|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Glance Nets – efficient convolutional neural networks with adaptive hard example mining显示文摘Dear editor,Deep convolutional neural networks (CNNs) have become the dominant approach in various computer vision tasks such as image classification [1–4]. Despite the success of CNNs, it is impeded to deploy such deep CNN models in real-time tasks due to high computational complexity. To address the problem, we propose Glance Nets with several bypasses (Figure 1). In modern CNNs, it is believed that shallow layers provide lower-level features, whereas deep layers correspond to higherlevel features. However, it is not always | Hanqing SUN Yanwei PANG | 2018 | Science China(Information Sciences)2018，61，10： | 11 |
| 2 | Research and application of methods for effectiveness evaluation of mine cooling system显示文摘Regarding the complexity and inconsistency of results in existing evaluation methods of mine cooling system, this paper clarifies the advantages, disadvantages and application of various mine cooling systems through principle analysis, and divides all the cooling systems into air-cooling, ice-cooling and water-cooling according to the transportation of cold energy. On this basis, the paper proposes a simple and efficient evaluation method for mine cooling system. The first index of this method is the air temperature at point C which is 15 m away from the return wind corner at working face. A cooling system will be judged ineligible if the air temperature at point C is above 30 °C during operation, because in this case, the combustible gases in coal will sharply overflow, inducing gas incidents. Based on the preliminary judgment of the first index, another two evaluation indexes are proposed based on the cooling ability and dehumidification of an airflow volume of 1000 m3/min at point C to evaluate the investment and operation cost of mine cooling system. This evaluation method has already been successfully applied in the cooling system design of Zhangshuanglou coal mine. | Guo Pingye Wang Yanwei Duan Mengmeng Pang Dongyang Li Nan | 2015 | International Journal of Mining Science and Technology2015，25，4： | 7 |
| 3 | Heterogeneous memory enhanced graph reasoning network for cross-modal retrieval显示文摘Cross-modal retrieval(CMR) aims to retrieve the instances of a specific modality that are relevant to a given query from another modality, which has drawn much attention because of its importance in bridging vision with language. A key to the success of CMR is to learn more discriminative and robust representations for both visual and textual instances to further reduce the heterogeneous discrepancy existing in different modalities. In this paper, we address this challenging issue by proposing a heterogeneous memory enhanced graph reasoning network, named HMGR, to connect the semantic correlations between vision and language.On the one hand, we design a novel dual-path network architecture to generate relationship enhanced global representations by employing modality-specific graph reasoning on extracted local features for each instance.In this way, the topological interdependencies of both visual and textual intra-instance local fragments are fully mined to achieve a deeper semantic understanding of the relationships between them. On the other hand,we focus on utilizing inter-instance semantic correlated knowledge to enhance the discriminability of the final learned representations, which is achieved by introducing a joint heterogeneous memory network to iteratively restore both visual and textual instance-level information. Through interacting with long-term contextual multimodal knowledge, an encouraging shared latent feature space for mitigating the heterogeneous gap across different modalities can be learned. Extensive experiments under both image-text retrieval and video-text retrieval scenarios on three benchmark datasets demonstrate the effectiveness of our proposed method. | Zhong JI Kexin CHEN Yuqing HE Yanwei PANG Xuelong LI | 2022 | Science China(Information Sciences)2022，65，7： | 4 |
| 4 | Triple discriminator generative adversarial network for zero-shot image classification显示文摘One key challenge in zero-shot classification(ZSC)is the exploration of knowledge hidden in unseen classes.Generative methods such as generative adversarial networks(GANs)are typically employed to generate the visual information of unseen classes.However,the majority of these methods exploit global semantic features while neglecting the discriminative differences of local semantic features when synthesizing images,which may lead to sub-optimal results.In fact,local semantic information can provide more discriminative knowledge than global information can.To this end,this paper presents a new triple discriminator GAN for ZSC called TDGAN,which incorporates a text-reconstruction network into a dual discriminator GAN(D2GAN),allowing to realize cross-modal mapping from text descriptions to their visual representations.The text-reconstruction network focuses on key text descriptions for aligning semantic relationships to enable synthetic visual features to effectively represent images.Sharma-Mittal entropy is exploited in the loss function to make the distribution of synthetic classes be as close as possible to the distribution of real classes.The results of extensive experiments over the Caltech-UCSD Birds-2011 and North America Birds datasets demonstrate that the proposed TDGAN method consistently yields competitive performance compared to several state-of-the-art ZSC methods. | Zhong JI Jiangtao YAN Qiang WANG Yanwei PANG Xuelong LI | 2021 | Science China(Information Sciences)2021，64，2： | 4 |
