Semisupervised learning from different information sources

This paper studies the use of a semisupervised learning algorithm from different information sources. We first offer a theoretical explanation as to why minimising the disagreement between individual models could lead to the performance improvement. Based on the observation, this paper proposes a semisupervised learning approach that attempts to minimise this disagreement by employing a co-updating method and making use of both labeled and unlabeled data. Three experiments to test the effectiveness of the approach are presented in this paper: (i) webpage classification from both content and hyperlinks; (ii) functional classification of gene using gene expression data and phylogenetic data and (iii) machine self-maintaining from both sensory and image data. The results show the effectiveness and efficiency of our approach and suggest its application potentials.     

Semi-supervised orthogonal discriminant analysis via label propagation

Trace ratio is a natural criterion in discriminant analysis as it directly connects to the Euclidean distances between training data points. This criterion is re-analyzed in this paper and a fast algorithm is developed to find the global optimum for the orthogonal constrained trace ratio problem. Based on this problem, we propose a novel semi-supervised orthogonal discriminant analysis via label propagation. Differing from the existing semi-supervised dimensionality reduction algorithms, our algorithm propagates the label information from the labeled data to the unlabeled data through a specially designed label propagation, and thus the distribution of the unlabeled data can be explored more effectively to learn a better subspace. Extensive experiments on toy examples and real-world applications verify the effectiveness of our algorithm, and demonstrate much improvement over the state-of-the-art algorithms.     

Boosting for transfer learning from multiple data sources

Transfer learning aims at adapting a classifier trained on one domain with adequate labeled samples to a new domain where samples are from a different distribution and have no class labels. In this paper, we explore the transfer learning problems with multiple data sources and present a novel boosting algorithm, SharedBoost. This novel algorithm is capable of applying for very high dimensional data such as in text mining where the feature dimension is beyond several ten thousands. The experimental results illustrate that the SharedBoost algorithm significantly outperforms the traditional methods which transfer knowledge with supervised learning techniques. Besides, SharedBoost also provides much better classification accuracy and more stable performance than some other typical transfer learning methods such as the structural correspondence learning (SCL) and the structural learning in the multiple sources transfer learning problems.     

Semi-paired and semi-supervised multimodal hashing via cross-modality label propagation

Multimedia Tools and Applications - Due to the fast query speed and low storage cost, multimodal hashing methods have been attracting increasing attention in large-scale cross-media retrieval...     

Semi-supervised dictionary learning with label propagation for image classification

Computational Visual Media - Sparse coding and supervised dictionary learning have rapidly developed in recent years, and achieved impressive performance in image classification. However, there is...     

Video recommendation over multiple information sources

Video recommendation is an important tool to help people access interesting videos. In this paper, we propose a universal scheme to integrate rich information for personalized video recommendation. Our approach regards video recommendation as a ranking task. First, it generates multiple ranking lists by exploring different information sources. In particular, one novel source user’s relationship strength is inferred through the online social network and applied to recommend videos. Second, based on multiple ranking lists, a multi-task rank aggregation approach is proposed to integrate these ranking lists to generate a final result for video recommendation. It is shown that our scheme is flexible that can easily incorporate other methods by adding their generated ranking lists into our multi-task rank aggregation approach. We conduct experiments on a large dataset with 76 users and more than 11,000 videos. The experimental results demonstrate the feasibility and effectiveness of our approach.     

Granular multiple kernel learning for identifying RNA-binding protein residues via integrating sequence and structure information

Neural Computing and Applications - RNA-binding proteins play an important role in the biological process. However, the traditional experiment technology to predict RNA-binding residues is...     

Visual tracking via weakly supervised learning from multiple imperfect oracles

Notwithstanding many years of progress, visual tracking is still a difficult but important problem. Since most top-performing tracking methods have their strengths and weaknesses and are suited for handling only a certain type of variation, one of the next challenges is to integrate all these methods and address the problem of long-term persistent tracking in ever-changing environments. Towards this goal, we consider visual tracking in a novel weakly supervised learning scenario where (possibly noisy) labels but no ground truth are provided by multiple imperfect oracles (i.e., different trackers). These trackers naturally have intrinsic diversity due to their different design strategies, and we propose a probabilistic method to simultaneously infer the most likely object position by considering the outputs of all trackers, and estimate the accuracy of each tracker. An online evaluation strategy of trackers and a heuristic training data selection scheme are adopted to make the inference more effective and efficient. Consequently, the proposed method can avoid the pitfalls of purely single tracking methods and get reliably labeled samples to incrementally update each tracker (if it is an appearance-adaptive tracker) to capture the appearance changes. Extensive experiments on challenging video sequences demonstrate the robustness and effectiveness of the proposed method.     

