Interactive tool for image annotation using a semi-supervised and hierarchical approach

This paper presents a semi-automatic tool, called IGAnn (Interactive image ANNotation), that assists users in annotating textual labels with images. IGAnn performs an interactive retrieval-like procedure: the system presents the user with images that have higher confidences, and then the user determines which images are actually relevant or irrelevant for a specified label. By collecting relevant and irrelevant images of iterations, a hierarchical classifier associated with the specified label is built using our proposed semi-supervised approach to compute confidence values of unlabeled images. This paper describes the system interface of IGAnn and also demonstrates quantitative experiments of our proposed approach.     

SPOID: a system to produce spot-the-difference puzzle images with difficulty

Spot-the-difference is a type of puzzles, where users try to find the different parts of two perceptually similar but actually different images. We propose a semi-automatic system to produce various spot-the-difference puzzle images tagged with their difficulties from a single input image. First, we extract regions to modify from the input by our modified maximal similarity-based region merging algorithm with little user intervention and then apply a variety of image editing techniques for each region to create a modified image. We evaluate the difficulty of a pair of the input and the modified images by considering the saliency and the perceptual difference of the modified region. We provide an empirical model to estimate the time to solve a pair of the images with respect to its difficulty. We show our experimental results and quantitative user research results to evaluate the effectiveness of the proposed method.     

目标检测数据集半自动生成技术研究

目标检测广泛使用于计算机视觉领域.在不同的场景中,我们需要使用不同的数据集训练模型.但是,人工生成数据集标签非常耗时.本文提出一种半自动的方法生成数据集标签,然后按照图像相似度设置的阈值自动筛选,最后保留符合要求的图像和对应的标签作为最终的数据集.实验表明,该方法可以提高数据集生成标签的速度,同时确保了准确率.     

Exploring album structure for face recognition in online social networks

In this paper, we propose an album-oriented face-recognition model that exploits the album structure for face recognition in online social networks. Albums, usually associated with pictures of a small group of people at a certain event or occasion, provide vital information that can be used to effectively reduce the possible list of candidate labels. We show how this intuition can be formalized into a model that expresses a prior on how albums tend to have many pictures of a small number of people. We also show how it can be extended to include other information available in a social network. Using two real-world datasets independently drawn from Facebook, we show that this model is broadly applicable and can significantly improve recognition rates.     

基于特征映射的微博用户标签兴趣聚类方法

针对现有的用户兴趣聚类方法没有考虑用户标签之间存在的语义相关性问题,提出了一种基于特征映射的微博用户标签兴趣聚类方法。首先,获取待分析用户及其所关注用户的用户标签,选取出现频数高于设定阈值的标签构建模糊矩阵的特征维;然后,考虑标签之间的语义相关性,利用特征映射的思想将用户标签根 据其与特征维标签之间的语义相似度映射到每个特征维下,计算每个特征维所对应的特征值;最后,利用模糊聚类得到了不同阈值下的用户兴趣聚类结果。实验结果表明,本文提出的基于特征映射的微博用户标签兴趣聚类方法有效地改善了用户兴趣聚类效果。     

Go anywhere: user-verifiable authentication over distance-free channel for mobile devices

Current mobile technology gives us ubiquitous services with personal mobile devices such as smart phones, tablet PCs, and laptops. With these mobile devices, the human users may wish to exchange sensitive data with others (e.g., their friends or their colleagues) over a secure channel. Public key cryptography is a good solution for establishing this secure channel. However, it is vulnerable to man-in-the-middle attack, if the entities have no shared information. A number of techniques based on human-assisted out-of-band channels have been proposed to solve this problem. Unfortunately, these works have a common shortcoming: The human users must be colocated in close proximity. In this paper, we focus on how to construct a distance-free channel, which is not location-limited for establishing a secure channel between two users (devices). The proposed distance-free channel provides identification and authentication of the devices at the different locations using taken pictures or pre-stored images. The human user participates in the authentication process by sending and verifying an image. We describe the prototype implementation operated on a smart phone and show the experimental results when actually two smart phones share a common key using Diffie–Hellman key agreement over the proposed distance-free channel.     

