Abstract:With the rapid growth of video resources, techniques for efficient organization of video clips are becoming appealing in the multimedia domain. In this article, a sketch-based approach is proposed to intuitively organize video clips by: (1) enhancing their narrations using sketch annotations and (2) structurizing the organization process by gesture-based free-form sketching on touch devices. There are two main contributions of this work. The first is a sketch graph, a novel representation for the narrative str… Show more
“…We conducted a study to evaluate VideoMap, which demonstrated how the system can facilitate exploration of video content and significantly reduce browsing time needed to understand and find events of interest. Firstly, we compared VideoMap to two state-of-the-art video visualization and interaction methods: Storyline [22] and the Sketch Graph method [24].…”
Section: Discussionmentioning
confidence: 99%
“…Besides the traditional interaction method of using markers on a timeline to navigate through video content [23], new natural sketch-based interaction has been used in video authoring [12,24] by operating on a sketch summary. Visual feedback is also important for efficient interaction, following user preferences [25].…”
Large-scale dynamic relational data visualization has attracted considerable research attention recently. We introduce dynamic data visualization into the multimedia domain, and present an interactive and scalable system, VideoMap, for exploring large-scale video content. A long video or movie has much content; the associations between the content are complicated. VideoMap uses new visual representations to extract meaningful information from video content. Map-based visualization naturally and easily summarizes and reveals important features and events in video. Multi-scale descriptions are used to describe the layout and distribution of temporal information, spatial information, and associations between video content. Firstly, semantic associations are used in which map elements correspond to video contents.Secondly, video contents are visualized hierarchically from a large scale to a fine-detailed scale. VideoMap uses a small set of sketch gestures to invoke analysis, and automatically completes charts by synthesizing visual representations from the map and binding them to the underlying data. Furthermore, VideoMap allows users to use gestures to move and resize the view, as when using a map, facilitating interactive exploration. Our experimental evaluation of VideoMap demonstrates how the system can assist in exploring video content as well as significantly reducing browsing time when trying to understand and find events of interest.
“…We conducted a study to evaluate VideoMap, which demonstrated how the system can facilitate exploration of video content and significantly reduce browsing time needed to understand and find events of interest. Firstly, we compared VideoMap to two state-of-the-art video visualization and interaction methods: Storyline [22] and the Sketch Graph method [24].…”
Section: Discussionmentioning
confidence: 99%
“…Besides the traditional interaction method of using markers on a timeline to navigate through video content [23], new natural sketch-based interaction has been used in video authoring [12,24] by operating on a sketch summary. Visual feedback is also important for efficient interaction, following user preferences [25].…”
Large-scale dynamic relational data visualization has attracted considerable research attention recently. We introduce dynamic data visualization into the multimedia domain, and present an interactive and scalable system, VideoMap, for exploring large-scale video content. A long video or movie has much content; the associations between the content are complicated. VideoMap uses new visual representations to extract meaningful information from video content. Map-based visualization naturally and easily summarizes and reveals important features and events in video. Multi-scale descriptions are used to describe the layout and distribution of temporal information, spatial information, and associations between video content. Firstly, semantic associations are used in which map elements correspond to video contents.Secondly, video contents are visualized hierarchically from a large scale to a fine-detailed scale. VideoMap uses a small set of sketch gestures to invoke analysis, and automatically completes charts by synthesizing visual representations from the map and binding them to the underlying data. Furthermore, VideoMap allows users to use gestures to move and resize the view, as when using a map, facilitating interactive exploration. Our experimental evaluation of VideoMap demonstrates how the system can assist in exploring video content as well as significantly reducing browsing time when trying to understand and find events of interest.
“…image, video, threedimensional (3D) model) has become an active research area. [22][23][24] Sketch-based retrieval methods allow users to submit a sketch drawing illustrating their search intent. Such a way of user query intent expression provides users much freedom to specify and clarify their search need.…”
Section: Related Workmentioning
confidence: 99%
“…Hu and Collomosse 6 adopted a Bag-of-Visual Words (BoVW) approach, incorporating Gradient Field HOG (GF-HOG) descriptor for SBIR. Liu et al 24 proposed an interactive sketch-based interface to organize video clips, enabling common users to easily draw simple sketches, and these sketches are automatically converted from keyframes of videos. Eitz et al 22 proposed a new sketch-based 3D model retrieval system based on bag-of-features framework.…”
Nowadays, the state-of-the-art mobile visual sensors technology makes it easy to collect a great number of clothing images. Accordingly, there is an increasing demand for a new efficient method to retrieve clothing images by using mobile visual sensors. Different from traditional keyword-based and content-based image retrieval techniques, sketch-based image retrieval provides a more intuitive and natural way for users to clarify their search need. However, this is a challenging problem due to the large discrepancy between sketches and images. To tackle this problem, we present a new sketch-based clothing image retrieval algorithm based on sketch component segmentation. The proposed strategy is to first collect a large scale of clothing sketches and images and tag with semantic component labels for training dataset, and then, we employ conditional random field model to train a classifier which is used to segment query sketch into different components. After that, several feature descriptors are fused to describe each component and capture the topological information. Finally, a dynamic component-weighting strategy is established to boost the effect of important components when measuring similarities. The approach is evaluated on a large, real-world clothing image dataset, and experimental results demonstrate the effectiveness and good performance of the proposed method.
“…Due to less information stored in line drawings when compared to the color photographs, the usage of line drawings in intelligent process of visual media, including the retrieval and re-use of images [9,10], videos [11,12], 3D graphical models [13,14,15] and conceptual design in industry [16,17], has attracted considerable attention recently. The reader is referred to [5] for a survey.…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.