Classification TV programs based on audio information using hidden Markov model

Liu, Z.; Huang, Jiajia; Wang, Y.

doi:10.1109/mmsp.1998.738908

Cited by 87 publications

(51 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…a common approach is to use Mel-Frequency Cepstral Coefficients (MFCC) [24] or to use time domain features, e.g. Root Mean Square of signal energy (RMS) [23] or Zero-Crossing Rate (ZCR) [25].…”

Section: Audio Descriptorsmentioning

confidence: 99%

“…Audio-based information may be derived from, both, time and frequency domains. Usual time-domain approaches include the use of Root Mean Square of signal energy (RMS) [23], sub-band information [5], Zero-Crossing Rate (ZCR) [25] or silence ratio; while frequency-domain features include energy distribution, frequency centroid [25], bandwidth, pitch [6] or Mel-Frequency Cepstral Coefficients (MFCC) [24].…”

mentioning

confidence: 99%

See 1 more Smart Citation

An audio-visual approach to web video categorization

Ionescu

Seyerlehner

Mironica

et al. 2012

Multimed Tools Appl

View full text Add to dashboard Cite

Abstract:In this paper we address the issue of automatic video genre categorization of web media using an audio-visual approach. To this end, we propose content descriptors which exploit audio, temporal structure and color information. The potential of our descriptors is experimentally validated both from the perspective of a classification system and as an information retrieval approach. Validation is carried out on a real scenario, namely on more than 288 hours of video footage and 26 video genres specific to blip.tv media platform. Additionally, to reduce semantic gap, we propose a new relevance feedback technique which is based on hierarchical clustering. Experimental tests prove that retrieval performance can be significantly increased in this case, becoming comparable to the one obtained with high level semantic textual descriptors. Abstract In this paper we address the issue of automatic video genre categorization of web media using an audio-visual approach. To this end, we propose content descriptors which exploit audio, temporal structure and color information. The potential of our descriptors is experimentally validated both from the perspective of a classification system and as an information retrieval approach. Validation is carried out on a real scenario, namely on more than 288 hours of video footage and 26 video genres specific to blip.tv media platform. Additionally, to reduce semantic gap, we propose a new relevance feedback technique which is based on hierarchical clustering. Experimental tests prove that retrieval performance can be significantly increased in this case, becoming comparable to the one obtained with high level semantic textual descriptors. Powered by Editorial Manager® and Preprint Manager® from Aries Systems Corporation

show abstract

Section: Audio Descriptorsmentioning

confidence: 99%

mentioning

confidence: 99%

An audio-visual approach to web video categorization

Ionescu

Seyerlehner

Mironica

et al. 2012

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…There have been many systems proposed for specific video genres. Partition and classification of broadcast videos into meaningful sections have attracted significant attention [1][2][3][4][5][6][7][8]. In [7], Liu et al segment news reports from other categories based on both audio and visual information.…”

Section: Related Backgroundmentioning

confidence: 99%

Content Structure Discovery in Educational Videos Using Shared Structures in the Hierarchical Hidden Markov Models

Phung

Bui

Venkatesh

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper, we present an application of the hierarchical HMM for structure discovery in educational videos. The HHMM has recently been extended to accommodate the concept of shared structure, ie: a state might multiply inherit from more than one parents. Utilising the expressiveness of this model, we concentrate on a specific class of video -educational videos -in which the hierarchy of semantic units is simpler and clearly defined in terms of topics and its subunits. We model the hierarchy of topical structures by an HHMM and demonstrate the usefulness of the model in detecting topic transitions.

show abstract

“…To extract semantic meanings like genre from video, several works have been studied such as video genre or scene detection methods with audio or visual information [2,3]. Ba Tu Truong et al [2] showed about 83.1 % detection rate using C4.5 decision tree classifier and visual information from 60 second long video clips.…”

Section: Introductionmentioning

confidence: 99%

“…Ba Tu Truong et al [2] showed about 83.1 % detection rate using C4.5 decision tree classifier and visual information from 60 second long video clips. Zhu Liu et al [3] used audio information and 5-staste HMM with 28 symbols in their method. Their result described the accuracy of about 84.7 % with 10 minutes long audio clips.…”

Section: Introductionmentioning

confidence: 99%

Automatic Video Genre Detection for Content-Based Authoring

Jin

Bae

2004

Advances in Multimedia Information Processing - PCM 2004

View full text Add to dashboard Cite

Abstract. In this paper, we propose a new video genre detection using semantic classification with multi-modal features. MPEG-7 audio-visual descriptors are used as multi-modal features. From the low-level multimodal features, genre as high-level semantic meaning is detected by using GINI index in Classification And Regression Tree (CART) algorithm. Experimental results show that the proposed method is useful to detect video genre automatically with a high detection rate.

show abstract

Classification TV programs based on audio information using hidden Markov model

Cited by 87 publications

References 3 publications

An audio-visual approach to web video categorization

An audio-visual approach to web video categorization

Content Structure Discovery in Educational Videos Using Shared Structures in the Hierarchical Hidden Markov Models

Automatic Video Genre Detection for Content-Based Authoring

Contact Info

Product

Resources

About