This book constitutes the refereed proceedings of the 9th International Conference on Internet Multimedia Computing and Service, ICIMCS 2017, held in Qingdao, China, in August 2017. The 20 revised full papers and 28 revised short papers presented were carefully reviewed and selected from 103 submissions. The papers are organized in topical sections on multimedia information fusion, image processing and object recognition, machine learning and representation learning, multimedia retrieval, poster papers.

With the proliferation of social network services, more and more social users, such as individuals and organizations, are simultaneously involved in multiple social networks for various purposes. In fact, multiple social networks characterize the same social users from different perspectives, and their contexts are usually consistent or complementary rather than independent. Hence, as compared to using information from a single social network, appropriate aggregation of multiple social networks offers us a better way to comprehensively understand the given social users. Learning across multiple social networks brings opportunities to new services and applications as well as new insights on user online behaviors, yet it raises tough challenges: (1) How can we map different social network accounts to the same social users? (2) How can we complete the item-wise and block-wise missing data? (3) How can we leverage the relatedness among sources to strengthen the learning performance? And (4) How can we jointly model the dual-heterogeneities: multiple tasks exist for the given application and each task has various features from multiple sources? These questions have been largely unexplored to date. We noticed this timely opportunity, and in this book we present some state-of-the-art theories and novel practical applications on aggregation of multiple social networks. In particular, we first introduce multi-source dataset construction. We then introduce how to effectively and efficiently complete the item-wise and block-wise missing data, which are caused by the inactive social users in some social networks. We next detail the proposed multi-source mono-task learning model and its application in volunteerism tendency prediction. As a counterpart, we also present a mono-source multi-task learning model and apply it to user interest inference. We seamlessly unify these models with the so-called multi-source multi-task learning, and demonstrate several application scenarios, such as occupation prediction. Finally, we conclude the book and figure out the future research directions in multiple social network learning, including the privacy issues and source complementarity modeling. This is preliminary research on learning from multiple social networks, and we hope it can inspire more active researchers to work on this exciting area. If we have seen further it is by standing on the shoulders of giants.

Micro-videos, a new form of user-generated contents, have been spreading widely across various social platforms, such as Vine, Kuaishou, and Tik Tok. Different from traditional long videos, micro-videos are usually recorded by smart mobile devices at any place within a few seconds. Due to its brevity and low bandwidth cost, micro-videos are gaining increasing user enthusiasm. The blossoming of micro-videos opens the door to the possibility of many promising applications, ranging from network content caching to online advertising. Thus, it is highly desirable to develop an effective scheme for the high-order micro-video understanding. Micro-video understanding is, however, non-trivial due to the following challenges: (1) how to represent micro-videos that only convey one or few high-level themes or concepts; (2) how to utilize the hierarchical structure of the venue categories to guide the micro-video analysis; (3) how to alleviate the influence of low-quality caused by complex surrounding environments and the camera shake; (4) how to model the multimodal sequential data, {i.e.}, textual, acoustic, visual, and social modalities, to enhance the micro-video understanding; and (5) how to construct large-scale benchmark datasets for the analysis? These challenges have been largely unexplored to date. In this book, we focus on addressing the challenges presented above by proposing some state-of-the-art multimodal learning theories. To demonstrate the effectiveness of these models, we apply them to three practical tasks of micro-video understanding: popularity prediction, venue category estimation, and micro-video routing. Particularly, we first build three large-scale real-world micro-video datasets for these practical tasks. We then present a multimodal transductive learning framework for micro-video popularity prediction. Furthermore, we introduce several multimodal cooperative learning approaches and a multimodal transfer learning scheme for micro-video venue category estimation. Meanwhile, we develop a multimodal sequential learning approach for micro-video recommendation. Finally, we conclude the book and figure out the future research directions in multimodal learning toward micro-video understanding.