The Experts below are selected from a list of 840 Experts worldwide ranked by ideXlab platform

Hsu-feng Hsiao - One of the best experts on this subject based on the ideXlab platform.

  • ISCAS - Saliency Detection with Multi-Contextual Models and Spatially Coherent Loss Function
    2019 IEEE International Symposium on Circuits and Systems (ISCAS), 2020
    Co-Authors: Po-sheng Huang, Chin-han Shen, Hsu-feng Hsiao
    Abstract:

    We have proposed a multi-contextual model architecture with color and depth information considered independently in this work. To utilize the feature maps of different levels better, short connection structures are used to integrate the knowledge from color and depth data separately. A novel loss function considering three criteria is proposed to improve the detection accuracy and spatial coherence of the detected results. The training process of the proposed network is divided into two stages, a pre-training Phase and a Refinement Phase to increase the efficiency of the network.

  • Saliency Detection with Multi-Contextual Models and Spatially Coherent Loss Function
    2019 IEEE International Symposium on Circuits and Systems (ISCAS), 2019
    Co-Authors: Po-sheng Huang, Chin-han Shen, Hsu-feng Hsiao
    Abstract:

    We have proposed a multi-contextual model architecture with color and depth information considered independently in this work. To utilize the feature maps of different levels better, short connection structures are used to integrate the knowledge from color and depth data separately. A novel loss function considering three criteria is proposed to improve the detection accuracy and spatial coherence of the detected results. The training process of the proposed network is divided into two stages, a pre-training Phase and a Refinement Phase to increase the efficiency of the network.

Po-sheng Huang - One of the best experts on this subject based on the ideXlab platform.

  • ISCAS - Saliency Detection with Multi-Contextual Models and Spatially Coherent Loss Function
    2019 IEEE International Symposium on Circuits and Systems (ISCAS), 2020
    Co-Authors: Po-sheng Huang, Chin-han Shen, Hsu-feng Hsiao
    Abstract:

    We have proposed a multi-contextual model architecture with color and depth information considered independently in this work. To utilize the feature maps of different levels better, short connection structures are used to integrate the knowledge from color and depth data separately. A novel loss function considering three criteria is proposed to improve the detection accuracy and spatial coherence of the detected results. The training process of the proposed network is divided into two stages, a pre-training Phase and a Refinement Phase to increase the efficiency of the network.

  • Saliency Detection with Multi-Contextual Models and Spatially Coherent Loss Function
    2019 IEEE International Symposium on Circuits and Systems (ISCAS), 2019
    Co-Authors: Po-sheng Huang, Chin-han Shen, Hsu-feng Hsiao
    Abstract:

    We have proposed a multi-contextual model architecture with color and depth information considered independently in this work. To utilize the feature maps of different levels better, short connection structures are used to integrate the knowledge from color and depth data separately. A novel loss function considering three criteria is proposed to improve the detection accuracy and spatial coherence of the detected results. The training process of the proposed network is divided into two stages, a pre-training Phase and a Refinement Phase to increase the efficiency of the network.

Shuai Cheng Li - One of the best experts on this subject based on the ideXlab platform.

  • String join using precedence count matrix
    Proceedings. 16th International Conference on Scientific and Statistical Database Management 2004., 2004
    Co-Authors: A.h.k. Tung, Shuai Cheng Li
    Abstract:

    In this paper; we propose a filter-and-refine string join algorithm. While the filtering Phase can rapidly prune away strings that are not joinable, the Refinement Phase employs a comprehensive algorithm to remove the remaining false alarms. The efficiency of the proposed scheme lies in the use of the precedence count matrix (PCM) for computing the edit distance between two sequences. With PCM, the complexity of sequence comparison is a constant time. We also evaluated the proposed sequence join algorithm, and our study shows that it outperforms the known techniques.

  • SSDBM - String join using precedence count matrix
    2004
    Co-Authors: A.h.k. Tung, Shuai Cheng Li
    Abstract:

    In this paper; we propose a filter-and-refine string join algorithm. While the filtering Phase can rapidly prune away strings that are not joinable, the Refinement Phase employs a comprehensive algorithm to remove the remaining false alarms. The efficiency of the proposed scheme lies in the use of the precedence count matrix (PCM) for computing the edit distance between two sequences. With PCM, the complexity of sequence comparison is a constant time. We also evaluated the proposed sequence join algorithm, and our study shows that it outperforms the known techniques.

Chin-han Shen - One of the best experts on this subject based on the ideXlab platform.

