Learning Deep Patch representation for Probabilistic Graphical Model-Based Face Sketch Synthesis

International Journal of Computer Vision - Face sketch synthesis has a wide range of applications in both digital entertainment and law enforcement. State-of-the-art examplar-based methods...     

电流密度对声电沉积生物活性透钙磷石涂层结构和形貌的影响

通过声电沉积工艺在碳／碳复合材料表面制备了生物活性透钙磷石涂层，采用SEM、FFIR、XRD研究了超声场中电流密度对涂层组成结构和形貌的影响。发现在一定工艺条件下，随电流密度增加，涂层的平均晶粒尺寸减小，致密度增加；当电流密度小于l0mA／cm^2时涂层形貌为片状，l0mA／cm^2-26mA／cm^2时为粒状，32mA／cm^2时为花菜心状。且涂层中透钙磷石晶体的择优取向也发生变化，择优晶面依次为(021)、(111)、(220)。同时还讨论了涂层微观结构变化机理。     

Reciprocal bi-directional generative adversarial network for cross-modal pedestrian re-identification

To improve the accuracy of cross-modal pedestrian re-identification,a reciprocal bi-directional generative adversarial network-based method is proposed.First,we build two generative adversarial networks to generate cross-modal heterogeneous images.Second,an associated loss is designed to pull close the distribution of features in latent space during the image translation between visible and infrared images so as to help the networks generate fake heterogeneous images that have high similarity with the real images.Finally,by concatenating the original and generated heterogeneous pedestrian images into the discriminative feature extraction network,images from different modalities can be unified into a common modality,thus suppressing the cross-modal gap.Representation learning and metric learning are utilized to achieve more discriminative pedestrian features.Comparative experiments are conducted on SYSU-MM01 and RegDB datasets to analyze the accuracy with different loss functions.Compared with other state-of-the-art cross-modal pedestrian re-identification methods,the proposed method achieves a higher accuracy and stronger robustness.     

超细聚苯乙烯(PS)树脂的制备工艺研究

采用O/W型苯乙烯微乳液体系,研究了乳化剂OP-10、助乳化剂DBS、交联剂DVB等对聚苯乙烯(PS)粒径分布的影响,基于正交试验,找出了量佳微乳液体系配方。采用激光粒度仪与透射电镜(TEM)对纳米PS粒子的粒径进行了测量研究,结果表明:交联PS粒子单分散性好,大小较均匀。     

尿素－双醛淀粉胶粘剂的制备

将改性淀粉代替甲醛与尿素进行缩合反应 ,合成出全新无毒的尿素 双醛淀粉胶粘剂。讨论了双醛淀粉与尿素的反应机理 ,并对二者反应的影响因素进行概括分析     

沉积温度对微波热解CVI制备碳/碳复合材料密度及组织结构的影响

以碳毡为预制体,N2为稀释气体,甲烷为碳源前驱体,其分压为10 kPa,滞留时间为0.15 s的工艺条件下,研究了不同沉积温度对微波热解化学气相渗透(chemical vapor infiltration,CVI)工艺制备碳/碳复合材料的致密化速率、样品的体积密度及其密度均匀性的影响,并对其组织结构进行了观察.分析了沉积温度对微波热解CVI工艺制备碳/碳复合材料的密度与组织结构的变化规律.结果表明:在微波热解CVI工艺中,随着沉积温度的降低,碳毡预制体的致密化速率及最终体积密度呈现先升后降,1100 ℃沉积制备复合材料的密度均匀性最好,并呈现从内到外逐步沉积的规律.热解碳的织构主要为中等织构.     

Effect of deposition time on microstructures and growth behavior of ZrC coatings prepared by low pressure chemical vapor deposition with the Br<Subscript>2</Subscript>-Zr-C<Subscript>3</Subscript>H<Subscript>6</Subscript>-H<Subscript>2</Subscript>-Ar System

ZrC coatings were deposited on graphite substrates by low pressure chemical vapor deposition (LPCVD) with the Br₂-Zr-C₃H₆-H₂-Ar system. The effects of deposition time on the microstructures and growth behavior of ZrC coatings were investigated. ZrC coating grew in an island-layer mode. The formation of coating was dominated by the nucleation of ZrC in the initial 20 minutes, and the rapid nucleation generated a fine-grained structure of ZrC coating. When the deposition time was over 30 min, the growth of coating was dominated by that of crystals, giving a column-arranged structure. Energy dispersive X-ray spectroscopy showed that the molar ratio of carbon to zirconium was near 1:1 in ZrC coating, and X-ray photoelectron spectroscopy showed that ZrC was the main phase in coatings, accompanied by about 2.5mol% ZrO₂ minor phase.     

钛合金表面声电沉积／碱热处理法制备HA涂层研究

为了使钛合金（Ti-6Al-4V）具有生物活性，可在其表面施加生物活性羟基磷灰石（HA）涂层。对比了声电沉积法和碱热处理法实验结果，采用扫描电镜（SEM）、X射线衍射仪（XRD）、电子能谱（EDS）、傅立叶红外透射光谱（FTIR）以及划痕测试等进行了分析。结果表明，直接采用声电沉积法在钛合金表面制备的羟基磷灰石涂层，经热处理后存在龟裂剥落现象；通过碱热处理法，对钛合金基体表面进行预处理，然后，借助声电沉积法，在钛金属表面沉积了透钙磷石涂层，经热碱液处理转变成的羟基磷灰石涂层，涂层完整，未出现剥落。经进一步高温烧结处理，所制涂层仍呈片状形貌，其由部分含钠的羟基磷灰石组成，而且HA涂层破坏的临界载荷未烧结前的4．365N提高至烧结后的8．175N。     

Video archaeology: understanding video manipulation history

Facing the explosive growth of near-duplicate videos, video archaeology is quite desired to investigate the history of the manipulations on these videos. With the determination of derived videos according to the manipulations, a video migration map can be constructed with the pair-wise relationships in a set of near-duplicate videos. In this paper, we propose an improved video archaeology (I-VA) system by extending our previous work (Shen et al. 2010). The extensions include more comprehensive video manipulation detectors and improved techniques for these detectors. Specially, the detectors are used for two categories of manipulations, i.e., semantic-based manipulations and non-semantic-based manipulations. Moreover, the improved detecting algorithms are more stable. The key of I-VA is the construction of a video migration map, which represents the history of how near-duplicate videos have been manipulated. There are various applications based on the proposed I-VA system, such as better understanding of the meaning and context conveyed by the manipulated videos, improving current video search engines by better presentation based on the migration map, and better indexing scheme based on the annotation propagation. The system is tested on a collection of 12,790 videos and 3,481 duplicates. The experimental results show that I-VA can discover the manipulation relation among the near-duplicate videos effectively.     

Image categorization: Graph edit distance+edge direction histogram

This paper presents a novel algorithm for computing graph edit distance (GED) in image categorization. This algorithm is purely structural, i.e., it needs only connectivity structure of the graph and does not draw on node or edge attributes. There are two major contributions: (1) Introducing edge direction histogram (EDH) to characterize shape features of images. It is shown that GED can be employed as distance of EDHs. This algorithm is completely independent on cost function which is difficult to be defined exactly. (2) Computing distance of EDHs with earth mover distance (EMD) which takes neighborhood bins into account so as to compute distance of EDHs correctly. A set of experiments demonstrate that the newly presented algorithm is available for classifying and clustering images and is immune to the planar rotation of images. Compared with GED from spectral seriation, our algorithm can capture the structure change of graphs better and consume 12.79% time used by the former one. The average classification rate is 5% and average clustering rate is 25% higher than the spectral seriation method.