Query:
学者姓名:黄庆明
Refining:
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract :
The current mainstream studies on Scene Graph Generation (SGG) devote to the long-tailed predicate distribution problem to generate unbiased scene graph. The long-tailed predicate distribution exists in VG dataset and is more severe during the SGG network training process. Most existing de-biasing methods solve the problem by applying re- sampling or re- weighting in a mini-batch, with the main idea being to provide unbiased attention to different predicate categories based on prior predicate distributions. During the training process of SGG models, existing training mode samples several images into a mini-batch to obtain training data, thus providing sparse and scattered predicate instances for training. However, sampling predicate instances from a limited set of predicate samples in terms of quantity and category poses difficulties in training unbiased SGG models. In order to provide a wider range for sampling predicate instances, this paper reorganizes the images in VG training set with a new form, i.e. object-pairs, and constructs VG-OP (VG Object-Pair) training set to save object-pairs. Meanwhile, this paper introduces a new SGG network training mode, which can realize unbiased SGG without re- sampling or re- weighting. In particular, a Predicate-balanced Sampling Network (PS-Net) is designed to validate the new training mode. Extensive experiments on VG test set demonstrate that our method achieves competitive or state-of-the-art unbiased SGG performance.
Keyword :
new training data organization form new training data organization form Tail Tail balanced predicate instances balanced predicate instances Proposals Proposals Unbiased scene graph generation Unbiased scene graph generation Head Head Training Training new training mode new training mode Training data Training data Semantics Semantics Predictive models Predictive models
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Xu, Hongbo , Wang, Lichun , Xu, Kai et al. A New Training Data Organization Form and Training Mode for Unbiased Scene Graph Generation [J]. | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2024 , 34 (7) : 5295-5305 . |
MLA | Xu, Hongbo et al. "A New Training Data Organization Form and Training Mode for Unbiased Scene Graph Generation" . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 34 . 7 (2024) : 5295-5305 . |
APA | Xu, Hongbo , Wang, Lichun , Xu, Kai , Fu, Fangyu , Yin, Baocai , Huang, Qingming . A New Training Data Organization Form and Training Mode for Unbiased Scene Graph Generation . | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY , 2024 , 34 (7) , 5295-5305 . |
Export to | NoteExpress RIS BibTex |
Abstract :
In our urban life, Illegal Driver Substitution (IDS) activity for a taxi is a grave unlawful activity in the taxi industry. Currently, the IDS activity is manually supervised by law enforcers, i.e., law enforcers empirically choose a taxi and inspect it. The pressing problem of this scheme is the dilemma between the limited number of law-enforcers and the large volume of taxis. In this paper, we propose a computational method that helps law enforcers efficiently find the taxis which tend to have the IDS activity. Firstly, our method converts the identification of the IDS activity to a supervised learning task. Secondly, two kinds of taxi driver behaviors, i.e., the Sleeping Time and Location (STL) behavior and the Pick-Up (PU) behavior are proposed. Thirdly, the multiple scale pooling on self-similarity is proposed to encode the individual behaviors into the universal features for all taxis. Finally, a Multiple Component-Multiple Instance Learning (MC-MIL) is proposed to handle the deficiency of the behavior features and to align the behavior features, simultaneously. Extensive experiments on a real-world data set shows that the proposed behavior features have a good generalization ability across different classifiers, and the proposed MC-MIL method suppresses the baseline methods.