Tracking multiple visual targets via particle-based belief propagation

Multiple-target tracking in video (MTTV) presents a technical challenge in video surveillance applications. In this paper, we formulate the MTTV problem using dynamic Markov network (DMN) techniques. Our model consists of three coupled Markov random fields: 1) a field for the joint state of the multitarget; 2) a binary random process for the existence of each individual target; and 3) a binary random process for the occlusion of each dual adjacent target. To make the inference tractable, we introduce two robust functions that eliminate the two binary processes. We then propose a novel belief propagation (BP) algorithm called particle-based BP and embed it into a Markov chain Monte Carlo approach to obtain the maximum a posteriori estimation in the DMN. With a stratified sampler, we incorporate the information obtained from a learned bottom-up detector (e.g., support-vector-machine-based classifier) and the motion model of the target into the message propagation. Other low-level visual cues such as motion and shape can be easily incorporated into our framework to obtain better tracking results. We have performed extensive experimental verification, and the results suggest that our method is comparable to the state-of-art multitarget tracking methods in all the cases we tested.     

Implicit consensus clustering from multiple graphs

Data Mining and Knowledge Discovery - Dealing with relational learning generally relies on tools modeling relational data. An undirected graph can represent these data with vertices depicting...     

Two-view correspondence learning via complex information extraction

Establishing reliable correspondences plays a vital role in many feature-matching based computer vision tasks. Given putative correspondences of feature points in two images, in this paper, we propose a novel network for inferring the probabilities of correspondences being inliers or outliers and regressing the relative pose encoded by the essential matrix. Previous research proposed an end-to-end permutation-equivariant classification network based on multi-layer perceptrons and context normalization. However, the context normalization treats each correspondence equally and ignore the extraction of channel information, as a result the representation capability of potential inliers can be reduced. To solve this problem, we apply attention mechanism in our network to capture complex information of the feature maps. Specifically, we introduce two types of attention blocks. We adopt the spatial attention block to capture complex spatial contextual information, and the rich channel information can be obtained by utilizing the channel attention block. To obtain richer contextual information and feature maps with stronger representative capacity, We combine these attention blocks with the PointCN block to form a new network with strong representative ability. Experimental results on several benchmark datasets show that the performance on outlier removal and camera pose estimation is significantly improved over the state-of-the-arts.

     

Embedding new data points for manifold learning via coordinate propagation

In recent years, a series of manifold learning algorithms have been proposed for nonlinear dimensionality reduction. Most of them can run in a batch mode for a set of given data points, but lack a mechanism to deal with new data points. Here we propose an extension approach, i.e., mapping new data points into the previously learned manifold. The core idea of our approach is to propagate the known coordinates to each of the new data points. We first formulate this task as a quadratic programming, and then develop an iterative algorithm for coordinate propagation. Tangent space projection and smooth splines are used to yield an initial coordinate for each new data point, according to their local geometrical relations. Experimental results and applications to camera direction estimation and face pose estimation illustrate the validity of our approach.

An objective-oriented approach to program comprehension using multiple information sources

Program comprehension is a key activity throughout software maintenance and reuse. The knowledge acquired through comprehending programs can guide engineers to perform various kinds of software maintenance and reuse tasks. The effective comprehension strategy and the associated efficient approach, as well as the sophisticated tool support, are the indispensable elements for an entire solution to program comprehension to reduce the high costs of this nontrivial activity. This paper presents an objective-oriented comprehension strategy, contrasting to the traditional comprehensive understanding strategy in the literature. It is a kind of on-demand understanding for specific tasks and more effective in practice. In addition, using multiple information sources to understand programs is proposed with the corresponding framework. From these two points of views, we propose a feature-oriented program comprehension approach using requirement documentation. This approach aims at a specific category of feature-related software maintenance and reuse tasks. Case studies are conducted to evaluate the proposed solution. Results from the studied cases show that the experimental prototype provides more explicit advices for software engineers when performing these tasks.     

Deep learning based origin-destination prediction via contextual information fusion

Origin-Destination (OD) prediction which aims to predict the number of passenger’s travel demands from one region to another, is critically important to many real applications including intelligent transportation systems and public safety. The challenges of this problem lie in both the dynamic patterns of the human mobility data and data sparsity in issue in some regions. Thus it is difficult to model the complex spatio-temporal correlations of the human mobility data to predict the OD of their trips. Meanwhile, the crowd flows in different regions of a city and the context features (e.g. holiday, weather and POIs) are potentially useful to alleviate the data sparsity issue and improve the OD prediction, but are largely ignored by existing works. In this paper, we propose a deep spatio-temporal framework which named Auxiliary-tasks Enhanced Spatio-Temporal Network (AEST) to more effectively address the OD prediction problem. AEST trains a model to conduct OD inference via learning crowd flow and external data as auxiliary task. The novel Hierarchical Convolutional LSTM (HC-LSTM) Network is proposed which combines CNN, GCN and LSTM to effectively capture spatiao-temporal correlations. In addition, we design a Contextual Network (ContextNet) which learns representations of contextual information to assist OD prediction. We conduct extensive experiments over bike and taxicab trip datasets in New York. The results show that our method is superior to the state-of-art approaches.

