low budget and have to comply to the functional and non-functional requirements of the customers. Traditional software engineering methods cannot cope with these challenges in an adequate way. The Component-approach promises to be a solution for the efficient development of high-quality systems. The paper describes the basics of the Component-approach and its application to the area of recognition systems. Special attention is paid to Component technologies, the integration of heterogeneous systems by using wrapping techniques and the central issue of Component reuse. The works in this paper have been part of the project Adaptive READ which was funded by the German Federal Ministry of Education and Research.

Chen-kuo Chiang - One of the best experts on this subject based on the ideXlab platform.

  • Learning Component-Level Sparse Representation for Image and Video Categorization
    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 2013
    Co-Authors: Chen-kuo Chiang, Chao-hsien Liu, Chih-hsueh Duan, Shang-hong Lai
    Abstract:

    A novel Component-level dictionary Learning framework that exploits image/video group characteristics based on sparse representation is introduced in this paper. Unlike the previous methods that select the dictionaries to best reconstruct the data, we present an energy minimization formulation that jointly optimizes the Learning of both sparse dictionary and Component-level importance within one unified framework to provide a discriminative and sparse representation for image/video groups. The importance measures how well each feature Component represents the group property with the dictionary. Then, the dictionary is updated iteratively to reduce the influence of unimportant Components, thus refining the sparse representation for each group. In the end, by keeping the top K important Components, a compact representation is obtained for the sparse coding dictionary. Experimental results on several public image and video data sets are shown to demonstrate the superior performance of the proposed algorithm compared with the-state-of-the-art methods.

  • Learning Component level sparse representation using histogram information for image classification
    International Conference on Computer Vision, 2011
    Co-Authors: Chen-kuo Chiang, Chih-hsueh Duan, Shang-hong Lai, Shihfu Chang
    Abstract:

    A novel Component-level dictionary Learning framework which exploits image group characteristics within sparse coding is introduced in this work. Unlike previous methods, which select the dictionaries that best reconstruct the data, we present an energy minimization formulation that jointly optimizes the Learning of both sparse dictionary and Component level importance within one unified framework to give a discriminative representation for image groups. The importance measures how well each feature Component represents the image group property with the dictionary by using histogram information. Then, dictionaries are updated iteratively to reduce the influence of unimportant Components, thus refining the sparse representation for each image group. In the end, by keeping the top K important Components, a compact representation is derived for the sparse coding dictionary. Experimental results on several public datasets are shown to demonstrate the superior performance of the proposed algorithm compared to the-state-of-the-art methods.

  • ICCV - Learning Component-level sparse representation using histogram information for image classification
    2011 International Conference on Computer Vision, 2011
    Co-Authors: Chen-kuo Chiang, Chih-hsueh Duan, Shang-hong Lai, Shihfu Chang
    Abstract:

    A novel Component-level dictionary Learning framework which exploits image group characteristics within sparse coding is introduced in this work. Unlike previous methods, which select the dictionaries that best reconstruct the data, we present an energy minimization formulation that jointly optimizes the Learning of both sparse dictionary and Component level importance within one unified framework to give a discriminative representation for image groups. The importance measures how well each feature Component represents the image group property with the dictionary by using histogram information. Then, dictionaries are updated iteratively to reduce the influence of unimportant Components, thus refining the sparse representation for each image group. In the end, by keeping the top K important Components, a compact representation is derived for the sparse coding dictionary. Experimental results on several public datasets are shown to demonstrate the superior performance of the proposed algorithm compared to the-state-of-the-art methods.

Shang-hong Lai - One of the best experts on this subject based on the ideXlab platform.

  • Learning Component-Level Sparse Representation for Image and Video Categorization
    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 2013
    Co-Authors: Chen-kuo Chiang, Chao-hsien Liu, Chih-hsueh Duan, Shang-hong Lai
    Abstract:

    A novel Component-level dictionary Learning framework that exploits image/video group characteristics based on sparse representation is introduced in this paper. Unlike the previous methods that select the dictionaries to best reconstruct the data, we present an energy minimization formulation that jointly optimizes the Learning of both sparse dictionary and Component-level importance within one unified framework to provide a discriminative and sparse representation for image/video groups. The importance measures how well each feature Component represents the group property with the dictionary. Then, the dictionary is updated iteratively to reduce the influence of unimportant Components, thus refining the sparse representation for each group. In the end, by keeping the top K important Components, a compact representation is obtained for the sparse coding dictionary. Experimental results on several public image and video data sets are shown to demonstrate the superior performance of the proposed algorithm compared with the-state-of-the-art methods.

