您的检索：
学者姓名：黄庆明
精炼检索结果：
年份
成果类型
收录类型
来源
综合
合作者
语言
清除所有精炼条件
摘要 ：
Organizing a few webpages from social media into hot topics is one of the key steps to understand trends on web. Discovering popular yet hot topics from web faces a sea of noise webpages which never evolve into popular topics. In this paper, we discover that the similarity values between webpages in a popular topic contain the statistically similar features observed in L & eacute;vy walks. Consequently, we present a simple, novel, yet very powerful Explore-Exploit (EE) approach to group topics by simulating L & eacute;vy walks nature in the similarity space. The proposed EE-based topic clustering is an effective and efficient method which is a solid move towards handling a sea of noise webpages. Experiments on two public data sets demonstrate that our approach is not only comparable to the State-Of-The-Art (SOTA) methods in terms of effectiveness but also significantly outperforms the SOTA methods in terms of efficiency.
关键词 ：
User-generated content User-generated content Noise robust clustering Noise robust clustering Explore-exploit Explore-exploit L & eacute;vy walks L & eacute;vy walks Web topic detection Web topic detection
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Pang, Junbiao , Huang, Qingming . Towards scalable topic detection on web via simulating Lévy walks nature of topics in similarity space [J]. | INFORMATION SCIENCES , 2024 , 690 . |
| MLA | Pang, Junbiao 等. "Towards scalable topic detection on web via simulating Lévy walks nature of topics in similarity space" . | INFORMATION SCIENCES 690 (2024) . |
| APA | Pang, Junbiao , Huang, Qingming . Towards scalable topic detection on web via simulating Lévy walks nature of topics in similarity space . | INFORMATION SCIENCES , 2024 , 690 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Semi-supervised pose estimation poses a significant challenge in computer vision. Although numerous semi-supervised classification techniques have been developed, they often rely on confidence scores to assess the quality of pseudo-labels, a feat that is challenging to achieve in pose estimation tasks. In pose estimation, for instance, confidence merely indicates the likelihood of a specific location on the heatmap being a keypoint, rather than the overall prediction quality. To address this issue, this paper introduces an ensemble framework leveraging diverse student models to evaluate the credibility of pseudo-labels by assessing their consistency across multiple models. Specifically, within a double-mean-teacher framework, we create two distinct student models (DS) to encourage two teacher models to generate distinct decision boundaries for the same sample. Experimental results demonstrate the effectiveness of our approach in enhancing semi-supervised pose estimation performance across three datasets.
关键词 ：
Ensemble Learning Ensemble Learning 2D Pose Estimation 2D Pose Estimation Semi-supervised Learning Semi-supervised Learning
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Wu, Jiaqi , Pang, Junbiao , Huang, Qingming . Ensemble of Distinct Students for SSL 2D Pose Estimation [J]. | 2024 2ND ASIA CONFERENCE ON COMPUTER VISION, IMAGE PROCESSING AND PATTERN RECOGNITION, CVIPPR 2024 , 2024 . |
| MLA | Wu, Jiaqi 等. "Ensemble of Distinct Students for SSL 2D Pose Estimation" . | 2024 2ND ASIA CONFERENCE ON COMPUTER VISION, IMAGE PROCESSING AND PATTERN RECOGNITION, CVIPPR 2024 (2024) . |
| APA | Wu, Jiaqi , Pang, Junbiao , Huang, Qingming . Ensemble of Distinct Students for SSL 2D Pose Estimation . | 2024 2ND ASIA CONFERENCE ON COMPUTER VISION, IMAGE PROCESSING AND PATTERN RECOGNITION, CVIPPR 2024 , 2024 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Organizing interesting webpages into hot topics is one of key steps to understand the trends of multimodal web data. A state-of-the-art solution is firstly to organize webpages into a large volume of multi-granularity topic candidates; hot topics are further identified by estimating their interestingness. However, these topic candidates contain a large number of fragments of hot topics due to both the inefficient feature representations and the unsupervised topic generation. This paper proposes a bundling-refining approach to mine more complete hot topics from fragments. Concretely, the bundling step organizes the fragment topics into coarse topics; next, the refining step proposes a submodular-based method to refine coarse topics in a scalable approach. The propose unconventional method is simple, yet powerful by leveraging submodular optimization, our approach outperforms the traditional ranking methods which involve the careful design and complex steps. Extensive experiments demonstrate that the proposed approach surpasses the state-of-the-art method (i.e. , latent Poisson deconvolution Pang et al. (2016)) 20% accuracy and 10% one on two public data sets, respectively.
