955 Hits in 1.9 sec

AHINE: Adaptive Heterogeneous Information Network Embedding [article]

Yucheng Lin, Xiaoqing Yang, Zang Li, Jieping Ye
2019 arXiv   pre-print
Network embedding is an effective way to solve the network analytics problems such as node classification, link prediction, etc. It represents network elements using low dimensional vectors such that the graph structural information and properties are maximumly preserved. Many prior works focused on embeddings for networks with the same type of edges or vertices, while some works tried to generate embeddings for heterogeneous network using mechanisms like specially designed meta paths. In this
more » ... aper, we propose two novel algorithms, GHINE (General Heterogeneous Information Network Embedding) and AHINE (Adaptive Heterogeneous Information Network Embedding), to compute distributed representations for elements in heterogeneous networks. Specially, AHINE uses an adaptive deep model to learn network embeddings that maximizes the likelihood of preserving the relationship chains between non-adjacent nodes. We apply our embeddings to a large network of points of interest (POIs) and achieve superior accuracy on some prediction problems on a ride-hailing platform. In addition, we show that AHINE outperforms state-of-the-art methods on a set of learning tasks on public datasets, including node labelling and similarity ranking in bibliographic networks.
arXiv:1909.01087v1 fatcat:i63hwokwbrbcxa7yo25xmpdjru

Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network [article]

Zhikang Zou, Xiaoye Qu, Pan Zhou, Shuangjie Xu, Xiaoqing Ye, Wenhao Wu, Jin Ye
2021 arXiv   pre-print
(TS: Target Supervision) Method TS MAE MSE MORR [7] yes 3.15 15.7 ConvLSTM-nt [48] yes 2.53 11.2 MCNN [51] yes 2.24 8.5 FA [6] semi 7.47 - HGP [49] semi 4.36 - GPTL [31] semi  ...  (TS: Target Supervision) Method TS MAE MSE MCNN [51] yes 26.4 41.3 CP-CNN [42] yes 20.1 30.1 IG-CNN [38] yes 13.6 21.1 Cycle GAN [52] syn 25.4 39.7 SE Cycle GAN [46] syn 19.9 28.3  ... 
arXiv:2107.12858v1 fatcat:xheysldadrh4hefguvwncnrzuq

Canonical basis for type A4

Yuwang Hu, Jiachen Ye, Xiaoqing Yue
2003 Journal of Algebra  
The global crystal basis or canonical basis plays an important role in the theory of the quantum groups and their representations. The tight monomials are the simplest elements in the canonical basis. Based on Lusztig and Xi's work, the regions of tight monomials in quantized enveloping algebra of type A 4 are determined in this paper.
doi:10.1016/s0021-8693(03)00066-8 fatcat:6rxmtlaxrvbn7muwpg3nbf5xs4

Analysis of the Temporal and Spatial Distribution of Extreme Climate Indices in Central China

Yan Li, Junfang Zhao, Rui Miao, Yan Huang, Xiaoqing Fan, Xiaoqing Liu, Xueqi Wang, Ye Wang, Yuyang Shen
2022 Sustainability  
Using the daily precipitation and temperature data of 101 meteorological stations in four provinces of central China (Henan, Hubei, Hunan, Jiangxi) from 1988 to 2017, we analyzed the temporal and spatial dynamics and periodicity of nine extreme climate indices in central China, using the predefined methods for analyzing extreme climate events, such as a M-K test, a linear trend analysis, and a wavelet analysis. The extreme climate characteristics and changes in central China in the past 30
more » ... were revealed. The results showed that the CSDI was significantly reduced linearly at a rate of −0.19 d/10a, and the WSDI and TXx increased significantly at rates of 0.25 d/10a and 0.30℃/10a, respectively. The CDD decreased significantly at a rate of −1.67 d/10a. The duration of extreme low-temperature and drought events in central China showed a gradual shortening, while the duration of extreme high-temperature events and the high-temperature values increased. The results of the abrupt climate change test showed that some extreme climate indices in central China had significant abrupt climate changes after 2000. Analyzing the cyclicality of each index, it was determined that the extreme climate index in central China had a significant cyclical change every 2–4 years, and the change was more notable after 2000. Analyzing the spatial distribution of the extreme climate indices, it was determined that Jiangxi had the longest duration of all high-temperature events, and was the largest and longest of events of extreme precipitation. It was also determined that the Jiangxi region was at greater risk of extreme climate events in central China. The results of this study can provide a scientific basis for climate change trends, local disaster prevention, and mitigation management in central China.
doi:10.3390/su14042329 fatcat:2x2w3f54pzd3lc6uqtplw2jn5y