A photomosaic image generation method using photo annotation in a social network environment

With the growing use of social networking services, various applications have been developed to utilize their vast capabilities. Photomosaic techniques, which combine many images to create a new rendering of an input image, can benefit from the capabilities of social networks. In this study, we propose a method that generates a photomosaic image by considering social network context. Our algorithm creates a photomosaic that incorporates photos posted by other users in the users network . We enable the matching function to easily select photos from the albums of users who are connected to the owner of the input image, by computing the closeness of those connections. Moreover, our technique allows the photos in the albums of friends who are annotated in the source image to be matched more effectively.     

Automated analysis of images in documents for intelligent document search

Authors use images to present a wide variety of important information in documents. For example, two-dimensional (2-D) plots display important data in scientific publications. Often, end-users seek to extract this data and convert it into a machine-processible form so that the data can be analyzed automatically or compared with other existing data. Existing document data extraction tools are semi-automatic and require users to provide metadata and interactively extract the data. In this paper, we describe a system that extracts data from documents fully automatically, completely eliminating the need for human intervention. The system uses a supervised learning-based algorithm to classify figures in digital documents into five classes: photographs, 2-D plots, 3-D plots, diagrams, and others. Then, an integrated algorithm is used to extract numerical data from data points and lines in the 2-D plot images along with the axes and their labels, the data symbols in the figure’s legend and their associated labels. We demonstrate that the proposed system and its component algorithms are effective via an empirical evaluation. Our data extraction system has the potential to be a vital component in high volume digital libraries.     

Topic-tracking-based dynamic user modeling with TV recommendation applications

One of the challenging issues in TV recommendation applications based on implicit rating data is how to make robust recommendation for the users who irregularly watch TV programs and for the users who have their time-varying preferences on watching TV programs. To achieve the robust recommendation for such users, it is important to capture dynamic behaviors of user preference on watched TV programs over time. In this paper, we propose a topic tracking based dynamic user model (TDUM) that extends the previous multi-scale dynamic topic model (MDTM) by incorporating topic-tracking into dynamic user modeling. In the proposed TDUM, the prior of the current user preference is estimated as a weighted combination of the previously learned preferences of a TV user in multi-time spans where the optimal weight set is found in the sense of the evidence maximization of the Bayesian probability. So, the proposed TDUM supports the dynamics of public users’ preferences on TV programs for collaborative filtering based TV program recommendation and the highly ranked TV programs by similar watching taste user group (topic) can be traced with the same topic labels epoch by epoch. We also propose a rank model for TV program recommendation. In order to verify the effectiveness of the proposed TDUM and rank model, we use a real data set of the TV programs watched by 1,999 TV users for 7 months. The experiment results demonstrate that the proposed TDUM outperforms the Latent Dirichlet Allocation (LDA) model and the MDTM in log-likelihood for the topic modeling performance, and also shows its superiority compared to LDA, MDTM and Bayesian Personalized Rank Matrix Factorization (BPRMF) for TV program recommendation performance in terms of top-N precision-recall.     

Robust event discovery from photo collections using Signature Image Bases (SIBs)

Analyzing personal photo albums for understanding the related events is an emerging trend. A reliable event recognition tool could suggest appropriate annotation of pictures, provide the context for single image classification and tagging, achieve automatic selection and summarization, ease organization and sharing of media among users. In this paper, a novel method for fast and reliable event-type classification of personal photo albums is presented. Differently from previous approaches, the proposed method does not process photos individually but as a whole, exploiting three main features, namely Saliency, Gist, and Time, to extract an event signature, which is characteristic for a specific event type. A highly challenging database containing more than 40.000 photos belonging to 19 diverse event-types was crawled from photo-sharing websites for the purpose of modeling and performance evaluation. Experimental results showed that the proposed approach meets superior classification accuracy with limited computational complexity.     

