Biologically Inspired Visual Model With Preliminary Cognition and Active Attention Adjustment.

Currently, many of the processing techniques for the location-based queries provide information of a single type of spatial objects, based on their spatial closeness to the query object. However, in real-life applications the user may be interested in obtaining information about different types of objects, in terms of their quality, cost, and neighboring relationship. We term the different types of objects with better quality and closer to each other the Neighboring skyline set (or NS set). Three new types of location-based queries, the Distance-based neighboring skyline query (Dist-NS query), the Cost-based neighboring skyline query (Cost-NS query), and the Budget-based neighboring skyline query (BGT-NS query), are presented to determine the NS sets according to user’s specific requirement. A R-tree-based index, the $$R^{a,c}$$-tree, is first designed to manage each type of objects with their locations, attributes, and costs. Then, a simultaneous traversal of the $$R^{a,c}$$-trees built on different types of objects is employed with several pruning criteria to prune the non-qualifying object sets as early as possible, so as to improve the query performance. Extensive experiments using the synthetic dataset demonstrate the efficiency and the effectiveness of the proposed algorithms.

Heterogeneous information networks have drawn much attention in recent years due to their significant applications, such as text mining, e-commerce, social networks, and bioinformatics. Clustering different types of objects simultaneously based upon not only their relations of the same type, but also the relations between different types of objects can improve the clustering quality mutually. In this paper, we propose a general model, in which both the homogeneous and heterogeneous relations are considered simultaneously, to describe the structure of the heterogeneous information networks and devise a novel parametric free multi-type overlapped clustering approach. In this model, different types of relations between different types of objects are represented by a group of matrices. In this way, we transfer the multi-type clustering problem into the information compression problem. Subsequently, greedy search approaches, which aim at describing the group of relational matrices with least bits, are proposed. Moreover, by discovering the discriminative clusters among different types of objects, we devise effective parameter-free strategies to discover either overlapping or non-overlapping structure among different types of clusters. Extensive experiments on real-world and synthetic data sets demonstrate our methods are effective and efficient.

In recent years, the computer vision applications in the robotics have been improved to approach human-like visual perception and scene/context understanding. Following this aspiration, in this study, we explored the possibility of better object manipulation performance by connecting the visual recognition of objects to their physical attributes, such as weight and center of gravity (CoG). To develop and test this idea, an object manipulation platform is built comprising a robotic arm, a depth camera fixed at the top center of the workspace, embedded encoders in the robotic arm mechanism, and microcontrollers for position and force control. Since both the visual recognition and force estimation algorithms use deep learning principles, the test set-up was named as Deep-Table. The objects in the manipulation tests are selected from everyday life and are common to be seen on modern office desktops. The visual object localization and recognition processes are performed from two distinct branches by deep convolutional neural network architectures. We present five of the possible cases, having different levels of information availability on the object weight and CoG in the experiments. The results confirm that using our algorithm, the robotic arm can move different types of objects successfully varying from several grams (empty bottle) to around 250 g (ceramic cup) without failure or tipping. The proposed method also shows that connecting the object recognition with load estimation and contact point further improves the performance characterized by a smoother motion.

Template matching techniques are widely used in many computer vision tasks. Generally, a likelihood value is calculated from similarity measures, however the relation between these measures and the data likelihood is often incorrectly stated. It is clear that accurate likelihood estimation will improve the efficiency of the matching algorithms. This paper introduces a novel method for estimating the likelihood PDFS accurately based on the PDF Projection Theorem, which provides the correct relation between the feature likelihood and the data likelihood, permitting the use of different types of features for different types of objects and still estimating consistent likelihoods. The proposed method removes the normalization and bias problems that are usually associated with the likelihood calculations. We demonstrate that it significantly improves template matching in pose estimation problems. Qualitative and quantitative results are compared against traditional likelihood estimation schemes.

We present a new shape recognition algorithm for binary images based on the morphological approach. The standard algorithms based on the morphological hit-or-miss transform use block structure patterns, but in many practical situations, this may cause problems because the size of the object is unknown. In the proposed method, we match the corners of the object instead of the block structure pattern. Because most objects have different structure elements for the corners, our method gives a more reasonable approach and the size of the object plays a less significant role in our recognition algorithm than in the standard algorithms. Our method can be easily adapted to recognize the features of different types of objects.

