Web image concept annotation with better understanding of tags and visual features

This paper focuses on improving the semi-manual method for web image concept annotation. By sufficiently studying the characteristics of tag and visual feature, we propose the Grouping-Based-Precision & Recall-Aided (GBPRA) feature selection strategy for concept annotation. Specifically, for visual features, we construct a more robust middle level feature by concatenating the k-NN results for each type of visual feature. For tag, we construct a concept-tag co-occurrence matrix, based on which the probability of an image belonging to certain concept can be calculated. By understanding the tags’ quality and groupings’ semantic depth, we propose a grouping based feature selection method; by studying the tags’ distribution, we adopt Precision and Recall as a complementary indicator for feature selection. In this way, the advantages of both tags and visual features are boosted. Experimental results show our method can achieve very high Average Precision, which greatly facilitates the annotation of large-scale web image dataset.     

Boosting image object retrieval and indexing by automatically discovered pseudo-objects

State-of-the-art object retrieval systems are mostly based on the bag-of-visual-words representation which encodes local appearance information of an image in a feature vector. An image object search is performed by comparing query object’s feature vector with those for database images. However, a database image vector generally carries mixed information of the entire image which may contain multiple objects and background. Search quality is degraded by such noisy (or diluted) feature vectors. To tackle this problem, we propose a novel representation, pseudo-objects – a subset of proximate feature points with its own feature vector to represent a local area, to approximate candidate objects in database images. In this paper, we investigate effective methods (e.g., grid, G-means, and GMM–BIC) to estimate pseudo-objects. Additionally, we also confirm that the pseudo-objects can significantly benefit inverted-file indexing both in accuracy and efficiency. Experimenting over two consumer photo benchmarks, we demonstrate that the proposed method significantly outperforms other state-of-the-art object retrieval and indexing algorithms.     

一种基于二值粒子群优化和支持向量机的目标检测算法

针对复杂场景下目标检测和目标检测中特征选择问题,该文将二值粒子群优化算法(BPSO)用于特征选择,结合支持向量机(SVM)技术提出了一种新颖的基于BPSO-SVM特征选择的自动目标检测算法。该算法将目标检测转化为目标识别问题,采用wrapper特征选择模型,以SVM为分类器,通过样本训练分类器,根据分类结果,利用BPSO算法在特征空间中进行全局搜索,选择最优特征集进行分类。基于BPSO-SVM的特征选择方法降低了特征维数,显著提高了分类器性能。实验结果表明,该文算法不仅有效提高了复杂场景下目标姿态、尺度、光照变化和局部被遮挡时的检测准确率,还大大缩短了检测时间。     

混合蒙特卡罗搜索的特征选择算法的优化

特征选择是机器学习和数据挖掘中处理高维数据的初步步骤,通过消除冗余或不相关的特征来识别数据集中最重要和最相关的特征,从而提高分类精度和降低计算复杂度。文中提出混合蒙特卡罗树搜索特征选择算法(HMCTS),首先,根据蒙特卡罗树搜索方法迭代生成一个初始特征子集,利用ReliefF算法过滤选择前k个特征形成候选特征子集;然后,利用KNN分类器的分类精度评估候选特征,通过反向传播将模拟结果更新到迭代路径上所有选择的节点;最后,选择高精度的候选特征作为最佳特征子集。仿真结果表明,对比HPSO-LS和MOTiFS算法,HMCTS算法具有良好的可扩展性,且分类精度高。     

用于特征选择的BF算法及其与BF算法的比较

借助于人工智能搜索技术,Xu等人提出了计算量优于B&B算法的全局最优特征提取BF*算法。本文在分析了BF*算法搜索树T_B结构的基础上,提出了一种比T_B具有更少节点的搜索树T_b及相应的BF**算法。并证明,在不另增加存贮量和保持全局最优特性的前提下,BF**算法在计算量方面优于BF*算法。     

特征选择算法综述

自20世纪90年代以来,特征选择成为模式识别和机器学习领域的重要研究方向,研究成果十分显著,但是也存在许多问题需要进一步研究。本文首先将特征选择视为特征集合空间中的启发式搜索问题,对特征选择涉及的四个要素进行了阐述,然后从各个角度对特征选择算法进行了分类,概述了其各个分支的发展态势,最后探讨了基于多目标免疫优化的特征选择方法的研究思路。     

Semi-supervised Robust Feature Selection with eq-Norm Graph for Multiclass Classification

Flexible manifold embedding (FME) is a semi-supervised dimension reduction framework.It has been extended into feature selection by using different loss functions and sparse regularization methods.However,these kind of methods used the quadratic form of graph embedding,thus the results are sensitive to noise and outliers.In this paper,we propose a general semi-supervised feature selection model that optimizes an eq-norm of FME to decrease the noise sensitivity.Compare to the fixed parameter model,the eq-norm graph brings flexibility to balance the manifold smoothness and the sensitivity to noise by tuning its parameter.We present an efficient iterative algorithm to solve the proposed eq-norm graph embedding based semi-supervised feature selection problem,and offer a rigorous convergence analysis.Experiments performed on typical image and speech emotion datasets demonstrate that our method is effective for the multiclass classification task,and outperforms the related state-of-the-art methods.     

