Video abstraction based on the visual attention model and online clustering

Ji, Qingge; Fang, Zhi-Dang; Xie, Zhenhua; Lu, Zhe‐Ming

doi:10.1016/j.image.2012.11.008

Cited by 47 publications

(25 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The value of salient object detection models lies in their applications in many areas such as computer vision, graphics, and robotics. For instance, these models have been successfully applied in many applications such as object detection and recognition [22]- [30], image and video compression [31], [32], video summarization [33]- [35], photo collage/media re-targeting/cropping/thumb-nailing [20], [36], [37], image quality assessment [38]- [41], image segmentation [42]- [45], content-based image retrieval and image collection browsing [46]- [49], image editing and manipulating [50]- [53], visual tracking [54]- [60], object discovery [61], [62], and human-robot interaction [63]- [65].…”

mentioning

confidence: 99%

Salient Object Detection: A Benchmark

Borji

Cheng

Jiang

et al. 2015

IEEE Trans. on Image Process.

1,279

312

View full text Add to dashboard Cite

We extensively compare, qualitatively and quantitatively, 41 state-of-the-art models (29 salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over seven challenging data sets for the purpose of benchmarking salient object detection and segmentation methods. From the results obtained so far, our evaluation shows a consistent rapid progress over the last few years in terms of both accuracy and running time. The top contenders in this benchmark significantly outperform the models identified as the best in the previous benchmark conducted three years ago. We find that the models designed specifically for salient object detection generally work better than models in closely related areas, which in turn provides a precise definition and suggests an appropriate treatment of this problem that distinguishes it from other problems. In particular, we analyze the influences of center bias and scene complexity in model performance, which, along with the hard cases for the state-of-the-art models, provide useful hints toward constructing more challenging large-scale data sets and better saliency models. Finally, we propose probable solutions for tackling several open problems, such as evaluation scores and data set bias, which also suggest future research directions in the rapidly growing field of salient object detection.

show abstract

mentioning

confidence: 99%

Salient Object Detection: A Benchmark

Borji

Cheng

Jiang

et al. 2015

IEEE Trans. on Image Process.

1,279

312

View full text Add to dashboard Cite

show abstract

“…Another approach intends to group the frames into visually similar clusters and selects frames relevant to the cluster centers as key frames [17,18]. Zhuang et al [19] group the frames in clusters and selects the key frames from the largest clusters.…”

Section: Related Workmentioning

confidence: 99%

Scalable gastroscopic video summarization via similar-inhibition dictionary selection

Wang

Cong

Cao

et al. 2016

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

“…This metric was used in [24,62,63,68,69] for 2D video summaries. In 3D key-frame extraction methods, the computational complexity metric is only used by Lee et al in [22], where the computational complexity of Lee's and Huang's et al [18] methods are compared.…”

Section: Comparison Of User Summaries (Cus)mentioning

confidence: 99%

Towards key-frame extraction methods for 3D video: a review

Ferreira

Cruz

Assunção

2016

J Image Video Proc.

View full text Add to dashboard Cite

The increasing rate of creation and use of 3D video content leads to a pressing need for methods capable of lowering the cost of 3D video searching, browsing and indexing operations, with improved content selection performance. Video summarisation methods specifically tailored for 3D video content fulfil these requirements. This paper presents a review of the state-of-the-art of a crucial component of 3D video summarisation algorithms: the key-frame extraction methods. The methods reviewed cover 3D video key-frame extraction as well as shot boundary detection methods specific for use in 3D video. The performance metrics used to evaluate the key-frame extraction methods and the summaries derived from those key-frames are presented and discussed. The applications of these methods are also presented and discussed, followed by an exposition about current research challenges on 3D video summarisation methods.Keywords: 3D key-frames extraction, 3D video summarisation, Shot boundary detection ReviewIn the last years, new features have been implemented in video applications and terminal equipments due to users demand, who are always seeking for new viewing experiences more interactive and immersive, such as those provided by 3D video. This new visual experience is created by depth information that is part of 3D video and absent in classic 2D video. The inclusion of depth information in video signals is not a recent innovation, but the interest in this type of content and aspects related to it, such as acquisition, analysis, coding, transmission and visualisation, have been increasing recently [1,2]. Lately, 3D video has been attracting attention from industry, namely content producers, equipment providers, distributors and from the research community mostly on account of the improvements in Quality of Experience that it provides to viewers [3], as well as due to the new business opportunities presented by this emerging multimedia format. In the past, video repositories were relatively small so that indexing and retrieval operations were easy to perform. More recently, the massification of 3D video and its applications have resulted in the generation of huge amounts of data, increasing the need for methods that can efficiently index, search, browse and summarise the relevant information with minimum human intervention. Furthermore, 3D video description and management is also required to enable quick presentation of the most important information in a user-friendly manner [4,5]. Video summarisation is a video-content representation method that can fulfil these requirements. In contrast to summarisation of 2D video, which has been the subject of a significant amount of research, 3D video summarisation is still a relatively unexplored research problem which deserves more attention.A video summary is a short version of a full-length video that preserves the essential visual and semantic information of the original unabridged content. In the video summarisation process, a subset of key-frames or a set of shorter video...

show abstract

Video abstraction based on the visual attention model and online clustering

Cited by 47 publications

References 23 publications

Salient Object Detection: A Benchmark

Salient Object Detection: A Benchmark

Scalable gastroscopic video summarization via similar-inhibition dictionary selection

Towards key-frame extraction methods for 3D video: a review

Contact Info

Product

Resources

About