Ming Cheung

Connection Discovery Using Big Data of User-Shared Images in Social Media

Billions of user-shared images are generated by individuals in many social networks today, and this particular form of user data is widely accessible to others due to the nature of online social sharing. When user social graphs are only accessible to exclusive parties, these user-shared images are proved to be an easier and effective alternative to discover user connections. This work investigated over 360 000 user shared images from two social networks, Skyrock and 163 Weibo, in which 3 million follower/ followee relationships are involved. It is observed that the shared images from users with a follower / followee relationship show relatively higher similarities . A multimedia big data system that utilizes this observed phenomenon is proposed as an alternative to user- generated tags and social graphs for follower/followee recommendation and gender identification. To the best of our knowledge, this is the first attempt in this field to prove and formulate such a phenomenon for mass user-shared images along with more practical prediction methods. These findings are useful for information or services recommendations in any social network with intensive image sharing, as well as for other interesting personalization applications, particularly when there is no access to those exclusive user social graphs.

Non-user Generated Annotation on User Shared Images for Connection Discovery

Social graphs, representing the online friendships among users, are one of the most fundamental types of data for many social media applications, such as recommendation, virality prediction and marketing. However, this data may be unavailable due to the privacy concerns of users, or kept privately by social network operators, which makes such applications difficult. One of the possible solutions to discover user connections is to use shared content, especially images on online social networks, such as Flickr and Instagram. This paper investigates how non-user generated labels annotated on shared images can be used for connection discovery with different color-based and feature-based methods. The label distribution is computed to represent users, and followee/follower relationships are recommended based on the distribution similarity. These methods are evaluated with over 200k images from Flickr and it is proven that with non-user generated labels, user connections can be discovered, regardless of the method used. Feature-based methods are also proven to be 95% better than color-based methods, and 65% better than tag-based methods.

A Cloud-Assisted Framework for Bag-of-Features Tagging in Social Networks

Recently, Bag-of-Features Tagging is proven to be an alternative to discover user connections from user shared images in social networks. This approach used unsupervised clustering to classify the user shared images and then correlate similar user, which is computationally intensive for real-world applications. This paper introduces a cloud-assisted framework to improve the efficiency and scalability of Bag-of-Features Tagging. The framework distributes the computation of the unsupervised clustering, the profile learning process and also the similarity calculation. The experiment proves how a scalable cloud-assisted framework outperforms a stand-alone machine with different parameters on a real social network dataset, Skyrock.

Visual Background Recommendation for Dance Performances Using Dancer-Shared Images

Dance performances use body gestures as a language to express emotion, and lighting and background images on the stage to create the scene and atmosphere. In conventional dance performances, the background images are usually selected or designed by professional stage designers according to the theme and the style of the dance. In new media dance performances, the stage effects are usually generated by media editing software. Selecting or producing a dance background is quite troublesome, and is generally carried out by skilled technicians. The goal of the research reported in this paper is to ease this process, meaning dancers can set background images for their dance performances without the need for stage designers. Instead of searching for background images from the sea of available resources, dancers are recommended images they are more likely to use. This paper proposes the idea of a novel system to recommend images based on content-based social computing. A model to predict a dancers interests in candidate images through social platforms, e.g., Pinterest, is proposed. With the help of such a system, dancers can select from the recommended images and set them as the backgrounds of their dance performances through a media editor. To the best of our knowledge, this would be the first dance background recommendation system for dance performances.

Analytics-Driven Visualization on Digital Directory via Screen-Smart Device Interactions

Informative directories have always responded to a fundamental need of humanity: providing available information around people. However, the escalating amount of content to be visualized on directories makes relevant information search extremely time-consuming. Meanwhile, digital displays based on screen-smart device interaction become an emerging interface of smart services to deal with daily-life challenges like information seeking. Also, multimedia content, such as movies, can be understood by multimedia analytics for recommendation, but there is no effective way to visualize the content of a directory. This paper proposes a novel directory visualization framework, called analytics-driven dynamic visualization on digital directory (AVDD): understanding user preferences via smartphone-based interaction and optimizing visualization by visual analytics in terms of high content relevancy and screen utilization for advanced directories. With experiments in laboratory and real-world settings, AVDD is proven to be effective for visualizing directory with screen utilization over 98% and the score for Likert-scale surveys achieving 73% on average in a movie directory.