关键词 ：
Submodularity Submodularity Poisson deconvolution Poisson deconvolution Scalability Scalability Hot topic detection Hot topic detection Random walks Random walks
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Pang, Junbiao , Hu, Anjing , Huang, Qingming . Bundle fragments into a whole: Mining more complete clusters via submodular selection of interesting webpages for web topic detection [J]. | EXPERT SYSTEMS WITH APPLICATIONS , 2024 , 260 . |
| MLA | Pang, Junbiao 等. "Bundle fragments into a whole: Mining more complete clusters via submodular selection of interesting webpages for web topic detection" . | EXPERT SYSTEMS WITH APPLICATIONS 260 (2024) . |
| APA | Pang, Junbiao , Hu, Anjing , Huang, Qingming . Bundle fragments into a whole: Mining more complete clusters via submodular selection of interesting webpages for web topic detection . | EXPERT SYSTEMS WITH APPLICATIONS , 2024 , 260 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Semi-supervised learning (SSL) poses a significant practical challenge in the field of computer vision. Pseudo Labeling methods (PL methods), as representative SSL techniques, obtain the State Of The Art (SOTA) performances in SSL. However, the error accumulation phenomenon that easily occurs during their self-training process results in high bias and variance in pseudo-labels, further hindering effective model training. To overcome this issue, we propose a feature-based perturbation method for ensemble learning method to make it more effective and efficient in SSL. By perturbing the features input to each prediction head within a multi-head ensemble structure, the method reduces the prediction correlation among prediction heads, thereby enhancing ensemble gain. It is worth emphasizing that the proposed method is highly generalizable and can be easily extended to arbitrary SSL frameworks. Experimental data demonstrate that our method outperforms the current state-of-the-art techniques on the CIFAR10 dataset and significantly improves the quality of pseudo-labels.
关键词 ：
Ensemble Learning Ensemble Learning Semi-supervised Learning Semi-supervised Learning Classification Classification
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Wu, Jiaqi , Pang, Junbiao , Huang, Qingming . Feature-based Perturbation Makes a Better Ensemble Learning for SSL Classification [J]. | 2024 2ND ASIA CONFERENCE ON COMPUTER VISION, IMAGE PROCESSING AND PATTERN RECOGNITION, CVIPPR 2024 , 2024 . |
| MLA | Wu, Jiaqi 等. "Feature-based Perturbation Makes a Better Ensemble Learning for SSL Classification" . | 2024 2ND ASIA CONFERENCE ON COMPUTER VISION, IMAGE PROCESSING AND PATTERN RECOGNITION, CVIPPR 2024 (2024) . |
| APA | Wu, Jiaqi , Pang, Junbiao , Huang, Qingming . Feature-based Perturbation Makes a Better Ensemble Learning for SSL Classification . | 2024 2ND ASIA CONFERENCE ON COMPUTER VISION, IMAGE PROCESSING AND PATTERN RECOGNITION, CVIPPR 2024 , 2024 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Objectives: In pose estimation, semi-supervised learning is a crucial approach to overcome the lack of information problem of labeled data. However, for semi-supervised learning, the insufficient number of labeled samples also severely affects its functionality. The fewer labeled the data, the less stable the prediction. Deep ensemble is a good way to improve model accuracy and stability. However, the training time of model ensemble is long and the resource consumption is high, so it cannot be applied in many practical scenarios. Therefore, the methods we propose the Decomposed Channel based Multi-Stream Ensemble (DCMSE) network, which can extend a single model to a stream-ensemble structure and generate the ensemble prediction to solve the large variance of prediction from the lack of labeled data, and improve the performance. The Channel Deconstruction and Ensembling (CDE) module makes the network benefits from both diversity and commonality by implementing ensemble without increasing the size of parameters. The output features are split into two parts, common-channels and private-channels. In feature sampling, on the one hand, common channels can provide commonality between streams. On the other hand, private channels can provide diversity for each stream and avoid homogenization of the predictions for each stream. Both diversity and commonality allow the network to not only gain in the ensemble of streams, but also improve the prediction accuracy of each stream itself. Results: Moreover, we propose mean-stream consistency constraints and cross-stack consistency constraints to obtain gains from unlabeled data. The Mean-Stream (MS) consistency constraint uses multi-stream ensemble prediction to additionally supervise each stream. Based on the characteristics of the Stacked Hourglass model, the Cross-Stage consistency constraint (CS) uses the forecasting results of later stages to supervise the forecasting of previous stages from the perspective of stages. Conclusion: Our approach achieves better results than SOTAs on the FLIC and Openfield-Pranav and our Sniffing data-set. Specifically, on the MSE, our method achieves at least 0.88, 0.13, and 0.08 improvements over the SOTA method on the FLIC, Openfield-Pranav, and our Sniffing datasets, respectively.