Keyword :
behavior modeling behavior modeling pooling pooling Illegal driver substitution activity Illegal driver substitution activity taxi supervision taxi supervision multiple scale multiple scale self-similarity self-similarity
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Pang, Junbiao , Sabir, Muhammad Ayub , Wang, Zuyun et al. Finding a Taxi With Illegal Driver Substitution Activity via Behavior Modelings [J]. | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS , 2024 . |
MLA | Pang, Junbiao et al. "Finding a Taxi With Illegal Driver Substitution Activity via Behavior Modelings" . | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2024) . |
APA | Pang, Junbiao , Sabir, Muhammad Ayub , Wang, Zuyun , Hu, Anjing , Yang, Xue , Yu, Haitao et al. Finding a Taxi With Illegal Driver Substitution Activity via Behavior Modelings . | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS , 2024 . |
Export to | NoteExpress RIS BibTex |
Abstract :
本发明实施例提供一种裂缝宽度测量方法及装置,所述方法包括:获取摄像头采集到的裂缝图像,并根据所述摄像头到裂缝表面的距离,以及所述摄像头拍摄所述裂缝图像时的焦距和像素,计算所述裂缝图像上单个像素点的宽度;识别所述裂缝图像的裂缝像素点,在所述裂缝像素点中选择单个裂缝像素点作为测量像素点,以所述测量像素点为中心点,在所述裂缝图像中获取裂缝块;根据预设算法计算得到所述裂缝块的裂缝主轴,获取经过所述测量像素点且垂直于所述裂缝主轴的直线;统计所述直线上的裂缝像素点的个数,通过所述裂缝像素点的个数及所述单个像素点的宽度计算得到裂缝宽度。采用本方法能够得到更高准确率的裂缝宽度计算结果。
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 庞俊彪 , 耿慧玲 , 段立娟 et al. 裂缝宽度测量方法及装置 : CN201911182766.5[P]. | 2019-11-27 . |
MLA | 庞俊彪 et al. "裂缝宽度测量方法及装置" : CN201911182766.5. | 2019-11-27 . |
APA | 庞俊彪 , 耿慧玲 , 段立娟 , 曾君 , 黄庆明 . 裂缝宽度测量方法及装置 : CN201911182766.5. | 2019-11-27 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Organizing webpages into hot topics is one of the key steps to understand the trends from multi-modal web data. To handle this pressing problem, Poisson Deconvolution (PD), a state-of-the-art method, recently is proposed to rank the interestingness of web topics on a similarity graph. Nevertheless, in terms of scalability, PD optimized by expectation-maximization is not sufficiently efficient for a large-scale data set. In this paper, we develop a Stochastic Poisson Deconvolution (SPD) to deal with the large-scale web data sets. Experiments demonstrate the efficacy of the proposed approach in comparison with the state-of-the-art methods on two public data sets and one large-scale synthetic data set. © 2019, Springer Nature Switzerland AG.
Keyword :
Maximum principle Maximum principle Stochastic systems Stochastic systems
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Lin, Jinzhong , Pang, Junbiao , Su, Li et al. Accelerating Topic Detection on Web for a Large-Scale Data Set via Stochastic Poisson Deconvolution [C] . 2019 : 590-602 . |
MLA | Lin, Jinzhong et al. "Accelerating Topic Detection on Web for a Large-Scale Data Set via Stochastic Poisson Deconvolution" . (2019) : 590-602 . |
APA | Lin, Jinzhong , Pang, Junbiao , Su, Li , Liu, Yugui , Huang, Qingming . Accelerating Topic Detection on Web for a Large-Scale Data Set via Stochastic Poisson Deconvolution . (2019) : 590-602 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Organizing multimodal Web pages into hot topics is the core step to grasp trends on the Web. However, the less-constrained social media generate noisy user-generated content, which makes a detected topic be less coherent and less interpretable. In this paper, we address this problem by proposing a coupled Poisson deconvolution to jointly handle topic detection and topic description. For the topic detection, the interestingness of a topic is estimated from the similarities refined by the description of topics; for the topic description, the interestingness of topics is leveraged to describe topics. Two processes cyclically detect interesting topics and generate the multimodal description of topics. This is the innovation of this paper, which just likes killing two birds with one stone. Experiments not only show the significantly improved accuracies for the topic detection but also demonstrate the interpretable descriptions for the topic description on two public data sets.
Keyword :
Multimodal description Multimodal description Poisson deconvolution (PD) Poisson deconvolution (PD) topic coherent topic coherent topic detection on Web topic detection on Web topic description topic description
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Pang, Junbiao , Tao, Fei , Huang, Qingming et al. Two Birds With One Stone: A Coupled Poisson Deconvolution for Detecting and Describing Topics From Multimodal Web Data [J]. | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2019 , 30 (8) : 2397-2409 . |
MLA | Pang, Junbiao et al. "Two Birds With One Stone: A Coupled Poisson Deconvolution for Detecting and Describing Topics From Multimodal Web Data" . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 30 . 8 (2019) : 2397-2409 . |
APA | Pang, Junbiao , Tao, Fei , Huang, Qingming , Tian, Qi , Yin, Baocai . Two Birds With One Stone: A Coupled Poisson Deconvolution for Detecting and Describing Topics From Multimodal Web Data . | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS , 2019 , 30 (8) , 2397-2409 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Bus arrival time prediction intends to improve the level of the services provided by transportation agencies. Intuitively, many stochastic factors affect the predictability of the arrival time, e.g., weather and local events. Moreover, the arrival time prediction for a current station is closely correlated with that of multiple passed stations. Motivated by the observations above, this paper proposes to exploit the long-range dependencies among the multiple time steps for bus arrival prediction via recurrent neural network (RNN). Concretely, RNN with long short-term memory block is used to "correct" the prediction for a station by the correlated multiple passed stations. During the correlation among multiple stations, one-hot coding is introduced to fuse heterogeneous information into a unified vector space. Therefore, the proposed framework leverages the dynamic measurements (i.e., historical trajectory data) and the static observations (i.e., statistics of the infrastructure) for bus arrival time prediction. In order to fairly compare with the state-of-the-art methods, to the best of our knowledge, we have released the largest data set for this task. The experimental results demonstrate the superior performances of our approach on this data set.
