Search

Relatedness measurement between multimedia such as images and videos plays an important role in computer vision, which is a base for many multimedia related applications including clustering, searching, recommendation, and annotation. Recently, with the explosion of social media, users can upload media data and annotate content with descriptive tags. In this paper, we aim at measuring the semantic relatedness of Flickr images. Firstly, four information theory based functions are used to measure the semantic relatedness of tags. Secondly, the integration of tags pair based on bipartite graph is proposed to remove the noise and redundancy. Thirdly, the order information of tags is added to measure the semantic relatedness, which emphasizes the tags with high positions. The data sets including 1000 images from Flickr are used to evaluate the proposed method. Two data mining tasks including clustering and searching are performed by the proposed method, which shows the effectiveness and robustness of the proposed method. Moreover, some applications such as searching and faceted exploration are introduced using the proposed method, which shows that the proposed method has broad prospects on web based tasks.

Visual relationship detection, as a challenging task used to find and distinguish interactions between object-pairs in one image, has received much attention recently. In this work, we devise a unified visual relationship detection framework with two types of correlation exploitation to address the combination explosion problem in the object-pairs proposing stage and the non-exclusive label problem in the predicate recognition stage. In the object-pairs proposing stage, with the exploitation of relative location correlation between two objects in one pair, one location-embedded rating module (LRM) is developed to effectively select plausible proposals. In the predicate recognition stage, one label-correlation graph module (LGM) is introduced to measure the implicit semantic correlation among predicates; and then assign discrete distributed labels to predicates to improve the precision of top-n recall. Experiments on the two widely used VRD and VG datasets show that our proposed method outperforms current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Hashing has been widely used in large-scale image retrieval based on approximate nearest neighbor search. Most learning-to-hashing methods adopt a two-stage algorithm to generate binary codes. First, original images are mapped into continuous visual features. Then, binary codes are generated by quantization step or separate projection. Nevertheless, these methods are sensitive to quantization operation, i.e., thresholding. To explicitly address this issue, this study proposes a novel feature quantization scheme with a loopy recurrent neural network, called loopy residual hashing, for the purpose of high accuracy in image retrieval. Instead of one-off thresholding-based feature binarization, the proposed approach performs an iterative threshold-then-approximate operation, which calculates the quantization residual after each thresholding step and then imitates another round of binarization to further approximate the coding residual. The resulting sequences of binary codes possess higher representation accuracy and extensive experiments on image retrieval demonstrate its superior discriminative capability over the prior art. In the meantime, theoretical approximation error analysis is given. [ABSTRACT FROM AUTHOR]

Hashing is a widely adopted method based on an approximate nearest neighbor search and is used in large-scale image retrieval tasks. Conventional learning-based hashing algorithms employ end-to-end representation learning, which is a one-off technique. Because of the tradeoff between efficiency and performance, conventional learning-based hashing methods must sacrifice code length to improve performance, which increases their computational complexity. To improve the efficiency of binary codes, motivated by the “nonsalient-to-salient” attention scheme of humans, we propose a recursive hashing mechanism that maps progressively expanded salient regions to a series of binary codes. These salient regions are generated by a conventional saliency model based on bottom-up saliency-driven attention and a semantic-guided saliency model based on top-down task-driven attention. After obtaining a series of salient regions, we perform long-range temporal modeling of salient regions using a graph-based recurrent deep network to obtain more refined representative features. The later output nodes inherit aggregated information from all previous nodes and extract discriminative features from more salient regions. Therefore, this network possesses more significant information and satisfactory scalability. The proposed recursive hashing neural network, optimized by a triplet ranking loss, is end-to-end trainable. Extensive experimental results from several image retrieval benchmarks show the scalability of our method and demonstrate its strong performance compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Association link network (ALN) can organize massive Web information to provide many intelligent services in our big data society. Effective semantic layered technologies not only can provide theoretical support for knowledge discovery in Web resources, but also can improve the searching efficiency of related information systems such as Web information system and industrial information system. How to realize the layer division of association semantic by the hierarchy analysis of ALN is an important research topic. To solve this problem, this paper proposes a hierarchy-cutting model of association semantic. First, experiments of four types of keywords with different linking roles are conducted to discover the possible distribution law. Experimental results show that these keywords with association role reveal previous power-law distribution. Then, based on the discovered power-law distribution, up-cutting and down-cutting points are presented to divide the association semantic into three layers. At the same time, theories of the hierarchy-cutting model are presented. Finally, examples of current core topic and permanent topics belonging to a domain are given. The experiments show that hierarchy-cutting points have high accuracy. The multilayer theory of association semantic can provide a theoretical support for knowledge recommendation with different particle sizes on ALNs. [ABSTRACT FROM PUBLISHER]

