Scene pathfinder: unsupervised clustering techniques for movie scenes extraction

Ellouze, Mehdi; Boujemaa, Nozha; Alimi, Adel M.

doi:10.1007/s11042-009-0325-5

Cited by 15 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vasileios et al took color histograms as features to segments video, which used the Euclidean distance and the spectral clustering algorithm to cluster frames [2]. Ellouze et al repaired the over-segmentation problem by classifying sections based on tempo features and fuzzy CMeans [3]. Das et al defined a unified interval type-2 fuzzy rule-based model using a fuzzy histogram and fuzzy co-occurrence matrix to detect cuts and various types of gradual transitions [4].…”

Section: A the Rules-based Methodsmentioning

confidence: 99%

See 1 more Smart Citation

User-Guided Clustering for Video Segmentation on Coarse-Grained Feature Extraction

Peng

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Video segmentation is the task of temporally dividing a video into semantic sections, which are typically based on a specific concept or a theme that is usually defined by the user's intention. However, previous studies of video segmentation have that far not taken a user's intention into consideration. In this paper, a two-stage user-guided video segmentation framework has been presented, including dimension reduction and temporal clustering. During the dimension reduction stage, a coarse granularity feature extraction is conducted by a deep convolutional neural network pre-trained on ImageNet. In the temporal clustering stage, the information of the user's intention is utilized to segment videos on time domain with a proposed operator, which calculates the similarity distance between dimension reduced frames. To provide more insight into the videos, a hierarchical clustering method that allows users to segment videos at different granularities is proposed. Evaluation on Open Video Scene Detection(OVSD) dataset shows that the average F-score achieved by the proposed method is 0.72, even coarse-grained feature extraction is adopted. The evaluation also demonstrated that the proposed method can not only produce different segmentation results according to the user's intention, but it also produces hierarchical segmentation results from a low level to a higher abstraction level. INDEX TERMSClustering methods, dimension reduction, feature extraction, user centered design, video segmentation.

show abstract

Section: A the Rules-based Methodsmentioning

confidence: 99%

“…. , S e1 ) generated by the temporal clustering method described in Algorithm 2, the hierarchical clustering selects a frame as the key frame of S i according to (3), which has the smallest difference from other frames in S i .…”

Section: Hierarchical Clusteringmentioning

confidence: 99%

User-Guided Clustering for Video Segmentation on Coarse-Grained Feature Extraction

Peng

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Scene detection techniques may be rule based, where some predefined rule are constructed to analyze the frames and shots and decision is made if they belong to the same scene or not [5]. Some scene detection techniques may be graph based [41], stochastic based or cluster based [42], [43], [44] in contrast to the rule based [5], [45]. The accuracy of such algorithms range from 80% to 86% as reported these different attempts.…”

Section: Related Workmentioning

confidence: 99%

Content-based Automatic Video Genre Identification

Shamsi¹,

Daudpota²,

Shaikh³

2019

IJACSA

View full text Add to dashboard Cite

Video content is evolving enormously with the heavy usage of internet and social media websites. Proper searching and indexing of such video content is a major challenge. The existing video search potentially relies on the information provided by the user, such as video caption, description and subsequent comments on the video. In such case, if users provide insufficient or incorrect information about the video genre, the video may not be indexed correctly and ignored during search and retrieval. This paper proposes a mechanism to understand the contents of video and categorize it as Music Video, Talk Show, Movie/Drama, Animation and Sports. For video classification, the proposed system uses audio and visual features like audio signal energy, zero crossing rate, spectral flux from audio and shot boundary, scene count and actor motion from video. The system is tested on popular Hollywood, Bollywood and YouTube videos to give an accuracy of 96%.

show abstract

“…The close relation between video scenes and the real-life events depicted in the video make scene detection a key-enabling technology for advanced applications such as event-based video indexing [Ballan et al 2011]. This has been used in movie video summarisation [Sang and Xu 2010], artistic video archives [Mitrović et al 2010], news story classification [Aly et al 2010 [Ellouze et al 2010;Zhu and Liang 2011]. Much work has been done on scene segmentation in the last decade.…”

Section: Semantic Temporal Segmentationmentioning

confidence: 99%

“…Generally speaking, automatic scene boundary detection techniques can be categorized into following classes, i.e. graph based [Ayadi et al 2012;del Fabro and Boszormenyi 2010;Mezaris, Sidiropoulos, Dimou and Kompatsiaris 2010;Sakarya and Telatar 2010;Sakarya et al 2012;Seeling 2010;Sidiropoulos, Mezaris, Kompatsiaris, Meinedo, Bugalho and Trancoso 2011;Su et al 2012;, film editing technique based [Choroś and Pawlaczyk 2010;Zhu and Liang 2011], statistics learning based [Baber, Afzulpurkar and Bakhtyar 2011;Chao, Changsheng, Jian and Hanqing 2011;Ellouze, Boujemaa and Alimi 2010;Huang and Zhang 2010;Mohanta et al 2010;Sang and Xu 2010;Seung-Bo et al 2010;Tjondronegoro and Chen 2010;Wilson et al 2010;Zeng et al 2010], and multi-features based [Dumont and Quénot 2012;Ercolessi et al 2011;Heejun and Jaesoo 2011;Huang and Tung 2010;Hui and Cuihua 2010;Mitrović, Hartlieb, Zeppelzauer and Zaharieva 2010;Poulisse et al 2012].…”

Section: Semantic Temporal Segmentationmentioning

confidence: 99%

MAC-REALM: A Video Content Feature Extraction and Modelling Framework

Parmar

Angelides

2015

The Computer Journal

View full text Add to dashboard Cite

This paper discusses MAC-REALM, a framework for extraction of syntactic and semantic content features and content modelling with either little or no user interaction. The framework integrates a four filter-plane strategy: a pre-processing plane that filters redundant data, a syntactic feature extraction plane that filters syntactic features, a semantic relationships analysis and linkage plane that filters the spatial and temporal relationships of content features, and finally a content modelling plane where the syntactic and semantic content features are integrated into a content model. Each of the four planes is split into three layers: the content layer, where the content to be processed is stored, the application layer, where the content is converted into content descriptions, and the MPEG-7 layer, where content descriptions are serialized. Using MPEG-7 standards to produce the content model will provide wideranging interoperability, while facilitating granular multi-content type searches. MAC-REALM aims at 'bridging' the semantic gap, by integrating the syntactic and semantic content features from extraction through to modelling.

show abstract

Scene pathfinder: unsupervised clustering techniques for movie scenes extraction

Cited by 15 publications

References 24 publications

User-Guided Clustering for Video Segmentation on Coarse-Grained Feature Extraction

User-Guided Clustering for Video Segmentation on Coarse-Grained Feature Extraction

Content-based Automatic Video Genre Identification

MAC-REALM: A Video Content Feature Extraction and Modelling Framework

Contact Info

Product

Resources

About