An iteratively reweighting algorithm for dynamic video summarization

Dong, Pei; Xia, Yong; Wang, Shanshan; Li, Zhuo; Feng, David Dagan

doi:10.1007/s11042-014-2126-8

Cited by 9 publications

(10 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…VIREO-374 concept detectors have demonstrated good performance in various applications. 18,20,50,51 To recognize the high-level semantic concepts for each keyframe of videos, VIREO-374 classifiers are exploited as the baseline detector set because of their supportive nature for Web video categories and good performance in various multimedia tasks.…”

Section: Web Video Classification Using Content Featuresmentioning

confidence: 99%

“…While some works concentrate on classifying Web videos based on the metadata uploaded by the user, other works utilize low‐level features by considering the visual and audio features along with text features. Furthermore, to fill the semantic gap between low‐level features and high‐level semantics, the utilization of different high‐level concept detectors has been examined in various multimedia tasks . To classify Web videos, a pool of informative concept detectors per category is selected using cross‐entropy optimization and by Flickr‐enriched context space .…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, to fill the semantic gap between low-level features and high-level semantics, the utilization of different high-level concept detectors [13][14][15][16][17] has been examined in various multimedia tasks. [18][19][20][21] To classify Web videos, a pool of informative concept detectors per category is selected using cross-entropy optimization 21 and by Flickr-enriched context space. 9 In this work, concept detectors are utilized in two different ways to classify Web videos.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Web video classification with visual and contextual semantics

Afzal

Shah

Tufail

2019

Int J Communication

View full text Add to dashboard Cite

Summary On the social Web, the amount of video content either originated from wireless devices or previously received from media servers has increased enormously in the recent years. The astounding growth of Web videos has stimulated researchers to propose new strategies to organize them into their respective categories. Because of complex ontology and large variation in content and quality of Web videos, it is difficult to get sufficient, precisely labeled training data, which causes hindrance in automatic video classification. In this paper, we propose a novel content‐ and context‐based Web video classification framework by rendering external support through category discriminative terms (CDTs) and semantic relatedness measure (SRM). Mainly, a three‐step framework is proposed. Firstly, content‐based video classification is proposed, where twofold use of high‐level concept detectors is leveraged to classify Web videos. Initially, category classifiers induced from VIREO‐374 detectors are trained to classify Web videos, and then concept detectors with high confidence for each video are mapped to CDT through SRM‐assisted semantic content fusion function to further boost the category classifiers, which intuitively provide a more robust measure for Web video classification. Secondly, a context‐based video classification is proposed, where twofold use of contextual information is also harnessed. Initially, cosine similarity and then semantic similarity are measured between text features of each video and CDT through vector space model (VSM)‐ and SRM‐assisted semantic context fusion function, respectively. Finally, classification results from content and context are fused to compensate for the shortcomings of each other, which enhance the video classification performance. Experiments on large‐scale video dataset validate the effectiveness of the proposed solution.

show abstract

Section: Web Video Classification Using Content Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Web video classification with visual and contextual semantics

Afzal

Shah

Tufail

2019

Int J Communication

View full text Add to dashboard Cite

show abstract

“…[ 19,32,33,39,74,135,145,169,173,203] Surveillance Continuous recording of activity using either a static or moving camera. Single or multiple cameras Event detection and anomaly identification.…”

Section: Rushesmentioning

confidence: 99%

Video Skimming: Taxonomy and Comprehensive Survey

K.,

Sen,

Raman

2019

Preprint

View full text Add to dashboard Cite

Video skimming, also known as dynamic video summarization, generates a temporally abridged version of a given video. Skimming can be achieved by identifying significant components either in uni-modal or multimodal features extracted from the video. Being dynamic in nature, video skimming, through temporal connectivity, allows better understanding of the video from its summary. Having this obvious advantage, recently, video skimming has drawn the focus of many researchers benefiting from the easy availability of the required computing resources. In this paper, we provide a comprehensive survey on video skimming focusing on the substantial amount of literature from the past decade. We present a taxonomy of video skimming approaches, and discuss their evolution highlighting key advances. We also provide a study on the components required for the evaluation of a video skimming performance.

show abstract

“…Essa necessidade tem sido foco de estudos que abarcam sobre a utilização de semântica nesse processo, mais especificamente, para a incorporação de metadados nos conteúdos audiovisuais com o objetivo de facilitar o acesso às informações neles contidas. Dong et. al.…”

Section: Revisão Da Literaturaunclassified

Desafios para a Localização e Recuperação de Informação em Conteúdos Educacionais Audiovisuais

Silveira¹,

Borges²

2017

Anais Do Workshop De Desafios Da Computação Aplicada À Educação (DesafIE!)

View full text Add to dashboard Cite

Com a evolução tecnológica, houve um aumento significativo do volume de dados na Web e do número de usuários, acarretando em um grande desafio a rapidez, precisão e eficiência na localização e recuperação da informação desejada. No contexto da educação, o e-learning e o uso de conteúdos audiovisuais têm se popularizado e o tamanho das bases de dados com esses tipos de conteúdo está crescendo. Dessa forma, é necessário um modo eficiente de estruturar e organizar esses conteúdos de acordo com seu significado semântico. Assim, o objetivo deste trabalho é discutir os desafios da utilização da semântica para subsidiar o processo de localização e recuperação de informação em conteúdos educacionais audiovisuais.

show abstract

An iteratively reweighting algorithm for dynamic video summarization

Cited by 9 publications

References 65 publications

Web video classification with visual and contextual semantics

Web video classification with visual and contextual semantics

Video Skimming: Taxonomy and Comprehensive Survey

Desafios para a Localização e Recuperação de Informação em Conteúdos Educacionais Audiovisuais

Contact Info

Product

Resources

About