With the rapid development of multiple technologies from the Internet to mobile phones and cameras, visual data is now widely available in huge amounts and great variety, bringing significant opportunities for novel processing of visual information as well as commercial applications.

Non-negative matrix factorization (NMF) is a useful technique to learn a parts-based representation by decomposing the original data matrix into a basis set and coeffcients with non-negative constraints. However, as an unsupervised method, the original NMF cannot utilize the discriminative class information. In this paper, we propose a semi-supervised class-driven NMF method to associate a class label with each basis vector by introducing an inhomogeneous representation cost constraint. This constraint forces the learned basis vectors to represent better for their own classes but worse for the others. Therefore, data samples in the same class will have similar representations, and consequently the discriminability in new representations could be boosted. Some experiments carried out on several standard databases validate the effectiveness of our method in comparison with the state-of-the-art approaches.

We propose a novel method that automatically analyzes stroke-related artistic styles of paintings. A set of adaptive interfaces are also developed to connect the style analysis with existing painterly rendering systems, so that the specific artistic style of a template painting can be effectively transferred to the input photo with minimal effort. Different from conventional texture-synthesis based rendering techniques that focus mainly on texture features, this work extracts, analyzes and simulates high-level style features expressed by artists' brush stroke techniques. Through experiments, user studies and comparisons with ground truth, we demonstrate that the proposed style-orientated painting framework can significantly reduce tedious parameter adjustment, and it allows amateur users to efficiently create desired artistic styles simply by specifying a template painting.

Although many existing movie recommender systems have investigated recommendation based on information such as clicks and tags, much less efforts have been made to explore the multimedia content of movies, which has potential information for the elicitation of the user's visual and musical preferences. In this paper, we explore the content from three media types (image, text, audio) and propose a novel multi-view semi-supervised movie recommendation method, which represents each media type as a view space for movies. The three views of movies are integrated to predict the rating values under the multi-view framework. Furthermore, our method considers the casual users who rate limited movies. The algorithm enriches the user profile with a semi-supervised way when there are only few rating histories. Experiments indicate that the multimedia content analysis reveals the user's profile in a more comprehensive way. Different media types can be a complement to each other for movie recommendation. And the experimental results validate that our semi-supervised method can effectively enrich the user profile for recommendation with limited rating history.

The massive web videos prompt an imperative demand on effciently grasping the major events. However, the distinct characteristics of web videos, such as the limited number of features, the noisy text information, and the unavoidable error in near-duplicate keyframes (NDKs) detection, make web video event mining a challenging task. In this paper, we propose a novel four-stage framework to improve the performance of web video event mining. Data preprocessing is the first stage. Multiple Correspondence Analysis (MCA) is then applied to explore the correlation between terms and classes, targeting for bridging the gap between NDKs and high-level semantic concepts. Next, co-occurrence information is used to detect the similarity between NDKs and classes using the NDK-within-video information. Finally, both of them are integrated for web video event mining through negative NDK pruning and positive NDK enhancement. Moreover, both NDKs and terms with relatively low frequencies are treated as useful information in our experiments. Experimental results on large-scale web videos from YouTube demonstrate that the proposed framework outperforms several existing mining methods and obtains good results for web video event mining.

The problem of detecting community structures of a social network has been extensively studied over recent years, but most existing methods solely rely on the network structure and neglect the context information of the social relations. The main reason is that a context-rich network offers too much flxibility and complexity for automatic or manual modulation of the multifaceted context in the analysis process. We address the challenging problem of incorporating context information into the community analysis with a novel visual analysis mechanism. Our approach consists of two stages: interactive discovery of salient context, and iterative context-guided community detection. Central to the analysis process is a context relevance model (CRM) that visually characterizes the influence of a given set of contexts on the variation of the detected communities, and discloses the community structure in specific context configurations. The extracted relevance is used to drive an iterative visual reasoning process, in which the community structures are progressively discovered. We introduce a suite of visual representations to encode the community structures, the context as well as the CRM. In particular, we propose an enhanced parallel coordinates representation to depict the context and community structures, which allows for interactive data exploration and community investigation. Case studies on several datasets demonstrate the effciency and accuracy of our approach.

With the rapid progress of the network and mobile techniques, mobile devices such as mobile phones and portable devices, have become one of the most important parts in common life. Effcient techniques for watching, navigating and sharing videos on mobile devices collaboratively are appealing in mobile environment. In this paper, we propose a novel approach supporting effciently collaborative operations on videos with sketch gestures. Furthermore, effective collaborative annotation and navigation operations are given to interact with videos on mobile devices for facilitating users' communication based on mobile devices' characteristics. Gesture operation and collaborative interaction architecture are given and improved during the interactive process. Finally, a user study is conducted showing that the effectivity and collaborative accessibility of video exploration is improved.

Tracking objects that undergo abrupt appearance changes and heavy occlusions is a challenging problem which conventional tracking methods can barely handle. To address the problem, we propose an online structure learning algorithm that contains three layers: an object is represented by a mixture of online structure models (OSMs) which are learnt from block-based online random forest classifiers (BORFs). BORFs are able to handle occlusion problems since they model local appearances of the target. To further improve the tracking accuracy and reliability, the algorithm utilizes mixture relational models (MRMs) as multi-mode context information to integrate BORFs into OSMs. Furthermore, the mixture construction of OSMs can avoid over-fitting effectively and is more flxible to describe targets. Fusing BORFs with MRMs, OSMs capture the discriminative parts of the target, which guarantees the reliability and robustness of our tracker. In addition, OSMs incorporate with block occlusion reasoning to update our BORFs and MRMs, which can deal with appearance changes and drifting problems effectively. Experiments on challenging videos show that the proposed tracker performs better than several state-of-the-art algorithms.