关键词 ：
Multi -Stream Ensemble Multi -Stream Ensemble Openfield-Pranav Openfield-Pranav CDE module CDE module DCMSE network DCMSE network UDA-AP UDA-AP
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Wu, Jiaqi , Pang, Junbiao , Huang, Qingming . Decomposed channel based Multi-Stream Ensemble: Improving consistency targets in semi-supervised 2D pose estimation [J]. | JOURNAL OF KING SAUD UNIVERSITY SCIENCE , 2024 , 36 (3) . |
| MLA | Wu, Jiaqi 等. "Decomposed channel based Multi-Stream Ensemble: Improving consistency targets in semi-supervised 2D pose estimation" . | JOURNAL OF KING SAUD UNIVERSITY SCIENCE 36 . 3 (2024) . |
| APA | Wu, Jiaqi , Pang, Junbiao , Huang, Qingming . Decomposed channel based Multi-Stream Ensemble: Improving consistency targets in semi-supervised 2D pose estimation . | JOURNAL OF KING SAUD UNIVERSITY SCIENCE , 2024 , 36 (3) . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
Scene graph generation provides high-order semantic information by understanding the objects and their relations in images. In order to improve the performance of scene graph generation, context fusion has been widely used in scene graph generation tasks, LSTM and Vision-Transformer are commonly used fusion modules. Both LSTM and Vision-Transformer realize context fusion by stacking multiple basic units, which needs to learn a large number of parameters of the units. However, the model computational efficiency of scene graph generation as a mid-level semantic understanding task to support downstream tasks is crucial. To simplify the context fusion computation, this paper proposes ASCF-Net (Augmented Spatial Context Fusion Network) which computes the spatial context of designated object by searching the nearest neighbor objects with high relevance and strengthens the context with random noise. Without learning parameters, the above computational process essentially simulates the attention mechanism. Experiments on VG dataset show that ASCF-Net uses 15.26% of the parameters of Bi-LSTM and 13.34% of the parameters of Vision-Transformer for context fusion based on the same baseline and achieves higher performance than using the two fusion modules. At the same time, ASCF-Net uses simple fusion module to obtain competitive results on VG dataset compared with the mainstream scene generation models.
