Weakly supervised image parsing via label propagation over discriminatively semantic graph

In this paper, we concentrate on a challenging problem, i.e., weakly supervised image parsing, whereby only weak image-level labels are available in the dataset. In tradition, an affinity graph of superpixels is constructed to strengthen weak information by leveraging the neighbors from the perspective of image-level labels. Existing work constructs the affinity graph by purely utilizing the visual relevance, where the context homogenization is a common phenomenon and hinders the performance of label prediction. To overcome the context homogenization problem, we not only consider the visual and semantic relevance but also the semantic distinction between every target superpixel and its neighbor superpixels in the affinity graph construction. We propose a novel way in constructing the inter-image contextual graph, and design a label propagation framework jointly combining visual relevance, semantic relevance and discriminative ability. Extensive experiments on real-world datasets demonstrate that our approach obtains significant gains.     

Self-correcting complex semantic analysis method based on pre-training mechanism

In the process of knowledge service,in order to meet the fragmentation management needs of intellectualization,knowledge ability,refinement and reorganization content resources.Through deep analysis and mining of semantic hidden knowledge,technology,experience,and information,it broke through the existing bottleneck of traditional semantic parsing technology from Text-to-SQL.The PT-Sem2SQL based on the pre-training mechanism was proposed.The MT-DNN pre-training model mechanism combining Kullback-Leibler technology was designed to enhance the depth of context semantic understanding.A proprietary enhancement module was designed that captured the location of contextual semantic information within the sentence.Optimize the execution process of the generated model by the self-correcting method to solve the error output during decoding.The experimental results show that PT-Sem2SQL can effectively improve the parsing performance of complex semantics,and its accuracy is better than related work.     

Tailored Mechanical Metamaterials with Programmable Quasi-Zero-Stiffness Features for Full-Band Vibration Isolation

Quasi-zero-stiffness (QZS) isolators of high-static-low-dynamic stiffness play an important role in ultra-low frequency vibration mitigation. While the current designs of QZS mainly exploit the combination of negative-stiffness corrector and positive-stiffness element, and only have a single QZS working range, here a class of tailored mechanical metamaterials with programmable QZS features is proposed. These programmed structures contain curved beams with geometries that are specifically designed to enable the prescribed QZS characteristics. When these metamaterials are compressed, the curved beams reach the prescribed QZS working range in sequence, thus enabling tailored stair-stepping force-displacement curves with multiple QZS working ranges. Compression tests demonstrate that a vast design space is achieved to program the QZS features of the metamaterials. Further vibration tests confirm the ultra-low frequency vibration isolation capability of the proposed mechanical metamaterials. The mechanism of QZS stems solely from the structural geometry of the curved beams and is therefore materials-independent. This design strategy opens a new avenue for innovating compact and scalable QZS isolators with multiple working ranges.     

高速IP路由查找中改善更新性能的方法

现有的高速IP路由查找算法更多地强调路由表的查找,却忽视了路由表的更新。而路由表的更新对整个路由查找算法的性能和实际应用有不可忽视的影响。分段式查找树(Multibittrie)查找算法作为常用的IP路由查找算法,具有算法简单、有效等特点,但是更新速率较慢。作者提出一种在分段式查找树中控制路由表更新时间的方法,此方法能够较大地改善分段式查找树的更新性能。文章对更新性能的改善作了论述。     

Language-guided graph parsing attention network for human-object interaction recognition

This paper focuses on the task of human-object interaction (HOI) recognition, which aims to classify the interaction between human and objects. It is a challenging task partially due to the extremely imbalanced data among classes. To solve this problem, we propose a language-guided graph parsing attention network (LG-GPAN) that makes use of the word distribution in language to guide the classification in vision. We first associate each HOI class name with a word embedding vector in language and then all the vectors can construct a language space specified for HOI recognition. Simultaneously, the visual feature is extracted from the inputs via the proposed graph parsing attention network (GPAN) for better visual representation. The visual feature is then transformed into the linguistic one in language space. Finally, the output score is obtained via measuring the distance between the linguistic feature and the word embedding of classes in language space. Experimental results on the popular CAD-120 and V-COCO datasets validate our design choice and demonstrate its superior performance in comparison to the state-of-the-art.     

