Multimodal Learning Toward Micro Video Understanding

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.

Image fusion in remote sensing or pansharpening involves fusing spatial (panchromatic) and spectral (multispectral) images that are captured by different sensors on satellites. This book addresses image fusion approaches for remote sensing applications. Both conventional and deep learning approaches are covered. First, the conventional approaches to image fusion in remote sensing are discussed. These approaches include component substitution, multi-resolution, and model-based algorithms. Then, the recently developed deep learning approaches involving single-objective and multi-objective loss functions are discussed. Experimental results are provided comparing conventional and deep learning approaches in terms of both low-resolution and full-resolution objective metrics that are commonly used in remote sensing. The book is concluded by stating anticipated future trends in pansharpening or image fusion in remote sensing.

Artificial intelligence, or AI, now affects the day-to-day life of almost everyone on the planet, and continues to be a perennial hot topic in the news. This book presents the proceedings of ECAI 2023, the 26th European Conference on Artificial Intelligence, and of PAIS 2023, the 12th Conference on Prestigious Applications of Intelligent Systems, held from 30 September to 4 October 2023 and on 3 October 2023 respectively in Kraków, Poland. Since 1974, ECAI has been the premier venue for presenting AI research in Europe, and this annual conference has become the place for researchers and practitioners of AI to discuss the latest trends and challenges in all subfields of AI, and to demonstrate innovative applications and uses of advanced AI technology. ECAI 2023 received 1896 submissions – a record number – of which 1691 were retained for review, ultimately resulting in an acceptance rate of 23%. The 390 papers included here, cover topics including machine learning, natural language processing, multi agent systems, and vision and knowledge representation and reasoning. PAIS 2023 received 17 submissions, of which 10 were accepted after a rigorous review process. Those 10 papers cover topics ranging from fostering better working environments, behavior modeling and citizen science to large language models and neuro-symbolic applications, and are also included here. Presenting a comprehensive overview of current research and developments in AI, the book will be of interest to all those working in the field.

This book sheds light on state-of-the-art theories for more challenging outfit compatibility modeling scenarios. In particular, this book presents several cutting-edge graph learning techniques that can be used for outfit compatibility modeling. Due to its remarkable economic value, fashion compatibility modeling has gained increasing research attention in recent years. Although great efforts have been dedicated to this research area, previous studies mainly focused on fashion compatibility modeling for outfits that only involved two items and overlooked the fact that each outfit may be composed of a variable number of items. This book develops a series of graph-learning based outfit compatibility modeling schemes, all of which have been proven to be effective over several public real-world datasets. This systematic approach benefits readers by introducing the techniques for compatibility modeling of outfits that involve a variable number of composing items. To deal with the challenging task of outfit compatibility modeling, this book provides comprehensive solutions, including correlation-oriented graph learning, modality-oriented graph learning, unsupervised disentangled graph learning, partially supervised disentangled graph learning, and metapath-guided heterogeneous graph learning. Moreover, this book sheds light on research frontiers that can inspire future research directions for scientists and researchers.

The 4-volume set LNCS 13534, 13535, 13536 and 13537 constitutes the refereed proceedings of the 5th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2022, held in Shenzhen, China, in November 2022. The 233 full papers presented were carefully reviewed and selected from 564 submissions. The papers have been organized in the following topical sections: Theories and Feature Extraction; Machine learning, Multimedia and Multimodal; Optimization and Neural Network and Deep Learning; Biomedical Image Processing and Analysis; Pattern Classification and Clustering; 3D Computer Vision and Reconstruction, Robots and Autonomous Driving; Recognition, Remote Sensing; Vision Analysis and Understanding; Image Processing and Low-level Vision; Object Detection, Segmentation and Tracking.

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.