Image annotation via graph learning

Image annotation has been an active research topic in recent years due to its potential impact on both image understanding and web image search. In this paper, we propose a graph learning framework for image annotation. First, the image-based graph learning is performed to obtain the candidate annotations for each image. In order to capture the complex distribution of image data, we propose a Nearest Spanning Chain (NSC) method to construct the image-based graph, whose edge-weights are derived from the chain-wise statistical information instead of the traditional pairwise similarities. Second, the word-based graph learning is developed to refine the relationships between images and words to get final annotations for each image. To enrich the representation of the word-based graph, we design two types of word correlations based on web search results besides the word co-occurrence in the training set. The effectiveness of the proposed solution is demonstrated from the experiments on the Corel dataset and a web image dataset.     

Multi-output learning via spectral filtering

In this paper we study a class of regularized kernel methods for multi-output learning which are based on filtering the spectrum of the kernel matrix. The considered methods include Tikhonov regularization as a special case, as well as interesting alternatives such as vector-valued extensions of L2 boosting and other iterative schemes. Computational properties are discussed for various examples of kernels for vector-valued functions and the benefits of iterative techniques are illustrated. Generalizing previous results for the scalar case, we show a finite sample bound for the excess risk of the obtained estimator, which allows to prove consistency both for regression and multi-category classification. Finally, we present some promising results of the proposed algorithms on artificial and real data.     

局部线性调和下的归纳式半监督分类算法

很多基于图的半监督分类算法是直推式的,即只解决了训练集上的数据标记,没解决新数据的标记问题.本文根据局部线性调和(LLC),提出一种归纳式丰监督分类算法SLLC.该算法采用混合模型建模原始数据,通过局部逼近确保标记平滑,利用分块的仿射变换实现了近似平滑的非线性映射.实验结果证实了本文算法的有效性.     

Coordination of communication in robot teams by reinforcement learning

In multi-agent systems, the study of language and communication is an active field of research. In this paper we present the application of Reinforcement Learning (RL) to the self-emergence of a common lexicon in robot teams. By modeling the vocabulary or lexicon of each agent as an association matrix or look-up table that maps the meanings (i.e. the objects encountered by the robots or the states of the environment itself) into symbols or signals we check whether it is possible for the robot team to converge in an autonomous, decentralized way to a common lexicon by means of RL, so that the communication efficiency of the entire robot team is optimal. We have conducted several experiments aimed at testing whether it is possible to converge with RL to an optimal Saussurean Communication System. We have organized our experiments alongside two main lines: first, we have investigated the effect of the team size centered on teams of moderated size in the order of 5 and 10 individuals, typical of multi-robot systems. Second, and foremost, we have also investigated the effect of the lexicon size on the convergence results. To analyze the convergence of the robot team we have defined the team’s consensus when all the robots (i.e. 100% of the population) share the same association matrix or lexicon. As a general conclusion we have shown that RL allows the convergence to lexicon consensus in a population of autonomous agents.     

Unsupervised feature selection via local structure learning and sparse learning

Multimedia Tools and Applications - Feature self-representation has become the backbone of unsupervised feature selection, since it is almost insensitive to noise data. However, feature selection...     

Multi-modal microblog classification via multi-task learning

Recent years have witnessed the flourishing of social media platforms (SMPs), such as Twitter, Facebook, and Sina Weibo. The rapid development of these SMPs has resulted in increasingly large scale multimedia data, which has been proved with remarkable marketing values. It is in an urgent need to classify these social media data into a specified list of concerned entities, such as brands, products, and events, to analyze their sales, popularity or influences. But this is a rather challenging task due to the shortness, conversationality, the incompatibility between images and text, and the data diversity of microblogs. In this paper, we present a multi-modal microblog classification method in a multi-task learning framework. Firstly features of different modalities are extracted for each microblog. Specifically, we extract TF-IDF features for each microblog text and low-level visual features and high-level semantic features for each microblog image. Then multiple related classification tasks are learned simultaneously for each feature to increase the sample size for each task and improve the prediction performance. Finally the outputs of each feature are integrated by a Support Vector Machine that learns how to optimally combine and weight each feature. We evaluate the proposed method on Brand-Social-Net to classify the contained 100 brands. Experimental results demonstrate the superiority of the proposed method, as compared to the state-of-the-art approaches.     