Keyword :
multi-step-ahead prediction multi-step-ahead prediction long-range dependencies long-range dependencies recurrent neural network recurrent neural network heterogenous measurement heterogenous measurement Bus arriving time prediction Bus arriving time prediction
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Pang, Junbiao , Huang, Jing , Du, Yong et al. Learning to Predict Bus Arrival Time From Heterogeneous Measurements via Recurrent Neural Network [J]. | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS , 2019 , 20 (9) : 3283-3293 . |
MLA | Pang, Junbiao et al. "Learning to Predict Bus Arrival Time From Heterogeneous Measurements via Recurrent Neural Network" . | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 20 . 9 (2019) : 3283-3293 . |
APA | Pang, Junbiao , Huang, Jing , Du, Yong , Yu, Haitao , Huang, Qingming , Yin, Baocai . Learning to Predict Bus Arrival Time From Heterogeneous Measurements via Recurrent Neural Network . | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS , 2019 , 20 (9) , 3283-3293 . |
Export to | NoteExpress RIS BibTex |
Abstract :
Organizing webpages into interesting topics is one of the key steps to understand the trends from multimodal Web data. The sparse, noisy, and less-constrained user-generated content results in inefficient feature representations. These descriptors unavoidably cause that a detected topic still contains a certain number of the false detected webpages, which further make a topic be less coherent, less interpretable, and less useful. In this paper, we address this problem from a viewpoint interpreting a topic by its prototypes, and present a two-step approach to achieve this goal. Following the detection-by-ranking approach, a sparse Poisson deconvolution is proposed to learn the intratopic similarities between webpages. To find the prototypes, leveraging the intratopic similarities, top-k diverse yet representative prototype webpages are identified from a submodularity function. Experimental results not only show the improved accuracies for the Web topic detection task, but also increase the interpretation of a topic by its prototypes on two public datasets.
Keyword :
Poisson deconvolution Poisson deconvolution sparsity sparsity Web topic detection Web topic detection submodularity submodularity prototype learning (PL) prototype learning (PL) topic interpretation topic interpretation
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Pang, Junbiao , Hu, Anjing , Huang, Qingming et al. Increasing Interpretation of Web Topic Detection via Prototype Learning From Sparse Poisson Deconvolution [J]. | IEEE TRANSACTIONS ON CYBERNETICS , 2019 , 49 (3) : 1072-1083 . |
MLA | Pang, Junbiao et al. "Increasing Interpretation of Web Topic Detection via Prototype Learning From Sparse Poisson Deconvolution" . | IEEE TRANSACTIONS ON CYBERNETICS 49 . 3 (2019) : 1072-1083 . |
APA | Pang, Junbiao , Hu, Anjing , Huang, Qingming , Tian, Qi , Yin, Baocai . Increasing Interpretation of Web Topic Detection via Prototype Learning From Sparse Poisson Deconvolution . | IEEE TRANSACTIONS ON CYBERNETICS , 2019 , 49 (3) , 1072-1083 . |
Export to | NoteExpress RIS BibTex |
Abstract :
As increasing volumes of urban data are being available, new opportunities arise for data-driven analysis that can lead to improvements in the lives of citizens through evidence-based policies. In particular, taxi trip is an important urban sensor that provides unprecedented insights into many aspects of a city, from economic activity, human mobility to land development. However, analyzing these data presents many challenges, e.g., sparse data for fine-grained patterns, and the regularity submerged by seemingly random data. Inspired by above challenges, we focus on Pick-Up (PU)/Drop-Off (DO) points from taxi trips, and propose a fine-grained approach to unveil a set of low spatio-temporal patterns from the regularity-discovered intensity. The proposed method is conceptually simple yet efficient, by leveraging point process to handle sparsity of points, and by decomposing point intensities into the low-rank regularity and the factorized basis patterns, our approach enables domain experts to discover patterns that are previously unattainable for them, from a case study motivated by traffic engineers.