We present a framework for example-based texture synthesis with feature directions aligned to vector fields with 2-way rotational symmetry, also known as orientation fields. Through a simple variational formulation, the framework allows the user to design the orientation field with intuitive controls, by interactively manipulating singularities and field directions. The resulting field is then used to guide a parallel synthesis. Our contribution is twofold: a design tool for orientation fields with a natural boundary condition, and a parallel texture synthesis adapted specifically for using such fields in feature alignment. We demonstrate the advantages of the procedure through examples on planar and curved patches with trivial topology.

Content-based shape retrieval techniques can facilitate 3D model resource reuse, 3D model modeling, object recognition, and 3D content classification. Recently more and more researchers have attempted to solve the problems of partial retrieval in the domain of computer graphics, vision, CAD, and multimedia. Unfortunately, in the literature, there is little comprehensive discussion on the state-of-the-art methods of partial shape retrieval. In this article we focus on reviewing the partial shape retrieval methods over the last decade, and help novices to grasp latest developments in this field. We first give the definition of partial retrieval and discuss its desirable capabilities. Secondly, we classify the existing methods on partial shape retrieval into three classes by several criteria, describe the main ideas and techniques for each class, and detailedly compare their advantages and limits. We also present several relevant 3D datasets and corresponding evaluation metrics, which are necessary for evaluating partial retrieval performance. Finally, we discuss possible research directions to address partial shape retrieval.

Visual analytics employs interactive visualizations to integrate users' knowledge and inference capability into numerical/algorithmic data analysis processes. It is an active research field that has applications in many sectors, such as security, finance, and business. The growing popularity of visual analytics in recent years creates the need for a broad survey that reviews and assesses the recent developments in the field. This report reviews and classifies recent work into a set of application categories including space and time, multivariate, text, graph and network, and other applications. More importantly, this report presents analytics space, inspired by design space, which relates each application category to the key steps in visual analytics, including visual mapping, model-based analysis, and user interactions. We explore and discuss the analytics space to add the current understanding and better understand research trends in the field.

The HP model for protein structure prediction abstracts the fact that hydrophobicity is a dominant force in the protein folding process. This challenging combinatorial optimization problem has been widely addressed through metaheuristics. The evaluation function is a key component for the success of metaheuristics; the poor discrimination of the conventional evaluation function of the HP model has motivated the proposal of alternative formulations for this component. This comparative analysis inquires into the effectiveness of seven different evaluation functions for the HP model. The degree of discrimination provided by each of the studied functions, their capability to preserve a rank ordering among potential solutions which is consistent with the original objective of the HP model, as well as their effect on the performance of local search methods are analyzed. The obtained results indicate that studying alternative evaluation schemes for the HP model represents a highly valuable direction which merits more attention.

In this paper, we present a simultaneous segmentation algorithm for multiple highly-occluded objects, which combines high-level knowledge and low-level information in a unified framework. The high-level knowledge provides sophisticated shape priors with the consideration of blocking relationship between nearby objects. Different from conventional layered model which attempts to solve the full ordering problem, we decompose the problem into a series of pairwise ones and this makes our algorithm scalable to a large number of objects. Objects are segmented in pixel level with higher-order soft constraints from superpixels, by a dual-level conditional random field. The model is optimized alternately by object layout and pixel-wise segmentation. We evaluate our system on different objects, i.e., clothing and pedestrian, and show impressive segmentation results and significant improvement over state-of-the-art segmentation algorithms.

Unknown words are one of the key factors that greatly affect the translation quality. Traditionally, nearly all the related researches focus on obtaining the translation of the unknown words. However, these approaches have two disadvantages. On the one hand, they usually rely on many additional resources such as bilingual web data; on the other hand, they cannot guarantee good reordering and lexical selection of surrounding words. This paper gives a new perspective on handling unknown words in statistical machine translation (SMT). Instead of making great efforts to find the translation of unknown words, we focus on determining the semantic function of the unknown word in the test sentence and keeping the semantic function unchanged in the translation process. In this way, unknown words can help the phrase reordering and lexical selection of their surrounding words even though they still remain untranslated. In order to determine the semantic function of an unknown word, we employ the distributional semantic model and the bidirectional language model. Extensive experiments on both phrase-based and linguistically syntax-based SMT models in Chinese-to-English translation show that our method can substantially improve the translation quality.

Co-analyzing a set of 3D shapes is a challenging task considering a large geometrical variability of the shapes. To address this challenge, this paper proposes a new automatic 3D shape co-segmentation algorithm by using spectral graph method. Our method firstly represents input shapes as a set of weighted graphs and extracts multiple geometric features to measure the similarities of faces in each individual shape. Secondly all graphs are embedded into the spectral domain to find meaningful correspondences across the set. After that we build a joint weighted matrix for the graph set and then apply normalized cut criterion to find optimal co-segmentation of the input shapes. Finally we evaluate our approach on different categories of 3D shapes, and the experimental results demonstrate that our method can accurately co-segment a wide variety of shapes, which may have different poses and significant topology changes.