Video surveillance is an integrated system with strong prevention capabilities and widely used in military, customs, police, fire fighting, airports, railways, urban transport and many other public places. It's an important part of security system because of its visualized, accurate, timely and rich information content. Video surveillance has become the main tool due to its rich, intuitive and accurate information. However, with the large-scale construction of video surveillance systems all over the world, problems such as 'useful information and clues cannot be found immediately with video big data' decrease detecting efficiency during crime prediction and public security governance. The increasing need of video based applications issues the importance of parsing and organizing the content in videos. However, the accurate understanding and managing video contents at the semantic level is still insufficient. The semantic gap between low level features and high level semantics cannot be bridged by manual or semi-automatic methods. In this paper, a semantic based model named video structural description (VSD) for representing and organizing the content in videos is introduced firstly. Video structural description aims at parsing video content into the text information, which uses spatiotemporal segmentation, feature selection, object recognition, and semantic web technology. The applications of VSD technology on public security from surveillance videos are given. The intelligent analysis of person and vehicle from surveillance video based on VSD is presented. The cloud enhanced platform managing surveillance videos is also given. At last, applications using VSD are introduced. [ABSTRACT FROM AUTHOR]

Recently, the number of surveillance video data has grown enormously since the popularity of the smart cities, which brings the difficulties to users for searching and analyzing the content of the videos. These video data are not limited to data anymore, which provide the effective information for criminal investigation systems, intrusion detection system, and many others. However, as the number of available cloud services increases, the problem of data discovery and selection arises. The semantic technology is an effective choice for enhancing the accurate of the data searching and analyzing process. In this paper, a semantic based cloud environment is proposed to facilitate the analyzing and searching process of surveillance video data. An architecture integrating ontology building, semantic annotation, and semantic search is proposed to leverage the semantic description of the video data to find them from concept-based level. A semantic intermediate layer which organizes the video data based on their semantic relations is given. Moreover, the proposed method is used in the intelligent transportation field, which shows the bright prospect of the proposed method in real applications. [ABSTRACT FROM AUTHOR]

Today, video surveillance technology is playing a more and more important role in traffic detection. Vehicle’s static properties are crucial information in examining criminal and traffic violations. With the development of video surveillance technology, it has been wildly used in the traffic monitoring. Image and video resources play an important role in traffic events analysis. With the rapid growth of the video surveillance devices, a large number of image and video resources are increasingly being created. It is crucial to explore, share, reuse, and link these multimedia resources for better organizing traffic events. Most of the video resources are currently annotated in an isolated way, which means that they lack semantic connections. Thus, providing the facilities for annotating these video resources is highly demanded. These facilities create the semantic connections among video resources and allow their metadata to be understood globally. Adopting semantic technologies, this paper introduces a video annotation platform. The platform enables user to semantically annotate video resources using vocabularies defined by traffic events ontologies. Moreover, the platform provides the search interface of annotated video resources. The result of initial development demonstrates the benefits of applying semantic technologies in the aspects of reusability, scalability, and extensibility. [ABSTRACT FROM AUTHOR]

SUMMARY Association relations between concepts are a class of simple but powerful regularities in binary data, which play important roles in enterprises and organizations with huge amounts of data. However, although there can be easily large number of association relation mined from databases, since existing objective and subjective methods scarcely take semantics into consideration, it has been recognized early in the knowledge discovery literature that most of them are of no interest to the user. In this paper, the semantic discrimination capability (SDC) of association relation is measured based on discrimination value model first. The formula of SDC integrating both statistical and graph features is proposed from five different strategies. The high correlation coefficient of the proposed method against discrimination value shows that the proposed SDC measure is accuracy. Moreover, an application using SDC on document clustering is carried out, which shows that SDC has broad prospects on data-related task such as document clustering. Copyright 2013 John Wiley © Sons, Ltd. [ABSTRACT FROM AUTHOR]