基于语义的领域构件接口名称匹配方法

提出了一种基于语义的领域构件接口名称的匹配方法。首先要对已有的构件库中的构件接13名称进行基于命名规则库、维度记录模型、词根表、环境和操作分类表的解析，得到解析构件库。基于解析构件库的匹配根据使用者对环境、对象（含义和组成信息）、操作的输入查询解析构件库，根据环境和操作信息过滤掉不符合要求的接口，基于设定的阈值对领域对象进行名称相似度和组成相似度的计算，得到匹配程度。基于该方法的构件匹配工具在实际工作中进行了应用，并取得了较好的效果。     

面向拟态云服务的异构执行体调度算法

针对当前异构调度模型仅从空间或者时间特性进行建模设计,缺少对时空特性的综合考虑且存在动态性和异构性不够均衡的问题。为使拟态云服务系统的动态、异构和冗余特性能够平衡互补,提出一种基于优先级和时间片的执行池调度算法,该算法基于执行池相似性指标进行优先级预排序,结合时间片等策略进行方案调度。实验结果表明,所提算法有较好的动态性,结合时间片策略能够获得动态性和异构性的综合平衡,且算法耗时较低。     

基于潜在语义分析和相关反馈的图像检索方法

为了解决传统的CBIR系统中存在的"语义鸿沟"问题,提出一种基于潜在语义索引技术(LSI)和相关反馈技术的图像检索方法.在进行图像检索时,先在HSV空间下提取颜色直方图作为底层视觉特征进行图像检索,然后引入潜在语义索引技术试图将底层特征赋予更高层次的语义含义;并且结合相关反馈技术,通过与用户交互进一步提高检索精度.实验...     

Heterogeneous redundancies scheduling algorithm for mimic security defense

The scheduling of heterogeneous redundancies is one of the key lines of mimic security defense,but the existing scheduling strategies are lack of consideration about the similarity among redundancies and the scheduling algorithms are incomprehensive.A new scheduling algorithm called random seed & minimum similarity (RSMS) algorithm was proposed,which combined dynamics and reliability by determining a scheduling scheme with minimum global-similarity after choosing a seed-redundancy randomly.Theoretical analysis and simulation results show that RSMS algorithm possessed a far longer scheduling cycle than maximum dissimilarity algorithm,as well as a far lower failure rate than random scheduling algorithm,which represents an effective balance between dynamics and reliability.     

检测骨架图形特征点的新方法

端点、折点、歧点和交点是骨架图形的重要特点是，提出用快速查表法检测侯选特征点，再进行侯选特征点聚集，用局部结构分析，去除假特征点，判别真特征点的类型，并对折点给以大致的定量描述。实验结果表明，该方法能快速有效地找出骨架图形的特征点，在目标识别、字符识别等应用中起着关键作用。     

Neural network model for dependency parsing incorporating global vector feature

LSTM and piecewise CNN were utilized to extract word vector features and global vector features,respectively.Then the two features were input to feed forward network for training.In model training,the probabilistic training method was adopted.Compared with the original dependency paring model,the proposed model focused more on global features,and used all potential dependency trees to update model parameters.Experiments on Chinese Penn Treebank 5 (CTB5) dataset show that,compared with the parsing model using LSTM or CNN only,the proposed model not only remains the relatively low model complexity,but also achieves higher accuracies.     

Distributed arbitration scheme for on-chip CDMA bus with dynamic codeword assignment

Several code-division multiple access (CDMA)-based interconnect schemes have been recently proposed as alternatives to the conventional time-division multiplexing bus in multicore systems-on-chip. CDMA systems with a dynamic assignment of spreading codewords are particularly attractive because of their potential for higher bandwidth efficiency compared with the systems in which the codewords are statically assigned to processing elements. In this paper, we propose a novel distributed arbitration scheme for dynamic CDMA-bus-based systems, which solves the complexity and scalability issues associated with commonly used centralized arbitration schemes. The proposed arbitration unit is decomposed into multiple simple arbitration elements, which are connected in a ring. The arbitration ring implements a token-passing algorithm, which both resolves destination conflicts and assigns the codewords to processing elements. Simulation results show that the throughput reduction in an optimally configured dynamic CDMA bus due to arbitration-related overheads does not exceed 5%.     

基于潜在语义索引技术的用户兴趣模型构建

用户兴趣模型的表示是信息检索的核心技术之一.利用潜在语义索引的方法构建了一种用户兴趣模型,通过计算文本与模型的匹配程度,将满足约定条件的文本推荐给用户,并利用相关反馈信息更新用户的兴趣模型.最后通过实验验证了该方法的有效性,实验表明该模型可以很好地提高用户信息检索的效率.     

CCFNet: Cross-Complementary fusion network for RGB-D scene parsing of clothing images

Schemes to complement context relationships by cross-scale feature fusion have appeared in many RGB-D scene parsing algorithms; however, most of these works conduct multi-scale information interaction after multi-modal feature fusion, which ignores the information loss of the two modes in the original coding. Therefore, a cross-complementary fusion network (CCFNet) is designed in this paper to calibrate the multi-modal information before feature fusion, so as to improve the feature quality of each mode and the information complementarity ability of RGB and the depth map. First, we divided the features into low, middle, and high levels, among which the low-level features contain the global details of the image and the main learning features include texture, edge, and other features. The middle layer features contain not only some global detail features but also some local semantic features. Additionally, the high-level features contain rich local semantic features. Then, the feature information lost in the coding process of low and middle level features is supplemented and extracted through the designed cross feature enhancement module, and the high-level features are extracted through the feature enhancement module. In addition, the cross-modal fusion module is designed to integrate multi-modal features of different levels. The experimental results verify that the proposed CCFNet achieves excellent performance on the RGB-D scene parsing dataset containing clothing images, and the generalization ability of the model is verified by the dataset NYU Depth V2.     