基于簇相似的多分类器目标跟踪算法

由于跟踪过程中目标和背景的变化,传统的单分类器跟踪算法学习到大量的非目标信息而导致跟踪精度降低.针对该问题,本文提出使用树形结构保存历史分类器.在每一帧,根据树中路径距离选择分类器集对测试样本分类.提出了一种基于簇相似性比较的分类算法.通过建立以方差为尺度的特征空间,比较测试样本到簇中心的距离计算相似度,快速计算出目标样本.实验表明本算法能够在复杂条件下实现对目标的鲁棒跟踪.     

Feature selection for content-based image retrieval

In this article, we propose a novel system for feature selection, which is one of the key problems in content-based image indexing and retrieval as well as various other research fields such as pattern classification and genomic data analysis. The proposed system aims at enhancing semantic image retrieval results, decreasing retrieval process complexity, and improving the overall system usability for end-users of multimedia search engines. Three feature selection criteria and a decision method construct the feature selection system. Two novel feature selection criteria based on inner-cluster and intercluster relations are proposed in the article. A majority voting-based method is adapted for efficient selection of features and feature combinations. The performance of the proposed criteria is assessed over a large image database and a number of features, and is compared against competing techniques from the literature. Experiments show that the proposed feature selection system improves semantic performance results in image retrieval systems. This work was supported by the Academy of Finland, Project No. 213,462 (Finnish Centre of Excellence Program 2006–2011).     

Invariant‐Feature Based Object Tracking Using Discrete Dynamic Swarm Optimization

With the remarkable growth in rich media in recent years, people are increasingly exposed to visual information from the environment. Visual information continues to play a vital role in rich media because people's real interests lie in dynamic information. This paper proposes a novel discrete dynamic swarm optimization (DDSO) algorithm for video object tracking using invariant features. The proposed approach is designed to track objects more robustly than other traditional algorithms in terms of illumination changes, background noise, and occlusions. DDSO is integrated with a matching procedure to eliminate inappropriate feature points geographically. The proposed novel fitness function can aid in excluding the influence of some noisy mismatched feature points. The test results showed that our approach can overcome changes in illumination, background noise, and occlusions more effectively than other traditional methods, including color‐tracking and invariant feature‐tracking methods.     

Modified Jaccard index analysis and adaptive feature selection for location fingerprinting with limited computational complexity

We propose an approach for fingerprinting-based positioning which reduces the data requirements and computational complexity of the online positioning stage. It is based on a segmentation of the entire region of interest into subregions, identification of candidate subregions during the online-stage, and position estimation using a preselected subset of relevant features. The subregion selection uses a modified Jaccard which quantifies the similarity between the features observed by the user and those available within the reference fingerprint map. The adaptive feature selection is achieved using an adaptive forward-backward greedy search which determines a subset of features for each subregion, relevant with respect to a given fingerprinting-based positioning method. In an empirical study using signals of opportunity for fingerprinting the proposed subregion and feature selection reduce the processing time during the online-stage by a factor of about 10 while the positioning accuracy does not deteriorate significantly. In fact, in one of the two study cases, the 90th percentile of the circular error increased by 7.5% while in the other study case we even found a reduction of the corresponding circular error by 30%.     

Incremental object learning and robust tracking of multiple objects from RGB-D point set data

In this paper, we propose a novel model-free approach for tracking multiple objects from RGB-D point set data. This study aims to achieve the robust tracking of arbitrary objects against dynamic interaction cases in real-time. In order to represent an object without prior knowledge, the probability density of each object is represented by Gaussian mixture models (GMM) with a tempo-spatial topological graph (TSTG). A flexible object model is incrementally updated in the pro-posed tracking framework, where each RGB-D point is identified to be involved in each object at each time step. Furthermore, the proposed method allows the creation of robust temporal associations among multiple updated objects during split, complete occlusion, partial occlusion, and multiple contacts dynamic interaction cases. The performance of the method was examined in terms of the tracking accuracy and computational efficiency by various experiments, achieving over 97% accuracy with five frames per second computation time. The limitations of the method were also empirically investigated in terms of the size of the points and the movement speed of objects.     

An Interconnected Feature Pyramid Networks for object detection

Although deep learning makes major breakthroughs in object detection, object detection still faces several limitations listed as follows: (1) Many works underplay the feature selection, leading to the resulting key features are not prominent enough and prone to noise; (2) Many works pass back features in a layer-by-layer manner to achieve multi-scale features. However, as the distance of layers from each other increases, the semantics are diluted, and the transfer of information between layers becomes difficult. To overcome these problems, we propose a new Interconnected Feature Pyramid Networks (IFPN) for feature enhancement. It can simultaneously select attentive features through the attention mechanism and realize the free flow of information. On the basis of the improvements, we design a new IFPN Detector. Experiments on COCO dataset and Smart UVM dataset show that our method can bring a significant improvement.     

