Group Feature Selection for Audio-Based Video Genre Classification

Sageder, Gerhard; Zaharieva, Maia; Breiteneder, Christian

doi:10.1007/978-3-319-27671-7_3

Cited by 6 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we propose an unsupervised group feature selection approach which is an extended version of [45,46]. The approach exploits the canonical correlations between features (of potentially strongly varying dimensionality) to estimate the relevance of every single feature.…”

Section: Proposed Approachmentioning

confidence: 99%

“…In this section, we compare the performance of the proposed group feature selection approach with our previous work, CcaFS [45], which applies CCA on feature pairs, with two well-established but supervised subset-based feature selection approaches, consistency-based (ConFS) [34] and correlation-based(CorrFS) [16], and with the group feature selection approach group lasso (GL) [62]. For all approaches, we perform feature selection and model building for the classifier on 20% of the available data.…”

Section: Comparison To Related Work On Feature Selectionmentioning

confidence: 99%

“…On the opposite end of the scale, low-correlated features provide additional information which can improve the descriptive power of the feature set. In previous work, we explored the correlation-based ranking of feature pairs in order to perform feature selection [45,46]. In contrast to our previous approach, in this work we investigate each feature separately with respect to the currently selected feature set, improving both the quality and the classification performance of the selected features.…”

Section: Introductionmentioning

confidence: 99%

“…We propose an improved version of the CCA-based feature selection method presented in [45,46] that essentially compares CCA values between a single feature candidate and the set of already selected features. The approach is unsupervised and maintains the interpretation of entire features as the underlying feature components are kept together.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Unsupervised group feature selection for media classification

Zaharieva

Breiteneder

Hudec

2017

Int J Multimed Info Retr

Self Cite

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

Section: Proposed Approachmentioning

confidence: 99%

Section: Comparison To Related Work On Feature Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised group feature selection for media classification

Zaharieva

Breiteneder

Hudec

2017

Int J Multimed Info Retr

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this work we followed our previous setup [18,21] where only speech segments are used to train the LDA model. For each show, the domain posteriors of its segments were accumulated and length normalised and used as features for the discriminative classifier in the later stage: It is important to note that this dataset is by orders of magnitude larger than most of the datasets used in the literature for the genre ID task [2,4,5,6,8,15].…”

Section: Acoustic Latent Dirichlet Allocationmentioning

confidence: 99%

Automatic Genre and Show Identification of Broadcast Media

Doulaty

Saz

et al. 2016

Interspeech 2016

View full text Add to dashboard Cite

Huge amounts of digital videos are being produced and broadcast every day, leading to giant media archives. Effective techniques are needed to make such data accessible further. Automatic meta-data labelling of broadcast media is an essential task for multimedia indexing, where it is standard to use multi-modal input for such purposes. This paper describes a novel method for automatic detection of media genre and show identities using acoustic features, textual features or a combination thereof. Furthermore the inclusion of available meta-data, such as time of broadcast, is shown to lead to very high performance. Latent Dirichlet Allocation is used to model both acoustics and text, yielding fixed dimensional representations of media recordings that can then be used in Support Vector Machines based classification. Experiments are conducted on more than 1200 hours of TV broadcasts from the British Broadcasting Corporation (BBC), where the task is to categorise the broadcasts into 8 genres or 133 show identities. On a 200-hour test set, accuracies of 98.6% and 85.7% were achieved for genre and show identification respectively, using a combination of acoustic and textual features with meta-data.

show abstract

GenSpecVidOnt: a reference ontology for knowledge based video analytics with multimodal genre detection

Sreeja

Kovoor

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Group Feature Selection for Audio-Based Video Genre Classification

Cited by 6 publications

References 19 publications

Unsupervised group feature selection for media classification

Unsupervised group feature selection for media classification

Automatic Genre and Show Identification of Broadcast Media

GenSpecVidOnt: a reference ontology for knowledge based video analytics with multimodal genre detection

Contact Info

Product

Resources

About