Fusion of 3D-LIDAR and camera data for scene parsing

Fusion of information gathered from multiple sources is essential to build a comprehensive situation picture for autonomous ground vehicles. In this paper, an approach which performs scene parsing and data fusion for a 3D-LIDAR scanner (Velodyne HDL-64E) and a video camera is described. First of all, a geometry segmentation algorithm is proposed for detection of obstacles and ground areas from data collected by the Velodyne scanner. Then, corresponding image collected by the video camera is classified patch by patch into more detailed categories. After that, parsing result of each frame is obtained by fusing result of Velodyne data and that of image using the fuzzy logic inference framework. Finally, parsing results of consecutive frames are smoothed by the Markov random field based temporal fusion method. The proposed approach has been evaluated with datasets collected by our autonomous ground vehicle testbed in both rural and urban areas. The fused results are more reliable than that acquired via analysis of only images or Velodyne data.     

Visible and thermal images fusion architecture for few-shot semantic segmentation

Few-shot semantic segmentation (FSS) has drawn great attention in the community of computer vision, due to its remarkable potential for segmenting novel objects with few pixel-annotated samples. However, some interference factors, such as insufficient illumination and complex background, can impose more challenge to the segmentation performance than fully-supervised when the number of samples is insufficient. Therefore, we propose the visible and thermal (V-T) few-shot semantic segmentation task, which utilize the complementary and similar information of visible and thermal images to boost few-shot segmentation performance. As the first step, we build a novel outdoor city dataset Tokyo Multi-Spectral-4ⁱ for the V-T few-shot semantic segmentation task. In addition, a fusion architecture is proposed, which consists of an Edge Similarity fusion module (ES) and a Texture Edge Prototype module (TEP). The ES module fuses the bi-modal information by exploiting the edge similarity in the visible and thermal images. The TEP module extracts the prototype from two models by collaborating the representativeness and complementarity of the visible and thermal feature. Finally, extensive experiments conducted on the proposed datasets demonstrate that our architecture can achieve state-of-the-arts results.     

Fast ping‐pong arbitration for input–output queued packet switches

Input–output queued switches have been widely considered as the most feasible solution for large capacity packet switches and IP routers. In this paper, we propose a ping‐pong arbitration scheme (PPA) for output contention resolution in input–output queued switches. The challenge is to develop a high speed and cost‐effective arbitration scheme in order to maximize the switch throughput and delay performance for supporting multimedia services with various quality‐of‐service (QoS) requirements. The basic idea is to divide the inputs into groups and apply arbitration recursively. Our recursive arbiter is hierarchically structured, consisting of multiple small‐size arbiters at each layer. The arbitration time of an n‐input switch is proportional to log₄?n/2? when we group every two inputs or every two input groups at each layer. We present a 256×256 terabit crossbar multicast packet switch using the PPA. The design shows that our scheme can reduce the arbitration time of the 256×256 switch to 11 gates delay, demonstrating the arbitration is no longer the bottleneck limiting the switch capacity. The priority handling in arbitration is also addressed. Copyright © 2001 John Wiley & Sons, Ltd.     

Hardware Organization to Achieve High-Speed Elliptic Curve Cryptography for Mobile Devices

Elliptic curve cryptography (ECC) is recognized as a fast cryptography system and has many applications in security systems. In this paper, a novel sharing scheme is proposed to significantly reduce the number of field multiplications and the usage of lookup tables, providing high speed operations for both hardware and software realizations.

Parameterized High Throughput Function Evaluation for FPGAs

This paper presents parameterized module-generators for pipelined function evaluation using lookup tables, adders, shifters, multipliers, and dividers. We discuss trade-offs involved between (1) full-lookup tables, (2) bipartite (lookup-add) units, (3) lookup-multiply units, (4) shift-and-add based CORDIC units, and (5) rational approximation. Our treatment mainly focuses on explaining method (3), and briefly covers the background of the other methods. For lookup-multiply units, we provide equations for estimating approximation errors and rounding errors which are used to parameterize the hardware units. The resources and performance of the resulting design can be estimated given the input parameters. A selection of the compared methods are implemented as part of the current PAM-Blox module generation environment. An example shows that the lookup-multiply unit produces competitive designs with data widths up to 20 bits when compared with shift-and-add based CORDIC units. Additionally, the lookup-multiply method or rational approximation can produce efficient designs for larger data widths when evaluating functions not supported by CORDIC.