Keyword :
taxis trip taxis trip low-rank regularity low-rank regularity matrix factorization matrix factorization fine-grained pattern fine-grained pattern Spatio-temporal pattern Spatio-temporal pattern point process point process
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Pang, Junbiao , Huang, Jing , Yang, Xue et al. Discovering Fine-Grained Spatial Pattern From Taxi Trips: Where Point Process Meets Matrix Decomposition and Factorization [J]. | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS , 2018 , 19 (10) : 3208-3219 . |
MLA | Pang, Junbiao et al. "Discovering Fine-Grained Spatial Pattern From Taxi Trips: Where Point Process Meets Matrix Decomposition and Factorization" . | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 19 . 10 (2018) : 3208-3219 . |
APA | Pang, Junbiao , Huang, Jing , Yang, Xue , Wang, Zuyun , Yu, Haitao , Huang, Qingming et al. Discovering Fine-Grained Spatial Pattern From Taxi Trips: Where Point Process Meets Matrix Decomposition and Factorization . | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS , 2018 , 19 (10) , 3208-3219 . |
Export to | NoteExpress RIS BibTex |
Abstract :
To quickly grasp what interesting topics are happening on web, it is challenge to discover and describe topics from User-Generated Content (UGC) data. Describing topics by probable keywords and prototype images is an efficient human-machine interaction to help person quickly grasp a topic. However, except for the challenges from web topic detection, mining the multi-media description is a challenge task that the conventional approaches can barely handle: (1) noises from non-informative short texts or images due to less-constrained UGC; and (2) even for these informative images, the gaps between visual concepts and social ones. This paper addresses above challenges from the perspective of background similarity remove, and proposes a two-step approach to mining the multi-media description from noisy data. First, we utilize a devcovolution model to strip the similarities among non-informative words/images during web topic detection. Second, the background-removed similarities are reconstructed to identify the probable keywords and prototype images during topic description. By removing background similarities, we can generate coherent and informative multi-media description for a topic. Experiments show that the proposed method produces a high quality description on two public datasets. (C) 2017 Elsevier B.V. All rights reserved.
Keyword :
Topic detection Topic detection Poisson deconvolution Poisson deconvolution Multi-modal description Multi-modal description User-Generated Content User-Generated Content Topic description Topic description Background similarity Background similarity
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Pang, Junbiao , Tao, Fei , Li, Liang et al. A two-step approach to describing web topics via probable keywords and prototype images from background-removed similarities [J]. | NEUROCOMPUTING , 2018 , 275 : 478-487 . |
MLA | Pang, Junbiao et al. "A two-step approach to describing web topics via probable keywords and prototype images from background-removed similarities" . | NEUROCOMPUTING 275 (2018) : 478-487 . |
APA | Pang, Junbiao , Tao, Fei , Li, Liang , Huang, Qingming , Yin, Baocai , Tian, Qi . A two-step approach to describing web topics via probable keywords and prototype images from background-removed similarities . | NEUROCOMPUTING , 2018 , 275 , 478-487 . |
Export to | NoteExpress RIS BibTex |
Abstract :
本发明实施例提供一种获取网络话题原型的方法及装置。所述方法包括:基于所有候选网络话题,对所述候选网络话题对应的目标网页集合的相似度图进行拟合和重构,获得重构后的相似度图;所述候选网络话题通过对应的目标网页集合的相似度图进行聚类得到;基于重构后的相似度图,获取所述候选网络话题中每个网络话题对应的原型网页。本发明实施例所述方法可以找到网络话题中具有话题代表性和多样性的原型网页,直接将原型网页反馈给用户用以了解网络话题的内容,而不需要通过提取网络话题中各网页的关键词来了解网络话题,有效减少了网络话题中错误检测的网页对网络话题描述带来的负面影响,和提取的关键词语义不连续对用户理解产生的影响。
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 庞俊彪 , 胡安静 , 黄庆明 et al. 一种获取网络话题原型的方法及装置 : CN201711024178.X[P]. | 2017-10-27 . |
MLA | 庞俊彪 et al. "一种获取网络话题原型的方法及装置" : CN201711024178.X. | 2017-10-27 . |
APA | 庞俊彪 , 胡安静 , 黄庆明 , 尹宝才 . 一种获取网络话题原型的方法及装置 : CN201711024178.X. | 2017-10-27 . |
Export to | NoteExpress RIS BibTex |
Export
Results: |
Selected to |
Format: |