The Experts below are selected from a list of 223167 Experts worldwide ranked by ideXlab platform
Yongdong Zhang - One of the best experts on this subject based on the ideXlab platform.
-
R-Net: A Relationship Network for Efficient and Accurate Scene Text Detection
IEEE Transactions on Multimedia, 2020Co-Authors: Yuxin Wang, Hongtao Xie, Zheng-jun Zha, Youliang Tian, Yongdong ZhangAbstract:This paper introduces a novel bi-directional convolutional framework to cope with the large-variance scale problem in scene text detection. Due to the lack of scale normalization in recent CNN-based methods, text instances with large-variance scale are activated inconsistently in feature maps, which makes it hard for CNN-based methods to accurately locate multi-size text instances. Thus, we propose the Relationship Network (R-Net) that maps multi-scale convolutional features to a scale-invariant space to obtain consistent activation of multi-size text instances. Firstly, we implement an FPN-like backbone with a Spatial Relationship Module (SPM) to extract multi-scale features with powerful spatial semantics. Then, a Scale Relationship Module (SRM) constructed on feature pyramid propagates contextual scale information in sequential features through a bi-directional convolutional operation. SRM supplements the multi-scale information in different feature maps to obtain consistent activation of multi-size text instances. Compared with previous approaches, R-Net effectively handles the large-variance scale problem without complicated post processing and complex hand-crafted hyperparameter setting. Extensive experiments conducted on several benchmarks verify that our R-Net obtains state-of-the-art performance on both accuracy and efficiency. More specifically, R-Net achieves an F-measure of 85.6% at 21.4 frames/s and an F-measure of 81.7% at 11.8 frames/s for ICDAR 2015 and MSRA-TD500 datasets respectively, which is the latest SOTA. The code is available on https://github.com/wangyuxin87/R-Net.
-
IJCAI - DSRN: A Deep Scale Relationship Network for Scene Text Detection
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019Co-Authors: Yuxin Wang, Hongtao Xie, Yongdong ZhangAbstract:Nowadays, scene text detection has become increasingly important and popular. However, the large variance of text scale remains the main challenge and limits the detection performance in most previous methods. To address this problem, we propose an end-to-end architecture called Deep Scale Relationship Network (DSRN) to map multi-scale convolution features onto a scale invariant space to obtain uniform activation of multi-size text instances. Firstly, we develop a Scale-transfer module to transfer the multi-scale feature maps to a unified dimension. Due to the heterogeneity of features, simply concatenating feature maps with multi-scale information would limit the detection performance. Thus we propose a Scale Relationship module to aggregate the multi-scale information through bi-directional convolution operations. Finally, to further reduce the miss-detected instances, a novel Recall Loss is proposed to force the Network to concern more about miss-detected text instances by up-weighting poor-classified examples. Compared with previous approaches, DSRN efficiently handles the large-variance scale problem without complex hand-crafted hyperparameter settings (e.g. scale of default boxes) and complicated post processing. On standard datasets including ICDAR2015 and MSRA-TD500, the proposed algorithm achieves the state-of-art performance with impressive speed (8.8 FPS on ICDAR2015 and 13.3 FPS on MSRA-TD500).
Yuxin Wang - One of the best experts on this subject based on the ideXlab platform.
-
R-Net: A Relationship Network for Efficient and Accurate Scene Text Detection
IEEE Transactions on Multimedia, 2020Co-Authors: Yuxin Wang, Hongtao Xie, Zheng-jun Zha, Youliang Tian, Yongdong ZhangAbstract:This paper introduces a novel bi-directional convolutional framework to cope with the large-variance scale problem in scene text detection. Due to the lack of scale normalization in recent CNN-based methods, text instances with large-variance scale are activated inconsistently in feature maps, which makes it hard for CNN-based methods to accurately locate multi-size text instances. Thus, we propose the Relationship Network (R-Net) that maps multi-scale convolutional features to a scale-invariant space to obtain consistent activation of multi-size text instances. Firstly, we implement an FPN-like backbone with a Spatial Relationship Module (SPM) to extract multi-scale features with powerful spatial semantics. Then, a Scale Relationship Module (SRM) constructed on feature pyramid propagates contextual scale information in sequential features through a bi-directional convolutional operation. SRM supplements the multi-scale information in different feature maps to obtain consistent activation of multi-size text instances. Compared with previous approaches, R-Net effectively handles the large-variance scale problem without complicated post processing and complex hand-crafted hyperparameter setting. Extensive experiments conducted on several benchmarks verify that our R-Net obtains state-of-the-art performance on both accuracy and efficiency. More specifically, R-Net achieves an F-measure of 85.6% at 21.4 frames/s and an F-measure of 81.7% at 11.8 frames/s for ICDAR 2015 and MSRA-TD500 datasets respectively, which is the latest SOTA. The code is available on https://github.com/wangyuxin87/R-Net.