Political Cartoons in Commercial Advertising in Early Twentieth Century China

Xiaoqing Ye
2009 Asian Social Science  
If someone was accused of being 'unhygienic', it did not only mean that he didn't wash, but also that he was uneducated and backward (Ye, 2003:52) .  ...  Zhong answered in English: "Yes, I like it." (Rao and Yang, 2004:343 ). An educated, smart and desirable young man should certainly know how to look after his eyesight.  ... 
doi:10.5539/ass.v5n10p62 fatcat:weud5thodbaldfcv736vxvr7j4

An Attention-based Graph Neural Network for Heterogeneous Structural Learning [article]

Huiting Hong, Hantao Guo, Yucheng Lin, Xiaoqing Yang, Zang Li, Jieping Ye
2019 arXiv   pre-print
In this paper, we focus on graph representation learning of heterogeneous information network (HIN), in which various types of vertices are connected by various types of relations. Most of the existing methods conducted on HIN revise homogeneous graph embedding models via meta-paths to learn low-dimensional vector space of HIN. In this paper, we propose a novel Heterogeneous Graph Structural Attention Neural Network (HetSANN) to directly encode structural information of HIN without meta-path
more » ... achieve more informative representations. With this method, domain experts will not be needed to design meta-path schemes and the heterogeneous information can be processed automatically by our proposed model. Specifically, we implicitly represent heterogeneous information using the following two methods: 1) we model the transformation between heterogeneous vertices through a projection in low-dimensional entity spaces; 2) afterwards, we apply the graph neural network to aggregate multi-relational information of projected neighborhood by means of attention mechanism. We also present three extensions of HetSANN, i.e., voices-sharing product attention for the pairwise relationships in HIN, cycle-consistency loss to retain the transformation between heterogeneous entity spaces, and multi-task learning with full use of information. The experiments conducted on three public datasets demonstrate that our proposed models achieve significant and consistent improvements compared to state-of-the-art solutions.
arXiv:1912.10832v1 fatcat:trv7zyezzjf2dc6gr7xs4ukeoi

Contextualized Attitude Change [chapter]

Bertram Gawronski, Robert J. Rydell, Jan De Houwer, Skylar M. Brannon, Yang Ye, Bram Vervliet, Xiaoqing Hu
2018 Advances in Experimental Social Psychology  
Figure adapted from Ye, Tong, Chiu, and Gawronski (2017); reprinted with permission.  ...  Figure adapted from Gawronski, Ye, Rydell, and De Houwer (2014); reprinted with permission.  ... 
doi:10.1016/bs.aesp.2017.06.001 fatcat:5ikc2xu5rbbw5jqwgvnpmfxq6q

Meta Graph Attention on Heterogeneous Graph with Node-Edge Co-evolution [article]

Yucheng Lin, Huiting Hong, Xiaoqing Yang, Xiaodi Yang, Pinghua Gong, Jieping Ye
2020 arXiv   pre-print
Graph neural networks have become an important tool for modeling structured data. In many real-world systems, intricate hidden information may exist, e.g., heterogeneity in nodes/edges, static node/edge attributes, and spatiotemporal node/edge features. However, most existing methods only take part of the information into consideration. In this paper, we present the Co-evolved Meta Graph Neural Network (CoMGNN), which applies meta graph attention to heterogeneous graphs with co-evolution of
more » ... and edge states. We further propose a spatiotemporal adaption of CoMGNN (ST-CoMGNN) for modeling spatiotemporal patterns on nodes and edges. We conduct experiments on two large-scale real-world datasets. Experimental results show that our models significantly outperform the state-of-the-art methods, demonstrating the effectiveness of encoding diverse information from different aspects.
arXiv:2010.04554v1 fatcat:rp6olsi3xjayhfcjp5ycggp53y