基于组合学习的人脸超分辨率算法

现有的基于深度学习的人脸超分辨算法大部分仅仅利用一种网络分区重建高分辨率输出图像,并未考虑人脸图像中的结构性信息,导致了在人脸的重要器官重建上缺乏足够的细节信息。针对这一问题,提出一种基于组合学习的人脸超分辨率算法。该算法独立采用不同深度学习模型的优势重建感兴趣的区域,由此在训练网络的过程中每个人脸区域的数据分布不同,不同的子网络能够获得更精确的先验信息。首先,对人脸图像采用超像素分割算法生成人脸组件部分和人脸背景图像;然后,采用人脸组件生成对抗网络（C-GAN）独立重建人脸组件图像块,并采用人脸背景重建网络生成人脸背景图像;其次,使用人脸组件融合网络将两种不同模型重建的人脸组件图像块自适应融合;最后,将生成的人脸组件图像块合并至人脸背景图像中,重建出最终的人脸图像。在FEI数据集上的实验结果表明,与人脸图像超分辨率算法通过组件生成和增强学习幻构人脸图像（LCGE）及判决性增强的生成对抗网络（EDGAN）相比,所提算法的峰值信噪比（PSNR）值分别高出1.23 dB和1.11 dB。所提算法能够采用不同深度学习模型的优势组合学习重建更精准的人脸图像,同时拓展了图像重建先验的来源。     

Robot action planning via explanation-based learning

Domain-specific searching heuristics is greatly influential upon the searching efficiency of robot action planning (RAP), but its computer-realized recognition and acquisition, i.e., learning, is difficult. This paper makes an exploration into this challenge. First, a problem formulation of RAP is made. Then, by applying explanation-based learning, which is currently the only approach to acquiring domain-specific searching heuristics, a new learning based method is developed for RAP, named robot action planning via explanation-based learning (RAPEL). Finally, an example study demonstrates the effectiveness of RAPEL     

Silhouette-based gait recognition via deterministic learning

In this paper, we present a new silhouette-based gait recognition method via deterministic learning theory, which combines spatio-temporal motion characteristics and physical parameters of a human subject by analyzing shape parameters of the subject?s silhouette contour. It has been validated only in sequences with lateral view, recorded in laboratory conditions. The ratio of the silhouette?s height and width (H–W ratio), the width of the outer contour of the binarized silhouette, the silhouette area and the vertical coordinate of centroid of the outer contour are combined as gait features for recognition. They represent the dynamics of gait motion and can more effectively reflect the tiny variance between different gait patterns. The gait recognition approach consists of two phases: a training phase and a test phase. In the training phase, the gait dynamics underlying different individuals? gaits are locally accurately approximated by radial basis function (RBF) networks via deterministic learning theory. The obtained knowledge of approximated gait dynamics is stored in constant RBF networks. In the test phase, a bank of dynamical estimators is constructed for all the training gait patterns. The constant RBF networks obtained from the training phase are embedded in the estimators. By comparing the set of estimators with a test gait pattern, a set of recognition errors are generated, and the average L₁ norms of the errors are taken as the similarity measure between the dynamics of the training gait patterns and the dynamics of the test gait pattern. The test gait pattern similar to one of the training gait patterns can be recognized according to the smallest error principle. Finally, the recognition performance of the proposed algorithm is comparatively illustrated to take into consideration the published gait recognition approaches on the most well-known public gait databases: CASIA, CMU MoBo and TUM GAID.     

Multiple instance learning via Gaussian processes

Multiple instance learning (MIL) is a binary classification problem with loosely supervised data where a class label is assigned only to a bag of instances indicating presence/absence of positive instances. In this paper we introduce a novel MIL algorithm using Gaussian processes (GP). The bag labeling protocol of the MIL can be effectively modeled by the sigmoid likelihood through the max function over GP latent variables. As the non-continuous max function makes exact GP inference and learning infeasible, we propose two approximations: the soft-max approximation and the introduction of witness indicator variables. Compared to the state-of-the-art MIL approaches, especially those based on the Support Vector Machine, our model enjoys two most crucial benefits: (i) the kernel parameters can be learned in a principled manner, thus avoiding grid search and being able to exploit a variety of kernel families with complex forms, and (ii) the efficient gradient search for kernel parameter learning effectively leads to feature selection to extract most relevant features while discarding noise. We demonstrate that our approaches attain superior or comparable performance to existing methods on several real-world MIL datasets including large-scale content-based image retrieval problems.     

Online learning via congregational gradient descent

We propose and analyse a populational version of stepwise gradient descent suitable for a wide range of learning problems. The algorithm is motivated by genetic algorithms which update a population of solutions rather than just a single representative as is typical for gradient descent. This modification of traditional gradient descent (as used, for example, in the backpropogation algorithm) avoids getting trapped in local minima. We use an averaging analysis of the algorithm to relate its behaviour to an associated ordinary differential equation. We derive a result concerning how long one has to wait in order that, with a given high probability, the algorithm is within a certain neighbourhood of the global minimum. We also analyse the effect of different population sizes. An example is presented which corroborates our theory very well.This work was supported by the Australian Research Council.     