Neural TV program recommendation with label and user dual attention

TV program recommendation is very important for users to find interesting TV programs and avoid confusing users with a lot of information. Currently, they are basically traditional collaborative filtering algorithms, which only recommend through the interactive data between users and programs ignoring the important value of some auxiliary information. In addition, the neural network method based on attention mechanism can well capture the relationship between program labels to obtain accurate program and user representations. In this paper, we propose a neural TV program recommendation with label and user dual attention (NPR-LUA), which can focus on auxiliary information in program and user modules. In the program encoder module, we learn the auxiliary information from program labels through neural networks and word attention to identify important program labels. In the user encoder module, we learn the user representation through the programs that the user watches and use personalized attention mechanism to distinguish the importance of programs for each user. Experiments on real data sets show that our method can effectively improve the effectiveness of TV program recommendations than other existing models.

     

在线社交网络中延伸访问控制机制研究

针对社交网络中用户发布的数据延伸不可控的问题,提出了一种基于隐私标签的延伸控制机制。该机制基于用户关系跳数和资源转发跳数给用户和数据分配不同类型的隐私标签,以实现对数据的细粒度延伸访问控制。提出了隐私标签的生成算法和分配方法,设计了隐私标签约束规则并对可能出现的策略冲突进行分析。最后通过测试,表明了该机制可以实现社交网络中细粒度延伸控制,同时证明了该机制的安全性和有效性。     

Browsing museum image collections on a multi-touch table

In this paper we present a multi-touch tabletop system for browsing image databases, conceived for museums and art gallery exhibitions. The system exploits an innovative image browsing paradigm and image retrieval functionalities to perform natural and intuitive user interaction: users can explore the image database by handling digital pictures by means of touch gestures or by the use of a predetermined set of physical objects; once one of these objects is placed on the table, it is automatically recognized and the associated function is triggered. The set of objects and the function associations can be dynamically configured. An innovative feature of our application is that users can interactively create and manipulate image clusters where images are grouped according to their pictorial similarity. This is achieved by placing one or more specific tangible objects on the table surface. The system has been evaluated on a collection of photos organized in groups according to the UNESCO picture categories. The usability tests, performed considering different user categories, show that users consider the application to be attractive and interesting.     

面向移动端基于社交关系的图片缓存替换算法

随着移动终端深入人们的生活,移动社交APP得到了广泛使用。在移动社交APP中往往会使用大量的图片资源,如微信朋友圈、Instagram的图片分享等。在APP中浏览图片会消耗较多的网络流量,影响加载速度,因此大部分APP采用首先显示缩略图,根据用户需求再加载原图的策略。在服务器端也采用缓存技术来加快缩略图产生时间,减少磁盘I/O。但是,当前的缓存机制更多关注的是缓存的访问频率、最近访问时间等因素,并没有过多关注数据生成用户之间的社交关系,也没有考虑移动用户对缩略图和原图的不同访问模式。把缓存划分为两个部分:缩略图缓存区和原图缓存区,提出了基于社交关系的图片缓存替换算法,在传统缓存替换算法的基础上增加用户的社交关系以及缩略图和原图的关联关系,通过计算图片的缓存价值进行缓存替换。实验表明,所提出的基于社交关系的图片缓存替换算法对于缩略图和原图的缓存命中率都有明显提高。     

基于权邻域的代表性用户抽样算法

代表性用户抽样方法在社会网络分析领域中得到广泛的应用，如何使其抽取的子集代表网络中所有用户具有重要的研究意义。现有方法较少关注网络拓扑结构中用户潜在的大量有用信息，通过对统计分层抽样模型进行优化，提出了一种基于权邻域的代表性用户抽样算法。为了从网络拓扑结构中获得用户更多有价值的内容，该算法使用权邻域对用户代表度计算方法进行改进，同时与用户属性相结合。之后根据用户属性值将用户分成不同属性组，计算用户在每个属性组的代表度。接着通过质量函数来衡量代表性用户的代表程度。采用启发式贪心算法抽取代表性用户。在4个数据集上与6种传统抽样算法进行实验比较，结果表明基于权邻域的代表性用户抽样算法在精确率、召回率和F1-Measure评价指标上均有提升。     