Cyber-physical Directory: A Dynamic Visualization of Social Media Data

Information about people, places and events are examples of social data. These social data, widely spread on the Internet, are also displayed by directories directly in the physical world, enhancing interactivity and guiding people at a specific location. However, they are usually large, and reading these directories is time-consuming because they are not personalized, with information unrelated to a persons needs. Moreover these social data are static and may be irrelevant for many readers. This paper presents a new cyber-physical system: the cyber-physical directory, which provides a user with a customised and dynamic visualization of social data. An algorithm, based on the similarity between people and social data, finds which data are relevant to a specific user and displays them by using tag cloud techniques. The system is successfully tested with a real dataset from Foursquare, and an implementation is presented.

DeepArt: Learning Joint Representations of Visual Arts

This paper aims to generate a better representation of visual arts, which plays a key role in visual arts analysis works. Museums and galleries have a large number of artworks in the database, hiring art experts to do analysis works (e.g., classification, annotation) is time consuming and expensive and the analytic results are not stable because the results highly depend on the experiences of art experts. The problem of generating better representation of visual arts is of great interests to us because of its application potentials and interesting research challenges---both content information and each unique style information within one artwork should be summarized and learned when generating the representation. For example, by studying a vast number of artworks, art experts summary and enhance the knowledge of unique characteristics of each visual arts to do visual arts analytic works, it is non-trivial for computer. In this paper, we present a unified framework, called DeepArt, to learn joint representations that can simultaneously capture contents and style of visual arts. This framework learns unique characteristics of visual arts directly from a large-scale visual arts dataset, it is more flexible and accurate than traditional handcraft approaches. We also introduce Art500k, a large-scale visual arts dataset containing over 500,000 artworks, which are annotated with detailed labels of artist, art movement, genre, etc. Extensive empirical studies and evaluations are reported based on our framework and Art500k and all those reports demonstrate the superiority of our framework and usefulness of Art500k. A practical system for visual arts retrieval and annotation is implemented based on our framework and dataset. Code, data and system are publicly available at http://deepart.ece.ust.hk.

Evaluating the Privacy Risk of User-Shared Images

User-shared images are shared on social media about a user’s life and interests that are widely accessible to others due to their sharing nature. Unlike for online profiles and social graphs, most users are unaware of the privacy risks relating to shared images, as they do not directly disclose characteristics such as gender and origin. Recently, however, user-shared images have been proven to be an accessible alternative to social graphs for online friendship recommendation and gender identification. This article evaluates 1.6M user-shared images from an image-oriented social network, Fotolog, and concludes how they can create privacy risks by proposing a system for de-anonymization, as well as inferring information on online profiles with the user-shared images. It is concluded that given user-shared images, using social graphs is 2 and 2.5 times more effective in de-anonymization than using origins or genders. With two showcases, it is also proven that using user-shared images is effective in online friendship recommendation, gender identification, and origin inference. To the best of our knowledge, this is the first article to evaluate the privacy issue qualitatively with big multimedia data from a real social network.

Analyzing the User Inactiveness in a Mobile Social Game

This paper analyzes and evaluates the factors that affect the inactiveness of users and how they are related to inactiveness. A higher inactiveness indicates a user is more likely to be inactive. The analysis locates inactive users, who have not logged in to the system for some time, and evaluates the relationship between inactiveness and three dimensions: social networking, time, and in-app purchase. Based on the operational data from a mobile social game, Barcode Footballer, with more than 100k users and 1 million friendships, it is concluded that social networking, time and in-app purchase are all important factors in inactiveness. The results can be applied to mobile social games to detect potential inactive users such that their operators can retain those users by using encouragements.

Predicting Content Virality in Social Cascade

Predicting why and how certain content goes viral is attractive for many applications, such as viral marketing and social network applications, but is still a challenging task today. Existing prediction algorithms focus on predicting the content popularity without considering the timing. Those algorithms are based on information that may be uncommon or computationally expensive. This paper proposes a novel and practical algorithm to predict the virality of content. Instead of predicting the popularity, the algorithm predicts the time for the social cascade size to reach a given viral target. The algorithm is verified by the data from a popular social network - Digg.com and 2 synthesize datasets under different conditions. The results prove that the algorithm can achieve the lower bound with a practical significance for the time to reach the viral target.