Multi-scale attention guided network for end-to-end face alignment and recognition

Attention modules embedded in deep networks mediate the selection of informative regions for object recognition. In addition, the combination of features learned from different branches of a network can enhance the discriminative power of these features. However, fusing features with inconsistent scales is a less-studied problem. In this paper, we first propose a multi-scale channel attention network with an adaptive feature fusion strategy (MSCAN-AFF) for face recognition (FR), which fuses the relevant feature channels and improves the network’s representational power. In FR, face alignment is performed independently prior to recognition, which requires the efficient localization of facial landmarks, which might be unavailable in uncontrolled scenarios such as low-resolution and occlusion. Therefore, we propose utilizing our MSCAN-AFF to guide the Spatial Transformer Network (MSCAN-STN) to align feature maps learned from an unaligned training set in an end-to-end manner. Experiments on benchmark datasets demonstrate the effectiveness of our proposed MSCAN-AFF and MSCAN-STN.     

Selecting subsets of autoregressive parameters

Processes with seasonal components are frequently modelled in physics or economics. The class of subset models is appropriate for such data; subsets have only m efficients until the maximum lag L. An efficient algorithm is used to look for the best of the 2^L possible subsets with maximum lag L. The best subset is theoretically defined to be the one giving the smallest squared error of prediction when applied to new data. But in practice only transformations of the residual variance of the current data can be used as a selection criterion in comparing estimated subsets of different sizes. This paper compares the quality of models selected with different criteria. It is shown that subset selection can yield accurate models with less estimated parameters, that give a smaller prediction error than models with all parameters included. The maximum lag for the subsets is better restricted to a selected model order than to an a priori fixed maximum lag.     

基于显著性特征的选择性目标跟踪算法

针对长期目标跟踪算法中目标部分遮挡甚至消失情况下的目标有效跟踪问题,提出了一种融合了目标显著性特征的选择性跟踪算法.首先,为了有效抑制背景信息的干扰,综合HOG特征以及颜色统计特征的特点提出了前景概率图来实现增强目标显著性抑制背景干扰的效果.其次,为了减少跟踪漂移和解决重度照明和遮挡等挑战性场景中的跟踪失败问题,引入了具有筛选条件的选择性跟踪和检测框架,用以控制检测器的激活以及最终结果的选择.OTB2013数据集上的实验结果证明,本文算法可以取得91.1%的总体准确率以及67%的总体成功率,结果优于大部分跟踪算法.     

复杂场景下基于多特征融合的视频跟踪

为了解决常见视频跟踪方法在复杂场景中难以有效跟踪运动物体的难题,研究了在粒子滤波框架下基于多特征融合的判别式视频跟踪算法.首先分析了特征提取和跟踪算法的鲁棒性和准确性的关系,指出融合多种特征能有效地提升算法在复杂场景中的跟踪效果,然后选择提取HSV颜色特征和HOG特征描述目标表观,并在线训练逻辑斯特回归分类器构造判别式目标表观模型.在公开的复杂场景视频进行测试,比较了使用单一特征和多种特征的实验效果,并且将所提算法和经典跟踪算法进行了比较,实验结果表明融合多种特征的视频跟踪更具鲁棒性和准确性.     

Gateway Placement for Throughput Optimization in Wireless Mesh Networks

In this paper, we address the problem of gateway placement for throughput optimization in multi-hop wireless mesh networks. Assume that each mesh node in the mesh network has a traffic demand. Given the number of gateways to be deployed (denoted by k) and the interference model in the network, we study where to place exactly k gateways in the mesh network such that the total throughput is maximized while it also ensures a certain fairness among all mesh nodes. We propose a novel grid-based gateway deployment method using a cross-layer throughput optimization, and prove that the achieved throughput by our method is a constant times of the optimal. Simulation results demonstrate that our method can effectively exploit the available resources and perform much better than random and fixed deployment methods. In addition, the proposed method can also be extended to work with multi-channel and multi-radio mesh networks under different interference models.     

一种基于差异演化的特征子集选择算法

特征子集选择问题一直是人工智能领域研究的重要内容。特征子集选择算法研究是机器学习和数据挖掘等领域的研究热点。提出了基于差异演化算法的特征子集选择算法,实验证明该算法是简单、正确、有效的,并具有良好的收敛性和稳定性。     

Beyond visual word ambiguity: Weighted local feature encoding with governing region

Typically, k-means clustering or sparse coding is used for codebook generation in the bag-of-visual words (BoW) model. Local features are then encoded by calculating their similarities with visual words. However, some useful information is lost during this process. To make use of this information, in this paper, we propose a novel image representation method by going one step beyond visual word ambiguity and consider the governing regions of visual words. For each visual application, the weights of local features are determined by the corresponding visual application classifiers. Each weighted local feature is then encoded not only by considering its similarities with visual words, but also by visual words’ governing regions. Besides, locality constraint is also imposed for efficient encoding. A weighted feature sign search algorithm is proposed to solve the problem. We conduct image classification experiments on several public datasets to demonstrate the effectiveness of the proposed method.