| 5 | PSC-Net:learning part spatial co-occurrence for occluded pedestrian detection显示文摘Detecting pedestrians,especially under heavy occlusion,is a challenging computer vision problem with numerous real-world applications.This paper introduces a novel approach,termed as PSC-Net,for occluded pedestrian detection.The proposed PSC-Net contains a dedicated module that is designed to explicitly capture both inter and intra-part co-occurrence information of different pedestrian body parts through a graph convolutional network(GCN).Both inter and intra-part co-occurrence information contribute towards improving the feature representation for handling varying level of occlusions,ranging from partial to severe occlusions.Our PSC-Net exploits the topological structure of pedestrian and does not require part-based annotations or additional visible bounding-box(VBB)information to learn part spatial co-occurrence.Comprehensive experiments are performed on three challenging datasets:CityPersons,Caltech,and CrowdHuman datasets.Particularly,in terms of log-average miss rates and with the same backbone and input scale as those of the state-of-the-art MGAN,the proposed PSC-Net achieves absolute gains of 4.0%and 3.4%over MGAN on the heavy occlusion subsets of CityPersons and Caltech test sets,respectively. | Jin XIE Yanwei PANG Hisham CHOLAKKAL Rao ANWER Fahad KHAN Ling SHAO | 2021 | Science China(Information Sciences)2021，64，2： | 4 |
| 6 | Efficient HOGhuman detection显示文摘 | Pang Yanwei Yuan Yuan Li Xuelong | 2011 | Signal Processing2011，91，4： | 1 |
| 7 | Deterministic Column-Based Matrix Decom- position显示文摘 | Li Xuelong Pang Yanwei | 2010 | IEEE Transactions on Knowledge and Data Engineering2010，22，1： | 1 |
| 8 | Robust CoHOG Feature Ex- traction in Human-Centered Image/Video Management System 显示文摘 | Pang Yanwei Yan He Yuan Yuan | 2012 | IEEE Transactions on Systems Man and Cybernetics Part B : Cyber- netics2012，42，2： | 1 |
| 9 | Fully affine invariant SURF for image matching显示文摘 | Yanwei Pang Wei Li Yuan Yuan Jing Pan | 2012 | Neurocomputing2012，，： | 1 |
| 10 | Fast haar transform based feature extraction for face representation and recognition显示文摘 | PANG Yanwei | | 0，，03： | 1 |
| 11 | Binary two-di-mensional PCA显示文摘 | Pang Yanwei Tao Dacheng Yuan Yuan | 2008 | IEEE Transaction on Systems Man and Cybernetics Part B2008，38，4： | 1 |
| 12 | A New Nonlinear Fea- ture Extraction Method for Face Recognition显示文摘 | Pang Yanwei Liu Zhengkai Yu Nenghai | 2006 | Neurocomputing2006，69，： | 1 |
| 13 | L1-Norm-Based 2DPCA显示文摘 | Li Xuelong Pang Yanwei | 2009 | IEEE Transaction on Systems Man andCybemetics Part B2009，40，4： | 1 |
| 14 | L1-norm-based 2DPCA显示文摘 | Li Xuelong Pang Yanwei Yuan Yuan | 2010 | IEEE Transactions on Systems Man and Cybernetics2010，40，3： | 1 |
| 15 | Efficient HOG human detection 显示文摘 | Pang Yanwei Yuan Yuan Li Xuelong | 2011 | Signal Processing2011，91，4： | 1 |
| 16 | Fast haar transform based feature extraction for face representation and recognition显示文摘 | Pang Yanwei | 2009 | IEEE Transactions on Information Forensics and Security2009，3，4： | 1 |
| 17 | Special focus on deep learning for computer vision显示文摘Deep learning-based computer vision plays an increasingly important role in developing the highperformance intelligent perception systems such as self-driving vehicles,unmanned surface vehicles,robots,intelligent human-machine interactions,and visual surveillance.However,more effort has to be done to improve the performance so that deep learning-based computer vision can satisfy the rigorous demands of the intelligent perception systems.This special focus,which will also appear in next few issues,aims at collecting new ideas about deep learning-based computer vision to improve the performance in terms of accuracy and/or efficiency. | Yanwei PANG Xiang BAI Guofeng ZHANG | 2019 | Science China(Information Sciences)2019，62，12： | 1 |
| 18 | Generalized KPCA by adaptive rules in feature space显示文摘 | PANG Yanwei WANG Lei YUAN Yuan | 2010 | International Journal of Computer Mathematics2010，87，5： | 1 |
| 19 | Binary sparse nonnegative matrix factorization显示文摘 | Yuan Yuan Li Xuelong Pang Yanwei | 2009 | IEEE Transactions on Circuits and Systems for Video Technology2009，19，5： | 1 |
| 20 | A new nonlinear feature extraction method for face recognition 显示文摘 | PANG YANWEI LIU ZHENGKAI YU NENGHAI | 2006 | Nerocomputing2006，69，79： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员