TV Genre Classification Using Multimodal Information and Multilayer Perceptrons

Montagnuolo, Maurizio; Messina, Alberto

doi:10.1007/978-3-540-74782-6_63

Cited by 13 publications

(29 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comprehensive overview of the studies on TV genre classification can be found in [8,9]. In these papers, the authors also present a robust TV genre classification system.…”

Section: Introductionmentioning

confidence: 99%

“…In these papers, the authors also present a robust TV genre classification system. In their first system [8], they utilize visual features based on color -hue, saturation, value, luminance-, texture -Tamura features contrast, directionality-, and temporal activity. The audio features consist of average speech rate and normalized duration values of several audio classes, e.g.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Content-based video genre classification using multiple cues

Ekenel

Semela

Stiefelhagen

2010

Proceedings of the 3rd International Workshop on Automated Information Extraction in Media Production

View full text Add to dashboard Cite

This paper presents an automatic video genre classification system, which utilizes several low-level audio-visual cues as well as cognitive and structural information to classify the types of TV programs and YouTube videos. Classification is performed using support vector machines. The system is integrated to our content-based video processing system and shares the same features that we have been using for high-level feature detection task in TRECVID evaluations. The proposed system is extensively evaluated using complete TV programs from Italian RAI TV channel, from French TV channels, and videos from YouTube on which 99.6%, 99%, and 92.4% correct classification rates are attained, respectively. These results show that the developed system can reliably determine TV programs' genre. It also provides a good basis for classifying genres of YouTube videos, which can be improved by using additional information, such as tags and titles, to obtain more robust results. Further experiments indicate that the quality of video does not influence the results significantly. It is found that the performance drop in classifying genres of YouTube videos is mainly due to the large variety of content contained in these videos.

show abstract

“…A comprehensive overview of the studies on TV genre classification can be found in [8,9]. In these papers, the authors also present a robust TV genre classification system.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Content-based video genre classification using multiple cues

Ekenel

Semela

Stiefelhagen

2010

Proceedings of the 3rd International Workshop on Automated Information Extraction in Media Production

View full text Add to dashboard Cite

show abstract

“…4 In contrast to the previous audio sets, the RAI video dataset allows for the development and comparison of approaches using different modalities. Recent works demonstrate a tendency toward multimodal approaches [11,37,38]. The results achieved by our approach indicate the outstanding performance of the selected audio features in terms of F1-score of 95.80% despite the use of single modality only.…”

Section: Comparison To Related Work On Media Classificationmentioning

confidence: 68%

“…The second video dataset contains more than 100 h of complete broadcasted programmes of RAI television and compromises 7 genres: commercials, football, music, news, 1 https://www.youtube.com/user/BBC/. talk shows, weather forecasts, and cartoons [37,38]. In contrast to the BBC documentaries, the RAI broadcasts exhibit strongly varying structures and no explicit regularities among the different genres.…”

Section: Application Scenarios and Datasetsmentioning

confidence: 99%

“…In addition to some acoustic features, Ekenel and Semena consider visual, structural, and cognitive features. Similar to the works by Montagnuolo et al [37,38], the features are selected in a way which reflects the editors process in TV production and cannot be applied to arbitrary data. The audio-based approach by Ekenel and Semela [11] achieves comparable performance in terms of F1-score of 95.70%.…”

Section: Comparison To Related Work On Media Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised group feature selection for media classification

Zaharieva

Breiteneder

Hudec

2017

Int J Multimed Info Retr

View full text Add to dashboard Cite

The selection of an appropriate feature set is crucial for the efficient analysis of any media collection. In general, feature selection strongly depends on the data and commonly requires expert knowledge and previous experiments in related application scenarios. Current unsupervised feature selection methods usually ignore existing relationships among components of multi-dimensional features (group features) and operate on single feature components. In most applications, features carry little semantics. Thus, it is less relevant if a feature set consists of complete features or a selection of single feature components. However, in some domains, such as content-based audio retrieval, features are designed in a way that they, as a whole, have considerable semantic meaning. The disruption of a group feature in such application scenarios impedes the interpretability of the results. In this paper, we propose an unsupervised group feature selection algorithm based on canonical correlation analysis (CCA). Experiments with different audio and video classification scenarios demonstrate the outstanding performance of the proposed approach and its robustness across different datasets.

show abstract