Xianglin Zeng

Bio: Xianglin Zeng is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Video tracking & Video compression picture types. The author has an hindex of 2, co-authored 3 publications receiving 566 citations.

A Survey on Visual Content-Based Video Indexing and Retrieval

Abstract: Video indexing and retrieval have a wide spectrum of promising applications, motivating the interest of researchers worldwide. This paper offers a tutorial and an overview of the landscape of general strategies in visual content-based video indexing and retrieval, focusing on methods for video structure analysis, including shot boundary detection, key frame extraction and scene segmentation, extraction of features including static key frame features, object features and motion features, video data mining, video annotation, video retrieval including query interfaces, similarity measure and relevance feedback, and video browsing. Finally, we analyze future research directions.

Video shot segmentation using graph-based dominant-set clustering

Abstract: Video shot segmentation is a solid foundation for automatic video content analysis, for most content based video retrieval tasks require accurate segmentation of video boundaries. In recent years, using the tools of data mining and machine learning to detect shot boundaries has become more and more popular. In this paper, we propose an effective video segmentation approach based on a dominant-set clustering algorithm. The algorithm can not only automatically determine the number of video shots, but also obtain accurate shot boundaries with low computation complexity. Experimental results have demonstrated the effectiveness of the proposed shot segmentation approach.

A New Approach for Video Scene Boundary Detection

Abstract: Scene is the semantic unit in video. Video scene segmentation is a difficult task in content based video structure analysis. This paper proposes a new approach for scene boundary detection. We first construct shot content coherence signal using Normalized Cut criterion and then use a heuristic algorithm to detect scene boundary. Because the Normalized Cut criterion simultaneously emphasizes on the inhomogeneity of shots in different scenes and the homogeneity of shots in the same scene, the continuous signal reflects the coherence of shot content well. Experiments on different kinds of video clips demonstrate our approach performs well in scene segmentation.

Big Data: A Survey

Abstract: In this paper, we review the background and state-of-the-art of big data. We first introduce the general background of big data and review related technologies, such as could computing, Internet of Things, data centers, and Hadoop. We then focus on the four phases of the value chain of big data, i.e., data generation, data acquisition, data storage, and data analysis. For each phase, we introduce the general background, discuss the technical challenges, and review the latest advances. We finally examine the several representative applications of big data, including enterprise management, Internet of Things, online social networks, medial applications, collective intelligence, and smart grid. These discussions aim to provide a comprehensive overview and big-picture to readers of this exciting area. This survey is concluded with a discussion of open problems and future directions.

Toward Scalable Systems for Big Data Analytics: A Technology Tutorial

Abstract: Recent technological advancements have led to a deluge of data from distinctive domains (e.g., health care and scientific sensors, user-generated data, Internet and financial companies, and supply chain systems) over the past two decades. The term big data was coined to capture the meaning of this emerging trend. In addition to its sheer volume, big data also exhibits other unique characteristics as compared with traditional data. For instance, big data is commonly unstructured and require more real-time analysis. This development calls for new system architectures for data acquisition, transmission, storage, and large-scale data processing mechanisms. In this paper, we present a literature survey and system tutorial for big data analytics platforms, aiming to provide an overall picture for nonexpert readers and instill a do-it-yourself spirit for advanced audiences to customize their own big-data solutions. First, we present the definition of big data and discuss big data challenges. Next, we present a systematic framework to decompose big data systems into four sequential modules, namely data generation, data acquisition, data storage, and data analytics. These four modules form a big data value chain. Following that, we present a detailed survey of numerous approaches and mechanisms from research and industry communities. In addition, we present the prevalent Hadoop framework for addressing big data challenges. Finally, we outline several evaluation benchmarks and potential research directions for big data systems.

PROVID: Progressive and Multimodal Vehicle Reidentification for Large-Scale Urban Surveillance

Abstract: Compared with person reidentification, which has attracted concentrated attention, vehicle reidentification is an important yet frontier problem in video surveillance and has been neglected by the multimedia and vision communities. Since most existing approaches mainly consider the general vehicle appearance for reidentification while overlooking the distinct vehicle identifier, such as the license plate number, they attain suboptimal performance. In this paper, we propose PROVID, a PROgressive Vehicle re-IDentification framework based on deep neural networks. In particular, our framework not only utilizes the multimodality data in large-scale video surveillance, such as visual features, license plates, camera locations, and contextual information, but also considers vehicle reidentification in two progressive procedures: coarse-to-fine search in the feature domain, and near-to-distant search in the physical space. Furthermore, to evaluate our progressive search framework and facilitate related research, we construct the VeRi dataset, which is the most comprehensive dataset from real-world surveillance videos. It not only provides large numbers of vehicles with varied labels and sufficient cross-camera recurrences but also contains license plate numbers and contextual information. Extensive experiments on the VeRi dataset demonstrate both the accuracy and efficiency of our progressive vehicle reidentification framework.