UX Curve: A method for evaluating long-term user experience

The goal of user experience design in industry is to improve customer satisfaction and loyalty through the utility, ease of use, and pleasure provided in the interaction with a product. So far, user experience studies have mostly focused on short-term evaluations and consequently on aspects relating to the initial adoption of new product designs. Nevertheless, the relationship between the user and the product evolves over long periods of time and the relevance of prolonged use for market success has been recently highlighted. In this paper, we argue for the cost-effective elicitation of longitudinal user experience data. We propose a method called the “UX Curve” which aims at assisting users in retrospectively reporting how and why their experience with a product has changed over time. The usefulness of the UX Curve method was assessed in a qualitative study with 20 mobile phone users. In particular, we investigated how users’ specific memories of their experiences with their mobile phones guide their behavior and their willingness to recommend the product to others. The results suggest that the UX Curve method enables users and researchers to determine the quality of long-term user experience and the influences that improve user experience over time or cause it to deteriorate. The method provided rich qualitative data and we found that an improving trend of perceived attractiveness of mobile phones was related to user satisfaction and willingness to recommend their phone to friends. This highlights that sustaining perceived attractiveness can be a differentiating factor in the user acceptance of personal interactive products such as mobile phones. The study suggests that the proposed method can be used as a straightforward tool for understanding the reasons why user experience improves or worsens in long-term product use and how these reasons relate to customer loyalty.     

基于移动设备的个人云服务及资源Mashup

个人用户家庭或工作环境中的智能手机、个人电脑、智能相册等通过网络形成个人云,为个人的数据处理和共享带来了便利。然而,如何面向具体应用需求为用户提供方便、高效的个人云服务及资源整合仍然是一个亟待解决的问题。为此,提出了一种基于移动设备的个人云服务及资源Mashup框架来统一管理设备和描述服务及资源,并阐述了如何通过框架合理构建Mashup应用;此外,开发了基于Agent的框架实现以及Android客户端。基于该框架及客户端,用户可以通过整合个人云服务及资源方便、快捷地构造个人化应用。通过一个用户案例研究对所提出的Mashup框架及其实现的有效性和易用性进行了评估。     

Interactive 3D reconstruction from multiple images: A primitive-based approach

This paper proposes a fast and stable image-based modeling method which generates 3D models with high-quality face textures in a semi-automatic way. The modeler guides untrained users to quickly obtain 3D model data via several steps of simple user interface operations using predefined 3D primitives. The proposed method contains an iterative non-linear error minimization technique in the model estimation step with an error function based on finite line segments instead of infinite lines. The error corresponds to the difference between the observed structure and the predicted structure from current model parameters. Experimental results on real images validate the robustness and the accuracy of the algorithm.     

Discovering Typed Communities in Mobile Social Networks

Mobile social networks,which consist of mobile users who communicate with each other using cell phones,are reflections of people’s interactions in social lives.Discovering typed communities(e.g.,family communities or corporate communities) in mobile social networks is a very promising problem.For example,it can help mobile operators to determine the target users for precision marketing.In this paper we propose discovering typed communities in mobile social networks by utilizing the labels of relationships between users.We use the user logs stored by mobile operators,including communication and user movement records,to collectively label all the relationships in a network,by employing an undirected probabilistic graphical model,i.e.,conditional random fields.Then we use two methods to discover typed communities based on the results of relationship labeling:one is simply retaining or cutting relationships according to their labels,and the other is using sophisticated weighted community detection algorithms.The experimental results show that our proposed framework performs well in terms of the accuracy of typed community detection in mobile social networks.