-
IJCAI - DSRN: A Deep Scale Relationship Network for Scene Text Detection
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019Co-Authors: Yuxin Wang, Hongtao Xie, Yongdong ZhangAbstract:Nowadays, scene text detection has become increasingly important and popular. However, the large variance of text scale remains the main challenge and limits the detection performance in most previous methods. To address this problem, we propose an end-to-end architecture called Deep Scale Relationship Network (DSRN) to map multi-scale convolution features onto a scale invariant space to obtain uniform activation of multi-size text instances. Firstly, we develop a Scale-transfer module to transfer the multi-scale feature maps to a unified dimension. Due to the heterogeneity of features, simply concatenating feature maps with multi-scale information would limit the detection performance. Thus we propose a Scale Relationship module to aggregate the multi-scale information through bi-directional convolution operations. Finally, to further reduce the miss-detected instances, a novel Recall Loss is proposed to force the Network to concern more about miss-detected text instances by up-weighting poor-classified examples. Compared with previous approaches, DSRN efficiently handles the large-variance scale problem without complex hand-crafted hyperparameter settings (e.g. scale of default boxes) and complicated post processing. On standard datasets including ICDAR2015 and MSRA-TD500, the proposed algorithm achieves the state-of-art performance with impressive speed (8.8 FPS on ICDAR2015 and 13.3 FPS on MSRA-TD500).
Yuanfang Guan - One of the best experts on this subject based on the ideXlab platform.
-
Brain-specific functional Relationship Networks inform autism spectrum disorder gene prediction.
Translational psychiatry, 2018Co-Authors: Marlena Duda, Hongjiu Zhang, Dennis P. Wall, Margit Burmeister, Yuanfang GuanAbstract:Autism spectrum disorder (ASD) is a neuropsychiatric disorder with strong evidence of genetic contribution, and increased research efforts have resulted in an ever-growing list of ASD candidate genes. However, only a fraction of the hundreds of nominated ASD-related genes have identified de novo or transmitted loss of function (LOF) mutations that can be directly attributed to the disorder. For this reason, a means of prioritizing candidate genes for ASD would help filter out false-positive results and allow researchers to focus on genes that are more likely to be causative. Here we constructed a machine learning model by leveraging a brain-specific functional Relationship Network (FRN) of genes to produce a genome-wide ranking of ASD risk genes. We rigorously validated our gene ranking using results from two independent sequencing experiments, together representing over 5000 simplex and multiplex ASD families. Finally, through functional enrichment analysis on our highly prioritized candidate gene Network, we identified a small number of pathways that are key in early neural development, providing further support for their potential role in ASD.
-
Algorithms for modeling global and context-specific functional Relationship Networks
Briefings in bioinformatics, 2015Co-Authors: Zhu Fan, Bharat Panwar, Yuanfang GuanAbstract:Functional genomics has enormous potential to facilitate our understanding of normal and disease-specific physiology. In the past decade, intensive research efforts have been focused on modeling functional Relationship Networks, which summarize the probability of gene co-functionality Relationships. Such modeling can be based on either expression data only or heterogeneous data integration. Numerous methods have been deployed to infer the functional Relationship Networks, while most of them target the global (non-context-specific) functional Relationship Networks. However, it is expected that functional Relationships consistently reprogram under different tissues or biological processes. Thus, advanced methods have been developed targeting tissue-specific or developmental stage-specific Networks. This article brings together the state-of-the-art functional Relationship Network modeling methods, emphasizes the need for heterogeneous genomic data integration and context-specific Network modeling and outlines future directions for functional Relationship Networks.
-
Modeling the functional Relationship Network at the splice isoform level through heterogeneous data integration
2014Co-Authors: Rajasree Menon, Ridvan Eksi, Aysam Guerler, Yuan Zhang, Gilbert S. Omenn, Yuanfang GuanAbstract:Functional Relationship Networks, which reveal the collaborative roles between genes, have significantly accelerated our understanding of gene functions and phenotypic relevance. However, establishing such Networks for alternatively spliced isoforms remains a difficult, unaddressed problem due to the lack of systematic functional annotations at the isoform level, which renders most supervised learning methods difficult to be applied to isoforms. Here we describe a novel multiple instance learning-based probabilistic approach that integrates large-scale, heterogeneous genomic datasets, including RNA-seq, exon array, protein docking and pseudo-amino acid composition, for modeling a global functional Relationship Network at the isoform level in the mouse. Using this approach, we formulate a gene pair as a set of isoform pairs of potentially different properties. Through simulation and cross-validation studies, we showed the superior accuracy of our algorithm in revealing the isoform-level functional Relationships. The local Networks reveal functional diversity of the isoforms of the same gene, as demonstrated by both large-scale analyses and experimental and literature evidence for the disparate functions revealed for the isoforms of Ptbp1 and Anxa6 by our Network. Our work can assist the understanding of the diversity of functions achieved by alternative splicing of a limited set of genes in mammalian genomes, and may shift the current gene-centered Network prediction paradigm to the isoform level.