Type 1 diabetes mellitus (T1DM) causes cognitive changes in children, which may be due to deficits in brain functions. It is unclear whether T1DM children will have brain functional changes during the initial stage of the disease. We aimed to investigate the changes in the functional brain network topology in children with new-onset T1DM. In this study, 35 new-onset T1DM children and 33 age-, sex-matched healthy controls underwent resting-state fMRI. The whole brain functional connectivity density (FCD) analysis and seed-based functional connectivity (FC) analysis were performed to investigate the changes in functional brain networks in new-onset T1DM children when compared with the controls. Pearson correlational analysis was used to explore the correlation between FCD value of differential brain areas and clinical variables in T1DM children. Compared with the controls, children with new-onset T1DM exhibited significantly decreased FCDs of the right inferior temporal gyrus (ITG) and the right posterior cingulate cortex (PCC). In the subsequent FC analysis, decreased FC was found between right PCC and right cuneus and increased FC was found between right ITG and left orbital part of inferior frontal gyrus in children with new-onset T1DM compared to the controls. The FCD values of right ITG and PCC did not correlate with HbA1c, blood glucose level before imaging, and full-scale intelligence quotient (IQ) in T1DM children. These results revealed that T1DM affect the functional activity of the immature brain at the initial stage. These findings also indicate a decrease in regional brain function and abnormalities in temporal-frontal and limbic-occipital circuitry in children with new-onset T1DM, and highlight the effects of T1DM on children's brain networks involved in visual process and memory, which may contribute to the cognition impairments observed in children with T1DM.

This paper investigates the effects of encumbrance (holding different types of objects while using mobile devices) to understand the interaction difficulties that it causes. An experiment was conducted where participants performed a target acquisition task on a touchscreen mobile phone while carrying different types of bags and boxes. Mobility was also evaluated since people carry items from one place to another. Motion capture hardware was used to track hand and arm postures to examine how holding the different types of objects caused excessive movement and instability therefore resulting in performance to decline. The results showed encumbrance and mobility caused target accuracy to decrease although input while holding the box under the non-dominant arm was more accurate and exerted quicker targeting times than holding no objects. Encumbrance affected the dominant hand more than the non-dominant hand as targeting error significantly increased and caused greater hand instability. The issues caused by encumbrance suggest the topic requires more attention from researchers and users would benefit greatly if better interaction techniques and applications are developed to counteract the problems.

In an object oriented system, different types of objects may have one or more attributes in common. For example different types of objects in a library system might be loanable or catalogued. The first part of the paper introduces a distinction between object types and attribute types, showing that there are advantages in treating them as separate constructs of an object oriented programming language. Then generalized attribute types, (e.g. synchronized, journalized, protected) are discussed. It is shown how implementations involving a technique called bracket routines can lead to clearly modeled and cleanly implemented programs. It is then shown how the bracket technique can be effectively used to introduce protection and security concepts into a system. Among the clear advantages of this technique is that it results in better reusability of code.

There are various kinds of social media information, including different types of objects and relations among these objects, in music social communities such as Last.fm and Pandora. This information is valuable for music recommendation. However, there are two main challenges to exploit this rich social media information: (a) There are many different types of objects and relations in music social communities, which makes it difficult to develop a unified framework taking into account all objects and relations. (b) In these communities, some relations are much more sophisticated than pairwise relation, and thus cannot be simply modeled by a graph. We propose a novel music recommendation algorithm by using both multiple kinds of social media information and music acoustic-based content. Instead of graph, we use hypergraph to model the various objects and relations, and consider music recommendation as a ranking problem on this hypergraph. While an edge of an ordinary graph connects only two objects, a hyperedge represents a set of objects. In this way, hypergraph can be naturally used to model high-order relations.