An Efficient Local Search for the Feedback Vertex Set Problem

Zhiqiang Zhang, Ansheng Ye, Xiaoqing Zhou, Zehui Shao
2013 Algorithms  
Inspired by many deadlock detection applications, the feedback vertex set is defined as a set of vertices in an undirected graph, whose removal would result in a graph without cycle. The Feedback Vertex Set Problem, known to be NP-complete, is to search for a feedback vertex set with the minimal cardinality to benefit the deadlock recovery. To address the issue, this paper presents NewkLS FVS(LS, local search; FVS, feedback vertex set), a variable depth-based local search algorithm with a
more » ... ized scheme to optimize the efficiency and performance. Experimental simulations are conducted to compare the algorithm with recent metaheuristics, and the computational results show that the proposed algorithm can outperform the other state-of-art algorithms and generate satisfactory solutions for most DIMACSbenchmarks.
doi:10.3390/a6040726 fatcat:k4mytvtmbreelngyitw6yd6jcq

Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection [article]

Li Wang, Liang Du, Xiaoqing Ye, Yanwei Fu, Guodong Guo, Xiangyang Xue, Jianfeng Feng, Li Zhang
2021 arXiv   pre-print
The objective of this paper is to learn context- and depth-aware feature representation to solve the problem of monocular 3D object detection. We make following contributions: (i) rather than appealing to the complicated pseudo-LiDAR based approach, we propose a depth-conditioned dynamic message propagation (DDMP) network to effectively integrate the multi-scale depth information with the image context;(ii) this is achieved by first adaptively sampling context-aware nodes in the image context
more » ... d then dynamically predicting hybrid depth-dependent filter weights and affinity matrices for propagating information; (iii) by augmenting a center-aware depth encoding (CDE) task, our method successfully alleviates the inaccurate depth prior; (iv) we thoroughly demonstrate the effectiveness of our proposed approach and show state-of-the-art results among the monocular-based approaches on the KITTI benchmark dataset. Particularly, we rank 1^st in the highly competitive KITTI monocular 3D object detection track on the submission day (November 16th, 2020). Code and models are released at
arXiv:2103.16470v1 fatcat:3zikeoajn5fwjf3xz6oipoopre

Weakly Supervised Deep Depth Prediction Leveraging Ground Control Points for Guidance

Liang Du, Jiamao Li, Xiaoqing Ye, Xiaolin Zhang
2019 IEEE Access  
Despite the tremendous progress made in learning-based depth prediction, most methods rely heavily on large amounts of dense ground-truth depth data for training. To solve the tradeoff between the labeling cost and precision, we propose a novel weakly supervised approach, namely, the Guided-Net, by incorporating robust ground control points for guidance. By exploiting the guidance from ground control points, disparity edge gradients, and image appearance constraints, our improved network with
more » ... formable convolutional layers is empowered to learn in a more efficient way. The experiments on the KITTI, Cityscapes, and Make3D datasets demonstrate that the proposed method yields a performance superior to that of the existing weakly supervised approaches and achieves results comparable to those of the semisupervised and supervised frameworks. INDEX TERMS Computer vision, stereo image processing, stereo vision, weakly supervised learning. 5736 2169-3536
doi:10.1109/access.2018.2885773 fatcat:7pmknfedojbzxptvmegjotrb5q

In Situ TEM Studies of Catalysts Using Windowed Gas Cells

Fan Ye, Mingjie Xu, Sheng Dai, Peter Tieu, Xiaobing Ren, Xiaoqing Pan
2020 Catalysts  
For decades, differentially pumped environmental transmission electron microscopy has been a powerful tool to study dynamic structural evolution of catalysts under a gaseous environment. With the advancement of micro-electromechanical system-based technologies, windowed gas cell became increasingly popular due to its ability to achieve high pressure and its compatibility to a wide range of microscopes with minimal modification. This enables a series of imaging and analytical technologies such
more » ... atomic resolution imaging, spectroscopy, and operando, revealing details that were unprecedented before. By reviewing some of the recent work, we demonstrate that the windowed gas cell has the unique ability to solve complicated catalysis problems. We also discuss what technical difficulties need to be addressed and provide an outlook for the future of in situ environmental transmission electron microscopy (TEM) technologies and their application to the field of catalysis development.
doi:10.3390/catal10070779 fatcat:wr3usugjr5cw5ohvcbefztidsu