关键词 ：
Scene graph generation Scene graph generation VG dataset VG dataset Spatial nearest neighbor fusion Spatial nearest neighbor fusion Lightweight contextual module Lightweight contextual module
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | Xu, Hongbo , Wang, LiChun , Xu, Kai et al. Augmented Spatial Context Fusion Network for Scene Graph Generation [J]. | 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN , 2023 . |
| MLA | Xu, Hongbo et al. "Augmented Spatial Context Fusion Network for Scene Graph Generation" . | 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN (2023) . |
| APA | Xu, Hongbo , Wang, LiChun , Xu, Kai , Fu, Fangyu , Yin, Baocai , Huang, Qingming . Augmented Spatial Context Fusion Network for Scene Graph Generation . | 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN , 2023 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明涉及一种面向食品安全的多模态人机交互方法和系统、电子设备及存储介质。该方法包括：获取用于生成多模态食品安全知识图谱的相关多模态数据源；针对所述多模态数据源，利用文档处理方法、图像识别工具以及知识抽取工具抽取多模态数据的信息，获得多模态食品安全知识；基于所述食品安全知识，生成所述多模态食品安全知识图谱；以及构建多模态人机交互系统，并基于所述多模态食品安全知识图谱实现对多模态数据的人机交互。本发明将现有的多模态食品安全数据整理并生成食品安全知识图谱，实现针对多模态数据的人机交互，能够更好的展示食品安全信息，从而替代食品安全领域专家的知识，实现食品安全领域的智能化。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 吕龙龙 , 张永恒 , 庞俊彪 et al. 面向食品安全的多模态人机交互方法和系统、设备及介质 : CN202110969283.0[P]. | 2021-08-23 . |
| MLA | 吕龙龙 et al. "面向食品安全的多模态人机交互方法和系统、设备及介质" : CN202110969283.0. | 2021-08-23 . |
| APA | 吕龙龙 , 张永恒 , 庞俊彪 , 黄庆明 , 尹宝才 . 面向食品安全的多模态人机交互方法和系统、设备及介质 : CN202110969283.0. | 2021-08-23 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明实施例提供一种路面裂缝检测方法、装置、电子设备及介质；该方法包括采集道路的路面图像；对所述路面图像进行预处理，得到分辨率梯度变化的多个输入图像；将所述多个输入图像输入预先训练的路面裂缝检测模型，得到计算结果；其中，所述路面裂缝检测模型是基于样本路面图像和所述样本路面图像的裂缝标记数据训练得到的，所述路面裂缝检测模型包括多个阶段，每个阶段间进行多次多尺度融合；根据所述路面裂缝检测模型的计算结果，输出检测结果。本发明实施例通过输入分辨率梯度变化的多个输入图像，使用具有多尺度融合结构的路面裂缝检测模型，实现了对复杂情况下的路面裂缝检测，减弱了噪声影响，提高了检测精度。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 曾君 , 庞俊彪 , 李培育 et al. 路面裂缝检测方法、装置、电子设备及存储介质 : CN202011454642.0[P]. | 2020-12-10 . |
| MLA | 曾君 et al. "路面裂缝检测方法、装置、电子设备及存储介质" : CN202011454642.0. | 2020-12-10 . |
| APA | 曾君 , 庞俊彪 , 李培育 , 段立娟 , 黄庆明 . 路面裂缝检测方法、装置、电子设备及存储介质 : CN202011454642.0. | 2020-12-10 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
本发明提供一种城市交通动态知识图谱的构建方法及装置，方法包括：根据城市交通站点的地点节点以及地点节点属性特征，确定地点节点关系模型；根据预设采样周期获取的地点节点、地点节点属性特征以及地点节点关系模型，构建城市交通动态知识图谱；其中，地点节点属性特征包括：地点节点兴趣点属性特征、地点节点社会事件属性特征、地点节点路链交通属性特征以及地点节点交通属性特征。所述装置用于执行上述方法。本发明提供的城市交通动态知识图谱的构建方法及装置，通过构建城市交通动态知识图谱，能够提高知识图谱的动态特征，更准确的对交通变化进行预测，提高城市交通服务。
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| GB/T 7714 | 庞俊彪 , 王哲焜 , 吕龙龙 et al. 城市交通动态知识图谱的构建方法及装置 : CN202011364436.0[P]. | 2020-11-27 . |
| MLA | 庞俊彪 et al. "城市交通动态知识图谱的构建方法及装置" : CN202011364436.0. | 2020-11-27 . |
| APA | 庞俊彪 , 王哲焜 , 吕龙龙 , 黄庆明 , 尹宝才 . 城市交通动态知识图谱的构建方法及装置 : CN202011364436.0. | 2020-11-27 . |
| 导入链接 | NoteExpress RIS BibTex |
摘要 ：
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.
关键词 ：
Poisson deconvolution Poisson deconvolution sparsity sparsity Web topic detection Web topic detection submodularity submodularity prototype learning (PL) prototype learning (PL) topic interpretation topic interpretation
引用：
复制并粘贴一种已设定好的引用格式，或利用其中一个链接导入到文献管理软件中。
| 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 . |
| 导入链接 | NoteExpress RIS BibTex |
导出
| 数据： |
选中 到 |
| 格式： |
