Search

Nowadays, numerous social videos have pervaded on the web. Social web videos are characterized with the accompanying rich contextual information which describe the content of videos and thus greatly facilitate video search and browsing. Generally, those contextual data such as tags are provided at the whole video level, without temporal indication of when they actually appear in the video, let alone the spatial annotation of object related tags in the video frames. However, many tags only describe parts of the video content. Therefore, tag localization, the process of assigning tags to the underlying relevant video segments or frames even regions in frames is gaining increasing research interests and a benchmark dataset for the fair evaluation of tag localization algorithms is highly desirable. In this paper, we describe and release a dataset called DUT-WEBV, which contains about 4,000 videos collected from YouTube portal by issuing 50 concepts as queries. These concepts cover a wide range of semantic aspects including scenes like 'mountain', events like 'flood', objects like 'cows', sites like 'gas station', and activities like 'handshaking', offering great challenges to the tag (i.e., concept) localization task. For each video of a tag, we carefully annotate the time durations when the tag appears in the video and also label the spatial location of object with mask in frames for object related tag. Besides the video itself, the contextual information, such as thumbnail images, titles, and YouTube categories, is also provided. Together with this benchmark dataset, we present a baseline for tag localization using multiple instance learning approach. Finally, we discuss some open research issues for tag localization in web videos. [ABSTRACT FROM AUTHOR]

Presenting and browsing image search results play key roles in helping users to find desired images from search results. Most existing commercial image search engines present them, dependent on a ranked list. However, such a scheme suffers from at least two drawbacks: inconvenience for consumers to get an overview of the whole result, and high computation cost to find desired images from the list. In this paper, we introduce a novel search result summarization approach and exploit this approach to further propose an interactive browsing scheme. The main contribution of this paper includes: (1) a dynamic absorbing random walk to find diversified representatives for image search result summarization; (2) a local scaled visual similarity evaluation scheme between two images through inspecting the relation between each image and other images; and (3) an interactive browsing scheme, based on a tree structure for organizing the images obtained from the summarization approach, to enable users to intuitively and conveniently browse the image search results. Quantitative experimental results and user study demonstrate the effectiveness of the proposed summarization and browsing approaches. [ABSTRACT FROM AUTHOR]

Chinese calligraphy is an important part of Chinese traditional culture. More and more calligraphy works are digitized, preserved and exhibited in digital libraries. Users may want to appreciate the style-similar works simultaneously. However, currently available services such as metadata-based browsing and searching can not satisfy such kind of requirement. To allow users to appreciate the style-similar works conveniently, we propose a Supervised Learning Weighted Random Walk Model to discover calligraphy style relationships. In the model, we consider the heterogeneity of both edges and nodes, and then use some preference pairs to learn the weights of different types of edges in the graph. After the weight learning, the style relationships can be discovered by random walk on the heterogeneous graphs. In order to solve the out-of-graph node problem, we pre-compute the personalized vector for each character or visual word, then utilize the Linearity Theory for vector addition to approximate the relationships between the new node and other nodes in graph. Then we demonstrate several applications which prove the effectiveness and efficiency of our proposed model and a user study for benefit verification. Finally, we explore some strategies to enhance the performance with the explicit or implicit user interaction including feedback, clickthrough data tracking. [ABSTRACT FROM AUTHOR]