SemFlow: Semantic-driven Interpolation for Large Displacement Optical Flow

Xianshun Wang, Dongchen Zhu, Yanqing Liu, Xiaoqing Ye, Jiamao Li, Xiaolin Zhang
2019 IEEE Access  
XIAOQING YE received the B.S. degree from Wuhan University, China, in 2014.  ... 
doi:10.1109/access.2019.2911021 fatcat:f4tbdn3mb5bwrag2yifyjy4tma

ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection [article]

Zhenbo Xu, Wei Zhang, Xiaoqing Ye, Xiao Tan, Wei Yang, Shilei Wen, Errui Ding, Ajin Meng, Liusheng Huang
2020 arXiv   pre-print
3D object detection is an essential task in autonomous driving and robotics. Though great progress has been made, challenges remain in estimating 3D pose for distant and occluded objects. In this paper, we present a novel framework named ZoomNet for stereo imagery-based 3D detection. The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes. To further exploit the abundant texture cues in RGB images for more accurate
more » ... arity estimation, we introduce a conceptually straight-forward module -- adaptive zooming, which simultaneously resizes 2D instance bounding boxes to a unified resolution and adjusts the camera intrinsic parameters accordingly. In this way, we are able to estimate higher-quality disparity maps from the resized box images then construct dense point clouds for both nearby and distant objects. Moreover, we introduce to learn part locations as complementary features to improve the resistance against occlusion and put forward the 3D fitting score to better estimate the 3D detection quality. Extensive experiments on the popular KITTI 3D detection dataset indicate ZoomNet surpasses all previous state-of-the-art methods by large margins (improved by 9.4% on APbv (IoU=0.7) over pseudo-LiDAR). Ablation study also demonstrates that our adaptive zooming strategy brings an improvement of over 10% on AP3d (IoU=0.7). In addition, since the official KITTI benchmark lacks fine-grained annotations like pixel-wise part locations, we also present our KFG dataset by augmenting KITTI with detailed instance-wise annotations including pixel-wise part location, pixel-wise disparity, etc.. Both the KFG dataset and our codes will be publicly available at
arXiv:2003.00529v1 fatcat:kfcz5eoqvnaflhhlfqt6mkeb7a

Input-Output Example-Guided Data Deobfuscation on Binary

Yujie Zhao, Zhanyong Tang, Guixin Ye, Xiaoqing Gong, Dingyi Fang, Zhiyuan Tan
2021 Security and Communication Networks  
Data obfuscation is usually used by malicious software to avoid detection and reverse analysis. When analyzing the malware, such obfuscations have to be removed to restore the program into an easier understandable form (deobfuscation). The deobfuscation based on program synthesis provides a good solution for treating the target program as a black box. Thus, deobfuscation becomes a problem of finding the shortest instruction sequence to synthesize a program with the same input-output behavior as
more » ... the target program. Existing work has two limitations: assuming that obfuscated code snippets in the target program are known and using a stochastic search algorithm resulting in low efficiency. In this paper, we propose fine-grained obfuscation detection for locating obfuscated code snippets by machine learning. Besides, we also combine the program synthesis and a heuristic search algorithm of Nested Monte Carlo Search. We have applied a prototype implementation of our ideas to data obfuscation in different tools, including OLLVM and Tigress. Our experimental results suggest that this approach is highly effective in locating and deobfuscating the binaries with data obfuscation, with an accuracy of at least 90.34%. Compared with the state-of-the-art deobfuscation technique, our approach's efficiency has increased by 75%, with the success rate increasing by 5%.
doi:10.1155/2021/4646048 fatcat:hueuiilbmvdb3ncyzwz6rwg5wu
« Previous Showing results 1 — 15 out of 955 results