High-Order Co-Clustering (HOCC) methods have attracted high attention in recent years because of their ability to cluster multiple types of objects simultaneously using all available information. During the clustering process, HOCC methods exploit object co-occurrence information, i.e., inter-type relationships amongst different types of objects as well as object affinity information, i.e., intra-type relationships amongst the same types of objects. However, it is difficult to learn accurate intra-type relationships in the presence of noise and outliers. Existing HOCC methods consider the p nearest neighbours based on Euclidean distance for the intra-type relationships, which leads to incomplete and inaccurate intra-type relationships. In this paper, we propose a novel HOCC method that incorporates multiple subspace learning with a heterogeneous manifold ensemble to learn complete and accurate intra-type relationships. Multiple subspace learning reconstructs the similarity between any pair of objects that belong to the same subspace. The heterogeneous manifold ensemble is created based on two-types of intra-type relationships learnt using p-nearest-neighbour graph and multiple subspaces learning. Moreover, in order to make sure the robustness of clustering process, we introduce a sparse error matrix into matrix decomposition and develop a novel iterative algorithm. Empirical experiments show that the proposed method achieves improved results over the state-of-art HOCC methods for FScore and NMI.

Heterogeneous object co-clustering has become an important research topic in data mining. In early years of this research, people mainly worked on two types of heterogeneous data (denoted by pair-wise co-clustering); while recently more and more attention was paid to multiple types of heterogeneous data (denoted by high- order co-clustering). In this paper, we studied the high- order co-clustering of objects with star-structured interrelationship, i.e., there is a central type of objects that connects the other types of objects. Actually, this case could be a very good model for many real-world applications, such as the co-clustering of Web images, their low-level visual features, and the surrounding text. We used a tripartite graph to represent the interrelationships among different objects, and proposed a consistent information theory which generates an effective algorithm to obtain the co-clusters of different types of objects. Experiments on a Web image show that our proposed algorithm is a better choice compared with previous work on heterogeneous object co-clustering.

The problem of routing between two types of objects is considered. Two variants of the problem statement are considered: with a single point of collection and without it. An important aspect of the routes is the mandatory alternation of different types of objects. A mathematical model of the problem with boolean variables is proposed for each statement. A meaningful statement can be represented as the task of collecting haystacks in trucks afield. Two algorithms are developed to solve this problem. The first one is based on the “greedy” strategies, and the second one is based on the approach of Ant Colony Optimization (ACO) algorithms. To configure the parameters of the second algorithm it is carried out the computational experiment. The results of the experiment are provided. In conclusion, the main results of the work are presented.

The SiamFC target tracking algorithm has attracted extensive attention because of its good balance between speed and performance, but the tracking effect of the SiamFC algorithm is not satisfactory in complex background scenes. When SiamFC algorithm uses deep semantic features for tracking, it has good recognition ability for different types of objects, but it has insufficient discrimination for the same types of objects. Therefore, we propose an effective anti-interference module to improve the discrimination ability of the algorithm. The anti-interference module uses another feature extraction network to extract the features of the candidate target images generated by the SiamFC main network. In addition, we set up the feature vector set to save the feature vectors of the tracking target and the template image. Finally, the tracking target is selected by calculating the minimum cosine distance between the feature vector of the candidate target and the vector in the feature vector set. A large number of experiments show that our anti-interference module can effectively improve the performance of SiamFC algorithm, and the performance of this algorithm can be comparable to the popular algorithms.

Brain activity related to integrative processes in visual object recognition: bottom-up integration and the modulatory influence of stored knowledge

Scene classification from images is a challenging problem in computer vision due to its significant variability of scale, illumination, and view. Recently, Latent Dirichlet Allocation (LDA) model has grown popular in computer vision field, especially in scene labeling and classification. However, the effectiveness of the LDA model for the scene classification has not yet been addressed thoroughly. Especially, there is little experimental evaluation on the model's performance for different types of features. Fusion of multiple types of features is usually necessary in the scene classification due to the complexity of scene images. In this paper, we investigate the effectiveness of the LDA model in scene classification by using 7 types of features (i.e. uniform grid based interest points, Harris corner based interest points, scale invariant feature transform (SIFT), texture, shape, color, and location) and their various combinations. Furthermore, we compare the performance of the LDA model with Support Vector Machine (SVM) classifier. All experiments are performed on the UIUC Sport Scene database. The experiments demonstrate that the performance of the LDA model 1) is significantly lower than the SVM classifier for the scene classification over different types of features; and 2) decreases by fusing multiple features while improvement shown in SVM classifier.