A Bag-of-Importance Model With Locality-Constrained Coding Based Feature Learning &lt;newline/&gt;for Video Summarization

Lu, Shiyang; Wang, Zhiyong; Mei, Tao; Guan, Genliang; Feng, David Dagan

doi:10.1109/tmm.2014.2319778

Cited by 76 publications

(23 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to consider the structure of the video, methods typically cluster the video into events and select the most important segments per event [11,12]. Some researchers remove redundancy and select the representative frames from original video using sparse lasso model [13,2], while [14] extends a classical algorithm of text summarization, Maximal Marginal Relevance (MMR) approach, 20 to video domain. The objective of [14] is to increase relevance to the input video and penalize redundancy within the summary.…”

Section: Introductionmentioning

confidence: 99%

“…It has been researched by many researchers and heavy achievements have been made in recent years [2,3,4,5,17,6,7,8,9]. Review the past, video summarization is started by structured videos [18,19,8,20,21], such as news, sports or surveillance videos. Following, consumer videos is studied for video summarization by researchers as a new topic at the time [13,2,3,11,22].…”

mentioning

confidence: 99%

“…To ensure the best representation, the keypoints of those keyframes should cover the global keypoint pool as much as possible. Based the framework, an importance of individual local features is exploited in [20]. It proposed a bag-of-importance with locality-constrained coding [25] model which selects keyframes with more importance 85 and representativeness.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Spatial and temporal scoring for egocentric video summarization

et al. 2016

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Spatial and temporal scoring for egocentric video summarization

et al. 2016

View full text Add to dashboard Cite

“…clustering similar frames/shots and select a limited number of frames per cluster (usually, one frame per cluster) [8], [9], [10]. The bag of importance based method identifies the frames with important local features as keyframes [11]. The combination of global and local features for video frame representation has also been utilized for keyframe extraction [12].…”

Section: Introductionmentioning

confidence: 99%

Resource restricted on-line Video Summarization with Minimum Sparse Reconstruction

Mei

Wang

et al. 2015

2015 Picture Coding Symposium (PCS)

Self Cite

View full text Add to dashboard Cite

Video Summarization (VS) techniques have been widely utilized to produce a concise video content representation, such that the video content can be quickly explored and the complexity of video based analysis and retrieval applications can be highly reduced. However, little attention has been paid for online applications, especially for resource restricted applications, such as onboard VS. In this paper, our previous on-line Minimum Sparse Reconstruction (OnMSR) based VS algorithm is improved for resources restricted applications by confining the size of keyframes for reconstruction. Specially, an on-line reconstruction keyframe set update strategy is designed to meet the requirement of real-time resource restricted situation. Experimental results on various types of videos demonstrate the performance of OnMSR does not vary much by imposing resource constraint in the proposed resource restricted OnMSR (RR-onMSR) algorithm. As a result, the proposed RR-onMSR is very effective for real-time onboard VS applications.

show abstract

“…VS has been extensively studied and there exist a large number of methods [6,7,8,9]. For examples, the shot boundary based algorithms firstly detect shot boundaries [10,11], and then keyframes are selected in each shot for VS.…”

Section: Introductionmentioning

confidence: 99%

Iterative keyframe selection by orthogonal subspace projection

Mei

Guan

Wang

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Recent developments on sparse dictionary selection have demonstrated promising results for Video Summarization (VS). However, the convex relaxation based solution cannot ensure the sparsity of the dictionary directly. In this paper, a selection matrix is proposed to model the VS problem, according to which the L 0 norm of this selection matrix is imposed to ensure sparsity directly. As a result, a computational efficient Orthogonal Subspace Projection (OSP) based Iterative Keyframe Selection (IKS) algorithm is proposed for VS. In addition, a Percentage Of Reconstruction (POR) criterion is proposed to provide an intuitive and flexible control of the length of final video summaries even without prior knowledge of a given video. Experimental results on a popular benchmark dataset demonstrate that our proposed algorithm outperforms the state-of-the-art methods.

show abstract

A Bag-of-Importance Model With Locality-Constrained Coding Based Feature Learning <newline/>for Video Summarization

Cited by 76 publications

References 30 publications

Spatial and temporal scoring for egocentric video summarization

Spatial and temporal scoring for egocentric video summarization

Resource restricted on-line Video Summarization with Minimum Sparse Reconstruction

Iterative keyframe selection by orthogonal subspace projection

Contact Info

Product

Resources

About