Nanning Zheng - One of the best experts on this subject based on the ideXlab platform.
-
visual manipulation Relationship Network for autonomous robotics
IEEE-RAS International Conference on Humanoid Robots, 2018Co-Authors: Hanbo Zhang, Xuguang Lan, Xinwen Zhou, Zhiqiang Tian, Yang Zhang, Nanning ZhengAbstract:Robotic grasping is one of the most important fields in robotics, in which great progress has been made in recent years with the help of convolutional neural Network (CNN). However, including multiple objects in one scene can invalidate the existing CNN-based grasp detection algorithms, because manipulation Relationships among objects are not considered, which are required to guide the robot to grasp things in the right order. This paper presents a new CNN architecture called Visual Manipulation Relationship Network (VMRN) to help robots detect targets and predict the manipulation Relationships in real time, which ensures that the robot can complete tasks in a safe and reliable way. To implement end-to-end training and meet real-time requirements in robot tasks, we propose the Object Pairing Pooling Layer (OP2L) to help to predict all manipulation Relationships in one forward process. Moreover, in order to train VMRN, we collect a dataset named Visual Manipulation Relationship Dataset (VMRD) consisting of 5185 images with more than 17000 object instances and the manipulation Relationships between all possible pairs of objects in every image, which is labeled by the manipulation Relationship tree. The experimental results show that the new Network architecture can detect objects and predict manipulation Relationships simultaneously and meet the real-time requirements in robot tasks.
-
Visual Manipulation Relationship Network.
arXiv: Robotics, 2018Co-Authors: Hanbo Zhang, Xuguang Lan, Xinwen Zhou, Zhiqiang Tian, Nanning ZhengAbstract:Grasping is one of the most significant manip- ulation in everyday life, which can be influenced a lot by grasping order when there are several objects in the scene. Therefore, the manipulation Relationships are needed to help robot better grasp and manipulate objects. This paper presents a new convolutional neural Network architecture called Visual Manipulation Relationship Network (VMRN), which is used to help robot detect targets and predict the manipulation Relationships in real time. To implement end-to-end training and meet real-time requirements in robot tasks, we propose the Object Pairing Pooling Layer (OP2L), which can help to predict all manipulation Relationships in one forward process. To train VMRN, we collect a dataset named Visual Manipulation Rela- tionship Dataset (VMRD) consisting of 5185 images with more than 17000 object instances and the manipulation Relationships between all possible pairs of objects in every image, which is labeled by the manipulation Relationship tree. The experiment results show that the new Network architecture can detect objects and predict manipulation Relationships simultaneously and meet the real-time requirements in robot tasks.
-
Humanoids - Visual Manipulation Relationship Network for Autonomous Robotics
2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), 2018Co-Authors: Hanbo Zhang, Xuguang Lan, Xinwen Zhou, Zhiqiang Tian, Yang Zhang, Nanning ZhengAbstract:Robotic grasping is one of the most important fields in robotics, in which great progress has been made in recent years with the help of convolutional neural Network (CNN). However, including multiple objects in one scene can invalidate the existing CNN-based grasp detection algorithms, because manipulation Relationships among objects are not considered, which are required to guide the robot to grasp things in the right order. This paper presents a new CNN architecture called Visual Manipulation Relationship Network (VMRN) to help robots detect targets and predict the manipulation Relationships in real time, which ensures that the robot can complete tasks in a safe and reliable way. To implement end-to-end training and meet real-time requirements in robot tasks, we propose the Object Pairing Pooling Layer (OP2L) to help to predict all manipulation Relationships in one forward process. Moreover, in order to train VMRN, we collect a dataset named Visual Manipulation Relationship Dataset (VMRD) consisting of 5185 images with more than 17000 object instances and the manipulation Relationships between all possible pairs of objects in every image, which is labeled by the manipulation Relationship tree. The experimental results show that the new Network architecture can detect objects and predict manipulation Relationships simultaneously and meet the real-time requirements in robot tasks.
Nils Urbach - One of the best experts on this subject based on the ideXlab platform.
-
Inter-technology Relationship Networks : Arranging technologies through text mining
Technological Forecasting and Social Change, 2019Co-Authors: Peter Hofmann, Robert Keller, Nils UrbachAbstract:Ongoing advances in digital technologies – which enable new products, services, and business models – have fundamentally affected business and society through several waves of digitalization. When analyzing digital technologies, a dynamic system or an ecosystem model that represents interrelated technologies is beneficial owing to the systemic character of digital technologies. Using an assembly-based process model for situational method engineering, and following the design science research paradigm, we develop an analytical method to generate technology-related Network data that retraces elapsed patterns of technological change. We consider the technological distances that characterize technologies' proximities and dependencies. We use established text mining techniques and draw from technology innovation research as justificatory knowledge. The proposed method processes textual data from different information sources into an analyzable and readable inter-technology Relationship Network. To evaluate the method, we use exemplary digital technologies from the big data analytics domain as an application scenario.