深度残差学习下的光源颜色估计

目的 颜色恒常性通常指人类在任意光源条件下正确感知物体颜色的自适应能力,是实现识别、分割、3维视觉等高层任务的重要前提。对图像进行光源颜色估计是实现颜色恒常性计算的主要途径之一,现有光源颜色估计方法往往因局部场景的歧义颜色导致估计误差较大。为此,提出一种基于深度残差学习的光源颜色估计方法。方法 将输入图像均匀分块,根据局部图像块的光源颜色估计整幅图像的全局光源颜色。算法包括光源颜色估计和图像块选择两个残差网络：光源颜色估计网络通过较深的网络层次和残差结构提高光源颜色估计的准确性;图像块选择网络按照光源颜色估计误差对图像块进行分类,根据分类结果去除图像中误差较大的图像块,进一步提高全局光源颜色估计精度。此外,对输入图像进行对数色度预处理,可以降低图像亮度对光源颜色估计的影响,提高计算效率。结果 在NUS-8和重处理的ColorChecker数据集上的实验结果表明,本文方法的估计精度和稳健性较好;此外,在相同条件下,对数色度图像比原始图像的估计误差低10% 15%,图像块选择网络能够进一步使光源颜色估计网络的误差降低约5%。结论 在两组单光源数据集上的实验表明,本文方法的总体设计合理有效,算法精度和稳健性好,可应用于需要进行色彩校正的图像处理和计算机视觉等领域。     

Clustering ensemble via structured hypergraph learning

Clustering ensemble integrates multiple base clustering results to obtain a consensus result and thus improves the stability and robustness of the single clustering method. Since it is natural to use a hypergraph to represent the multiple base clustering results, where instances are represented by nodes and base clusters are represented by hyperedges, some hypergraph based clustering ensemble methods are proposed. Conventional hypergraph based methods obtain the final consensus result by partitioning a pre-defined static hypergraph. However, since base clusters may be imperfect due to the unreliability of base clustering methods, the pre-defined hypergraph constructed from the base clusters is also unreliable. Therefore, directly obtaining the final clustering result by partitioning the unreliable hypergraph is inappropriate. To tackle this problem, in this paper, we propose a clustering ensemble method via structured hypergraph learning, i.e., instead of being constructed directly, the hypergraph is dynamically learned from base results, which will be more reliable. Moreover, when dynamically learning the hypergraph, we enforce it to have a clear clustering structure, which will be more appropriate for clustering tasks, and thus we do not need to perform any uncertain postprocessing, such as hypergraph partitioning. Extensive experiments show that, our method not only performs better than the conventional hypergraph based ensemble methods, but also outperforms the state-of-the-art clustering ensemble methods.     

On the Expressiveness of Timed Coordination via Shared Dataspaces

Since Linda, many differents coordination models using shared dataspaces have been developped. However, a few only have incorporated the notion of time. This paper builds upon previous work to study the expressive power of two families of timed coordination models based on shared dataspaces. The first one relies on Linda's communication primitives whereas the second relies on the more general notion of multi-set rewriting, incorporated, for instance, in Gamma. We analyse the expressiveness increase provided by the primitives in each of the two families and also compare the expressiveness power of the two families.     

On Modeling Coordination via Asynchronous Communication and Enhanced Matching

The paper proposes a theoretical study of a coordination language embodying Linda's asynchronous communication primitive with a refined matching mechanism based on pairs composed of attribute names associated with their values. Computations in this language are described by means of an operational semantics, reporting the whole traces of executions. The non-compositionality of this intuitive operational semantics motivates the design of a compositional and fully abstract denotational semantics, which is then exploited for studying program equivalence in this setting.     

一种基于学习机制的并行遗传算法

基于生物学群落的概念,提出了一个群落-种群-个体的三层模型,并在该模型上发展了一种基于学习机制的并行遗传算法(PGABL)。算法引入黑板模型作为控制和交互的数据结构,采用群内、群间、群落三个学习算子,将遗传进化和遗传学习相结合,有效地改善了遗传算法的性能。实验结果表明,该算法具有良好的适应性和稳定性。     

Coordination of fractional-order nonlinear multi-agent systems via distributed impulsive control

The coordination of fractional-order nonlinear multi-agent systems via distributed impulsive control method is studied in this paper. Based on the theory of impulsive differential equations, algebraic graph theory, Lyapunov stability theory and Mittag-Leffler function, two novel sufficient conditions for achieving the cooperative control of a class of fractional-order nonlinear multi-agent systems are derived. Finally, two numerical simulations are verified to illustrate the effectiveness and feasibility of the proposed method.     

Effectiveness of vocabulary learning via mobile phone

Whereas the penetration of mobile phones in Asian countries keeps climbing, little research has explored the application of the short message service (SMS) in second language learning. This study aims to examine the effectiveness of SMS vocabulary lessons of limited lexical information on the small screens of mobile phones. Thirty high school students were randomly distributed into two groups and given two sets of English words either on paper or through SMS messages during two weeks. Students recognized more vocabulary during the post‐test after reading the regular and brief SMS lessons than they did after reading the relatively more detailed print material. Qualitative data from interviews offer information about the learning process as well as the benefits and limitations of m‐learning. Results of the questionnaires show that students in general hold positive attitudes towards learning vocabulary via mobile phone. On the other hand, technological limitations, unfamiliar presentations and learning activities may prevent students from reading SMS lessons.