#### DMCA

## Efficient Layout of Comic-Like Video Summaries

Citations: | 15 - 2 self |

### Citations

3827 |
Dynamic Programming
- Bellman
- 2003
(Show Context)
Citation Context ...t of panels in comiclike fashion are described in Section III. The first technique finds an optimal solution for a given cost function, while the second suboptimal method utilizes dynamic programming =-=[11]-=- to efficiently generate the summary. The results of the algorithms presented are evaluated by benchmarking the optimal against a suboptimal panelling solution. II. ESTIMATION OF FRAME SIZES Our aim i... |

1876 | Data clustering: a review
- Jain, Murty, et al.
- 1999
(Show Context)
Citation Context ...-based methods like K-means fail to achieve acceptable results since the number of existing clusters has to be defined a priori and these algorithms break down in presence of nonlinear cluster shapes =-=[12]-=-. Being capable of analysing inherent characteristics of the data and coping very well with high nonlinearity of clusters, a spectral clustering approach was adopted as a method for robust frame group... |

1673 | On spectral clustering: Analysis and an algorithm
- Ng, Jordan, et al.
- 2001
(Show Context)
Citation Context ...empts failed to develop a feasible layout algorithm. In order to uncover the underpinning structure of the key-frame data in an unsupervised manner, our work exploits K-way spectral clustering method =-=[9]-=- in perceptual grouping of extracted key-frames using locally scaled affinity matrix [10]. The work presented in this paper introduces a number of novel approaches to the algorithm pipeline, improving... |

136 | Video manga: Generating semantically meaningful video summaries
- Uchihashi, Foote, et al.
- 1999
(Show Context)
Citation Context ...iates our work from more typical reverse-storyboarding [6] or video summarization approaches. There have been attempts to utilize the form of comics as a medium for visual summarization of videos. In =-=[7]-=-, a layout algorithm that optimizes the ratio of white space left and approximation error of the frame importance function is proposed. Following a similar approach, the work presented in [8] introduc... |

130 |
Understanding Comics
- McCloud
- 1994
(Show Context)
Citation Context ...e universally familiar narrative structure of comics to generate easily readable visual summaries. Being defined as “spatially juxtaposed images in deliberate sequence intended to convey information” =-=[5]-=-, comics are the most prevalent medium that expresses meaning through a sequence of spatially structured images. Exploiting this concept, the proposed system follows the narrative structure of comics,... |

107 | Video summarization by curve simplification
- DeMenthon, Kobla, et al.
- 1998
(Show Context)
Citation Context ...izing cluster-validity analysis, Hanjalic and Zhang [2] remove the visual content redundancy among video frames using an unsupervised procedure. An interesting approach introduced by DeMenthon et al. =-=[3]-=- represents the video sequence as a curve in a high dimensional space, and the summary is represented by the set of salient points on that curve. Recently, Wah et al. [4] exploited a normalized cut al... |

90 |
An integrated scheme for automated video abstraction based on unsupervised cluster-validity analysis
- Hanjalic, Zhang
- 1999
(Show Context)
Citation Context ...od based on HSV color features, where the frame closest to the cluster center is chosen as the key frame representative for a given video shot. Utilizing cluster-validity analysis, Hanjalic and Zhang =-=[2]-=- remove the visual content redundancy among video frames using an unsupervised procedure. An interesting approach introduced by DeMenthon et al. [3] represents the video sequence as a curve in a high ... |

85 |
Combinatorial Algorithms For Computers and Calculators
- Nijenhuis, Wilf
- 1978
(Show Context)
Citation Context ...e summands is relevant, it is the case of composition of an integer into all possible parts, in the form . Due to a large number of possible compositions ,anefficient iterative algorithm described in =-=[14]-=- is used to generate all possible solutions. In order to find an optimal composition of page height into rows with heights , for every possible , a number of frames per row is calculated to satisfy th... |

39 | Grouping and dimensionality reduction by locally linear embedding
- Polito, Perona
- 2001
(Show Context)
Citation Context ... clearly separated, the eigenvalues deviate from the extreme values of 1 and 0. Thus, counting the eigenvalues that are close to 1 becomes unreliable. Based on the same idea, Polito and Perona in (1) =-=[13]-=- detect a location of a drop in the magnitude of the eigenvalues in order to estimate , but the algorithm still lacks the robustness that is required in our case. Therefore, a novel algorithm to robus... |

23 |
Summarizing video using a shot importance measure and a frame-packing algorithm
- Uchihashi, Foote
- 1999
(Show Context)
Citation Context ...ble resources. In addition, the majority of proposed algorithms are based on heuristics and do not offer an optimal solution. Fig. 1. Comparison of the layout algorithm speed for methods presented in =-=[16]-=- [ORIG], [8] [FAST] to our method [DPLY]. Linear complexity of the proposed layout algorithm is observable. Therefore, we propose a suboptimal solution using dynamic programming and we will show that ... |

22 |
Two-dimensional packing problems: A survey.“ European
- Lodi, Martello, et al.
- 2002
(Show Context)
Citation Context ...l resources. In our case, we need to optimally utilize the available two-dimensional space given required sizes of images. However, unlike many well studied problems like stock cutting or bin packing =-=[15]-=-, there is a nonlinear transformation layer of panel templates between the error function and available resources. In addition, the majority of proposed algorithms are based on heuristics and do not o... |

13 | Techniques for automated reverse storyboarding
- Dony, Mateer, et al.
- 2005
(Show Context)
Citation Context ...p://ieeexplore.ieee.org. Digital Object Identifier 10.1109/TCSVT.2007.897466 spatial position of panels in a comic strip. This approach differentiates our work from more typical reverse-storyboarding =-=[6]-=- or video summarization approaches. There have been attempts to utilize the form of comics as a medium for visual summarization of videos. In [7], a layout algorithm that optimizes the ratio of white ... |

10 |
A fast layout algorithm for visual video summaries
- Girgensohn
- 2003
(Show Context)
Citation Context ...deos. In [7], a layout algorithm that optimizes the ratio of white space left and approximation error of the frame importance function is proposed. Following a similar approach, the work presented in =-=[8]-=- introduces a number of heuristic rules to optimize the layout algorithm. However, due to an inherently difficult optimization, these attempts failed to develop a feasible layout algorithm. In order t... |

2 |
Adaptive key frame extraction using unsupervised clustering
- Yueting, Yong, et al.
- 1998
(Show Context)
Citation Context ...n challenge of systems for video summarization and browsing is to achieve a good balance between removal of redundant sections of video and representative coverage of the video summary. Zhuang et al. =-=[1]-=- proposed an unsupervised clustering method based on HSV color features, where the frame closest to the cluster center is chosen as the key frame representative for a given video shot. Utilizing clust... |

1 |
Video summarization and scene detection by graph modeling
- Chong-Wah, Yu-Fei, et al.
- 2005
(Show Context)
Citation Context ...ntroduced by DeMenthon et al. [3] represents the video sequence as a curve in a high dimensional space, and the summary is represented by the set of salient points on that curve. Recently, Wah et al. =-=[4]-=- exploited a normalized cut algorithm to globally and optimally partition the graph representation into video clusters and describe the evolution and perceptual importance of a video segment. This wor... |