  • ISCAS - Saliency Detection with Multi-Contextual Models and Spatially Coherent Loss Function
    2019 IEEE International Symposium on Circuits and Systems (ISCAS), 2020
    Co-Authors: Po-sheng Huang, Chin-han Shen, Hsu-feng Hsiao
    Abstract:

    We have proposed a multi-contextual model architecture with color and depth information considered independently in this work. To utilize the feature maps of different levels better, short connection structures are used to integrate the knowledge from color and depth data separately. A novel loss function considering three criteria is proposed to improve the detection accuracy and spatial coherence of the detected results. The training process of the proposed network is divided into two stages, a pre-training Phase and a Refinement Phase to increase the efficiency of the network.

  • Saliency Detection with Multi-Contextual Models and Spatially Coherent Loss Function
    2019 IEEE International Symposium on Circuits and Systems (ISCAS), 2019
    Co-Authors: Po-sheng Huang, Chin-han Shen, Hsu-feng Hsiao
    Abstract:

    We have proposed a multi-contextual model architecture with color and depth information considered independently in this work. To utilize the feature maps of different levels better, short connection structures are used to integrate the knowledge from color and depth data separately. A novel loss function considering three criteria is proposed to improve the detection accuracy and spatial coherence of the detected results. The training process of the proposed network is divided into two stages, a pre-training Phase and a Refinement Phase to increase the efficiency of the network.

João Luís Sobral - One of the best experts on this subject based on the ideXlab platform.

  • Towards a faster and accurate supertree inference
    2015 IEEE Symposium on Computers and Communication (ISCC), 2015
    Co-Authors: Diogo Telmo Neves, João Luís Sobral
    Abstract:

    Phylogenetic inference is one of the most challenging and important problems in computational biology. However, computing evolutionary links on data sets containing only few thousands of taxa easily becomes a daunting task. Moreover, recent advances in next-generation sequencing technologies are turning this problem even much harder, either in terms of complexity or scale. Therefore, phylogenetic inference requires new algorithms and methods to handle the unprecedented growth of biological data. In this paper, we identify several types of parallelism that are available while refining a supertree. We also present four improvements that we made to SuperFine - a state-of-the-art supertree (meta)method -, which add support: i) to use FastTree as the inference tool; ii) to use a parallel version of FastTree, or RAxML, as the inference tool; iii) to exploit intra-polytomy parallelism within the so-called polytomy Refinement Phase; and iv) to exploit, at the same time, inter-polytomy and intra-polytomy parallelism within the polytomy Refinement Phase. Together, these improvements allow an efficient and transparent exploitation of hybrid-polytomy parallelism. Additionally, we pinpoint how future contributions should enhance the performance of such applications. Our studies show groundbreaking results in terms of the achieved speedups, specially when using biological data sets. Moreover, we show that the new parallel strategy - which exploits the hybrid-polytomy parallelism within the polytomy Refinement Phase - exhibits good scalability, even in the presence of asymmetric sets of tasks. Furthermore, the achieved results show that the radical improvement in performance does not impair tree accuracy, which is a key issue in phylogenetic inferences.

  • ISCC - Towards a faster and accurate supertree inference
    2015 IEEE Symposium on Computers and Communication (ISCC), 2015
    Co-Authors: Diogo Telmo Neves, João Luís Sobral
    Abstract:

    Phylogenetic inference is one of the most challenging and important problems in computational biology. However, computing evolutionary links on data sets containing only few thousands of taxa easily becomes a daunting task. Moreover, recent advances in next-generation sequencing technologies are turning this problem even much harder, either in terms of complexity or scale. Therefore, phylogenetic inference requires new algorithms and methods to handle the unprecedented growth of biological data. In this paper, we identify several types of parallelism that are available while refining a supertree. We also present four improvements that we made to SuperFine — a state-of-the-art supertree (meta)method —, which add support: i) to use FastTree as the inference tool; ii) to use a parallel version of FastTree, or RAxML, as the inference tool; iii) to exploit intra-polytomy parallelism within the so-called polytomy Refinement Phase; and iv) to exploit, at the same time, inter-polytomy and intra-polytomy parallelism within the polytomy Refinement Phase. Together, these improvements allow an efficient and transparent exploitation of hybrid-polytomy parallelism. Additionally, we pinpoint how future contributions should enhance the performance of such applications. Our studies show groundbreaking results in terms of the achieved speedups, specially when using biological data sets. Moreover, we show that the new parallel strategy — which exploits the hybrid-polytomy parallelism within the polytomy Refinement Phase — exhibits good scalability, even in the presence of asymmetric sets of tasks. Furthermore, the achieved results show that the radical improvement in performance does not impair tree accuracy, which is a key issue in phylogenetic inferences.