  • Learning Component level sparse representation using histogram information for image classification
    International Conference on Computer Vision, 2011
    Co-Authors: Chen-kuo Chiang, Chih-hsueh Duan, Shang-hong Lai, Shihfu Chang
    Abstract:

    A novel Component-level dictionary Learning framework which exploits image group characteristics within sparse coding is introduced in this work. Unlike previous methods, which select the dictionaries that best reconstruct the data, we present an energy minimization formulation that jointly optimizes the Learning of both sparse dictionary and Component level importance within one unified framework to give a discriminative representation for image groups. The importance measures how well each feature Component represents the image group property with the dictionary by using histogram information. Then, dictionaries are updated iteratively to reduce the influence of unimportant Components, thus refining the sparse representation for each image group. In the end, by keeping the top K important Components, a compact representation is derived for the sparse coding dictionary. Experimental results on several public datasets are shown to demonstrate the superior performance of the proposed algorithm compared to the-state-of-the-art methods.

  • ICCV - Learning Component-level sparse representation using histogram information for image classification
    2011 International Conference on Computer Vision, 2011
    Co-Authors: Chen-kuo Chiang, Chih-hsueh Duan, Shang-hong Lai, Shihfu Chang
    Abstract:

    A novel Component-level dictionary Learning framework which exploits image group characteristics within sparse coding is introduced in this work. Unlike previous methods, which select the dictionaries that best reconstruct the data, we present an energy minimization formulation that jointly optimizes the Learning of both sparse dictionary and Component level importance within one unified framework to give a discriminative representation for image groups. The importance measures how well each feature Component represents the image group property with the dictionary by using histogram information. Then, dictionaries are updated iteratively to reduce the influence of unimportant Components, thus refining the sparse representation for each image group. In the end, by keeping the top K important Components, a compact representation is derived for the sparse coding dictionary. Experimental results on several public datasets are shown to demonstrate the superior performance of the proposed algorithm compared to the-state-of-the-art methods.

Vlad Posea - One of the best experts on this subject based on the ideXlab platform.

  • enhancing the Learning process qualitative validation of an informal Learning support system consisting of a knowledge discovery and a social Learning Component
    European Conference on Technology Enhanced Learning, 2010
    Co-Authors: Eline Westerhout, Paola Monachesi, Thomas Markus, Vlad Posea
    Abstract:

    In a Lifelong Learning context, learners often rely on informal Learning materials to access and process information. There is a growing interest in accessing educational material on the social web. We have created a system that facilitates learners and tutors in accessing informal knowledge sources in the context of a Learning task and describe the results of a summative and formative evaluation of this system. The system consists of a knowledge discovery Component and a social Learning Component. The evaluation shows that with our system informal resources can successfully enhance the Learning process within a Lifelong Learning context. The knowledge discovery Component assists the learner in identifying relevant concepts, discovering relations between concepts, and mastering the correct vocabulary. In addition the social Learning Component offers relevant and trusted documents and contacts on the basis of a learner's social network.

  • EC-TEL - Enhancing the Learning process: qualitative validation of an informal Learning support system consisting of a knowledge discovery and a social Learning Component
    Sustaining TEL: From Innovation to Learning and Practice, 2010
    Co-Authors: Eline Westerhout, Paola Monachesi, Thomas Markus, Vlad Posea
    Abstract:

    In a Lifelong Learning context, learners often rely on informal Learning materials to access and process information. There is a growing interest in accessing educational material on the social web. We have created a system that facilitates learners and tutors in accessing informal knowledge sources in the context of a Learning task and describe the results of a summative and formative evaluation of this system. The system consists of a knowledge discovery Component and a social Learning Component. The evaluation shows that with our system informal resources can successfully enhance the Learning process within a Lifelong Learning context. The knowledge discovery Component assists the learner in identifying relevant concepts, discovering relations between concepts, and mastering the correct vocabulary. In addition the social Learning Component offers relevant and trusted documents and contacts on the basis of a learner's social network.