Efficient visual attention based framework for extracting key frames from videos

Ejaz, Naveed; Mehmood, Irfan; Baik, Sung Wook

doi:10.1016/j.image.2012.10.002

Cited by 157 publications

(121 citation statements)

References 27 publications

Supporting

Mentioning

119

Contrasting

Unclassified

Order By: Relevance

“…Subjective evaluation methods were used in [16,[60][61][62][63]. In [60], subjective assessment was used to grade the single key-frame representations as 'good' , 'bad' or 'neutral' for each video shot and also give appreciations on the number of key-frames with possible grades being 'good' , 'too many' and 'too few' in the case of multiple key-frames per shot.…”

Section: Subjective Methodsmentioning

confidence: 99%

“…In [61,63], the quality of the key-frame summary is evaluated by asking users to give a mark between 0 to 100 for three criteria, 'informativeness' , 'enjoyability' and 'rank' after watching the original sequences and the respective key-frames summaries. Ejaz et al [62] used subjective evaluations to compare the proposed method with four prominent key-frame extraction methods: open video project (OV) [45], Delaunay triangulation (DT) [64], STIll and MOving Video Storyboard (STIMO) [65] and Video SUMMarisation (VSUMM) [24]. In this case, the evaluation is based on mean opinion scores (MOS) and viewers are asked to rate the quality of the key-frame summary on scale of 0 (minimum value) to 5 (maximum value) after watching the original sequences and the respective summaries generated by all the methods.…”

Section: Subjective Methodsmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Subjective Methodsmentioning

confidence: 99%

Section: Subjective Methodsmentioning

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

show abstract

“…The larger M i c is, the more attention it gets. To model the attention prior, linear fusion schemes are used for the fusion of various attention scores to generate an aggregated attention score [61]. The general form of linear fusion schemes is as follows:…”

Section: Attention Priormentioning

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

“…For example, as of now, one of the most primary video sharing web sites like YouTube reported that more than 1 billion unique users visit YouTube each month and 72 hours of video are uploaded every minute [13]. The evegrowing number of videos has motivated researchers to design efficient and effective video management schemes in order to provide a better overall multimedia experience to the consumer [1]. Summarization is mainly used to provide a condensed version of a full-length video through the identification of most important content within it [2,4].…”

Section: Introductionmentioning

confidence: 99%

“…Summarization is mainly used to provide a condensed version of a full-length video through the identification of most important content within it [2,4]. Video skimming and key frame extraction are the two basic methods for summarizing videos [1][2][3][4]. A video of much shorter duration than the actual one is produced in the later case whereas the former deals with extracting some salient frames from the videos which preserves the overall content of a video with minimum data.…”

Section: Introductionmentioning

confidence: 99%

Video Key Frame Extraction through Canonical Correlation Analysis and Graph Modularity

Panda

Kuanar

Chowdhury

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Key frame based video summarization has emerged as an important area of multimedia research in recent times. In this paper, we propose a novel automated approach for video key frame extraction in compressed domain using canonical correlation analysis (CCA) and graph modularity. We prune certain edges from the Video Similarity Graph (VSG) using an iterative strategy until there is no improvement in graph modularity. Resulting connected components in the final VSG correspond to separate clusters. The proposed algorithm also uses multifeature fusion using canonical correlation analysis to achieve higher semantic dependency between different video frames. Experimental results on some standard videos of different genre clearly indicate the superiority of the proposed method in terms of the F1 measure.

show abstract

Efficient visual attention based framework for extracting key frames from videos

Cited by 157 publications

References 27 publications

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

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

Scalable gastroscopic video summarization via similar-inhibition dictionary selection

Video Key Frame Extraction through Canonical Correlation Analysis and Graph Modularity

Contact Info

Product

Resources

About