Institution
Hefei University of Technology
Education•Hefei, China•
About: Hefei University of Technology is a education organization based out in Hefei, China. It is known for research contribution in the topics: Computer science & Microstructure. The organization has 28093 authors who have published 24935 publications receiving 324989 citations.
Papers published on a yearly basis
Papers
More filters
••
TL;DR: This paper investigates how to establish the relationship between semantic concepts based on the large-scale realworld click data from image commercial engine, which is a challenging topic because the click data suffers from the noise such as typos.
Abstract: In this paper, we investigate how to establish the relationship between semantic concepts based on the large-scale real-world click data from image commercial engine, which is a challenging topic because the click data suffers from the noise such as typos, the same concept with different queries, etc. We first define five specific relationships between concepts. We then extract some concept relationship features in textual and visual domain to train the concept relationship models. The relationship of each pair of concepts will thus be classified into one of the five special relationships. We study the efficacy of the conceptual relationships by applying them to augment imperfect image tags, i.e., improve representative power. We further employ a sophisticated hashing approach to transform augmented image tags into binary codes, which are subsequently used for content-based image retrieval task. Experimental results on NUS-WIDE dataset demonstrate the superiority of our proposed approach as compared to state-of-the-art methods.
100 citations
••
TL;DR: The successful incorporation of an IrIII photoredox catalyst and a NiII cross-coupling catalyst into a stable Zr12 MOF to efficiently catalyze C-S bond formation between various aryl iodides and thiols is reported.
Abstract: Metal-organic frameworks (MOFs) have been extensively used for single-site catalysis and light harvesting, but their application in multicomponent photocatalysis is unexplored. We report here the successful incorporation of an IrIII photoredox catalyst and a NiII cross-coupling catalyst into a stable Zr12 MOF, Zr12 -Ir-Ni, to efficiently catalyze C-S bond formation between various aryl iodides and thiols. The proximity of the IrIII and NiII catalytic components to each other (ca. 0.6 nm) in Zr12 -Ir-Ni greatly facilitates electron and thiol radical transfers from Ir to Ni centers to reach a turnover number of 38 500, an order of magnitude higher than that of its homogeneous counterpart. This work highlights the opportunity in merging photoredox and organometallic catalysts in MOFs to effect challenging organic transformations.
100 citations
••
TL;DR: By employing the finite-time control method, the consensus control algorithm for higher-order multiagent systems is designed and can guarantee that the state consensus is achieved in a finite time.
Abstract: By employing the finite-time control method, the consensus control algorithm for higher-order multiagent systems is designed in this paper. Under a neighbor-based rule, a higher-order finite-time consensus algorithm is explicitly constructed, which only uses local information. The finite-time consensus control algorithm can guarantee that the state consensus is achieved in a finite time. In addition, for multiagent systems having a leader-following structure, the consensus algorithm is also designed. Finally, two examples are presented to show the effectiveness.
100 citations
••
TL;DR: A review of the recent developments in ESPI systems for 3D displacement and strain measurement can be found in this article, where the basic theory, a brief derivation and different optical layouts are presented.
Abstract: Three dimensional(3D) displacements, which can be translated further into 3D strain, are key parameters for design, manufacturing and quality control. Using different optical setups, phase-shift methods, and algorithms, several different 3D electronic speckle pattern interferometry(ESPI) systems for displacement and strain measurements have been achieved and commercialized. This paper provides a review of the recent developments in ESPI systems for 3D displacement and strain measurement. After an overview of the fundamentals of ESPI theory, temporal phase-shift, and spatial phase-shift techniques, 3D deformation measurements by the temporal phase-shift ESPI system, which is suited well for static measurement, and by the spatial phase-shift ESPI system, which is particularly useful for dynamic measurement, are discussed. For each method, the basic theory, a brief derivation and different optical layouts are presented. The state of art application, potential and limitation of the ESPI systems are shown and demonstrated.
100 citations
••
TL;DR: The proposed framework utilizes two state-of-the-art ConvNets, i.e., the very deep spatial net (VGGNet) and the temporal net from Two-Stream convolutional layers, and proposes the new Line pooling strategy, which can speed up the extraction of feature and achieve the comparable performance of the Trajectory pooling.
Abstract: Deep ConvNets have shown their good performance in image classification tasks. However, there still remains problems in deep video representations for action recognition. On one hand, current video ConvNets are relatively shallow compared with image ConvNets, which limits their capability of capturing the complex video action information; on the other hand, temporal information of videos is not properly utilized to pool and encode the video sequences. Toward these issues, in this paper we utilize two state-of-the-art ConvNets, i.e., the very deep spatial net (VGGNet [1] ) and the temporal net from Two-Stream ConvNets [2] , for action representation. The convolutional layers and the proposed new layer, called frame-diff layer, are extracted and pooled with two temporal pooling strategies: Trajectory pooling and Line pooling. The pooled local descriptors are then encoded with vector of locally aggregated descriptors (VLAD) [3] to form the video representations. In order to verify the effectiveness of the proposed framework, we conduct experiments on UCF101 and HMDB51 data sets. It achieves accuracy of 92.08% on UCF101, which is the state-of-the-art, and the accuracy of 65.62% on HMDB51, which is comparable to the state-of-the-art. In addition, we propose the new Line pooling strategy, which can speed up the extraction of feature and achieve the comparable performance of the Trajectory pooling.
100 citations
Authors
Showing all 28292 results
Name | H-index | Papers | Citations |
---|---|---|---|
Yi Chen | 217 | 4342 | 293080 |
Xiang Zhang | 154 | 1733 | 117576 |
Jun Chen | 136 | 1856 | 77368 |
Shuicheng Yan | 123 | 810 | 66192 |
Yang Li | 117 | 1319 | 63111 |
Jian Liu | 117 | 2090 | 73156 |
Han-Qing Yu | 105 | 718 | 39735 |
Jianqiao Ye | 101 | 962 | 42647 |
Wei Liu | 96 | 1538 | 42459 |
Wei Zhou | 93 | 1640 | 39772 |
Panos M. Pardalos | 87 | 1207 | 39512 |
Zhong Chen | 80 | 1000 | 28171 |
Yong Zhang | 78 | 665 | 36388 |
Rong Cao | 76 | 568 | 21747 |
Qian Zhang | 76 | 891 | 25517 |