Efficient Layout of Comic-Like Video Summaries

Abstract

Abstract-In order to represent large amounts of information in the form of a video key-frame summary, this paper studies narrative grammar of comics, and using its universal and intuitive rules, lays out visual summaries in an efficient and user centered way. The system ranks importance of key-frame sizes in the final layout by balancing the dominant visual representability and discovery of unanticipated content utilizing a specific cost function and an unsupervised robust spectral clustering technique. A final layout is created using an optimization algorithm based on dynamic programming. Algorithm efficiency and robustness are demonstrated by comparing the results with the optimal panelling solutions.

Automatic Image Retrieval through Video Authoring and Transition

“…Video summarization has become an emerging field of research. Video summaries are becoming increasingly popular as a way to convert large chunks of video into smaller, more comprehensible units [7]. Video summarization methods are categorized on the basis of methodology used.…”

Interactive search and browsing interface for large-scale visual repositories

“…Focusing on the frame saliency and importance in the video summarisation context, a number of graph-based methods have been proposed [12] [13] [14]. However, the efficiency of these approaches heavily depends upon the size of the dataset, due to a high complexity of the spectral analysis exploited in their graph representation.…”

Hierarchical Modeling and Adaptive Clustering for Real-Time Summarization of Rush Videos

“…[8]. In addition, selection of COIs including objects and events can be solved by introducing user-attention model and domain knowledge [3,6,41,47]. In some work, graph theory [1,46,50] and dynamic programming [4,9,48] are applied for either video segmentation or optimal (suboptimal) clustering for summarization.…”

“…For internal summarization, audio information is often utilized together with image features [14-15, 20, 26, 32, 34-35, 40-42], among which camera motion [8,12,16] and object motion [1,7,13,44,47] are frequently employed to model the significance of frames for summarization. Some work using text information overlaid to help with the video summarization is also reported [10].…”