     

基于RGB-D的在线多示例学习目标跟踪算法

基于2D特征的目标跟踪算法缺少3维信息,因此在目标尺度、姿态变化和平面旋转时会引起跟踪不稳定易丢失目标的问题,为此提出一种基于RGB‐D的在线多示例学习目标跟踪算法。利用深度数据的特性在深度图中和RGB图中构建多尺度空间,提取多尺度的 Haar‐D特征和 Haar特征;利用多实例学习策略将多尺度的 Haar‐D特征和 Haar特征融合。实验结果表明,该算法能很好得处理室内或室外环境下目标姿态变化、平面旋转和部分遮挡的问题。     

Visual tracking via online discriminative multiple instance metric learning

Motion object tracking is an important issue in computer vision. In this paper, a robust tracking algorithm based on multiple instance learning (MIL) is proposed. First, a coarse-to-fine search method is designed to reduce the computation load of cropping candidate samples for a new arriving frame. Then, a bag-level similarity metric is proposed to select the most correct positive instances to form the positive bag. The instance’s importance to bag probability is determined by their Mahalanobis distance. Furthermore, an online discriminative classifier selection method, which exploits the average gradient and average weak classifiers strategy to optimize the margin function between positive and negative bags, is presented to solve the suboptimal problem in the process of selecting weak classifiers. Experimental results on challenging sequences show that the proposed method is superior to other compared methods in terms of both qualitative and quantitative assessments.     

Interactive learning and management of visual information via human-like software robot

To achieve smooth real-world interaction between people and computers, we developed a system that displays a three-dimensional computer-graphic human-like image from the waist up (anthropomorphic software robot: hereinafter “robot”) on the display, that interactively sees and hears, and that has fine and detailed control functions such as facial expressions, line of sight, and pointing at targets with its finger. The robot visually searches and identifies persons and objects in real space that it has learned in advance (registered space, which was our office in this case), manages the history information of the places and times it found objects and/or persons, and tells the user, indicating their three-dimensional positions with line of sight and its finger. It interactively learns new objects and persons with line of with their names and owners. By using this function, the robot can engage in simple dialogue (do a task) with the user. Osamu Hasegawa, Ph.D.: He received the B.E. and M.E. degrees from the Science University of Tokyo, in 1988, 1990 respectively. He received Ph.D. degree from the University of Tokyo, in 1993. Currently, he is a senior research scientist at the Electrotechnical Laboratory (ETL), Tsukuba, Japan. His research interests include Computer Vision and Multi-modal Human Interface. Dr. Hasegawa is a member of the AAAI, the Institute of Electronics, Information and Communication Engineers, Japan (IEICE), Information Processing Society of Japan and others. Katsuhiko Sakaue, Ph.D.: He received the B.E., M.E., and Ph.D. degrees all in electronic engineering from the University of Tokyo, in 1976, 1978 and 1981, respectively. In 1981, he joined the Electrotechnical Laboratory, Ministry of International Trade and Industry, and engaged in researches in image processing and computer vision. He received the Encouragement Prize in 1979 from IEICE, and the Paper Award in 1985 from Information Processing Society of Japan. He is a member of IEICE, IEEE, IPSJ, ITE. Satoru Hayamizu, Ph.D.: He is a leader of Interactive Intermodal Integration Lab. at Electrotechnical Laboratory. He received the B.E., M.E., Ph.D. degrees from Tokyo University. Since 1981, he has been working on speech recognition, spoken dialogue, and communication with artifacts. From 1989 to 1990, he was a visiting scholar in Carnegie Mellon University and in 1994 a visiting scientist in LIMSI/CNRS.     

Development of an adaptive learning system with two sources of personalization information

Previous research of adaptive learning mainly focused on improving student learning achievements based only on single-source of personalization information, such as learning style, cognitive style or learning achievement. In this paper, an innovative adaptive learning approach is proposed by basing upon two main sources of personalization information, that is, learning behavior and personal learning style. To determine the initial learning styles of the students, the [Keefe, J. W. (1987). Learning Styles: Theory and Practice. Reston, VA: National Association of Secondary School Principals.] questionnaire is employed in our approach. To more precisely reflect the learning behaviors of each student, the interactions and learning results of each student are analyzed when adjusting the subject materials. Based on the innovative approach, an adaptive learning system has been developed; moreover, an experiment was conducted to evaluate the performance of our approach. By analyzing the results from three groups of students using different adaptive learning approaches, it can be found that the innovative approach is helpful in improving both the learning achievement and learning efficiency of individual students.