TV ad video categorization with probabilistic latent concept learning

Authors:
Jinqiao Wang;Lingyu Duan;Lei Xu;Hanqing Lu;Jesse S. Jin
Affiliations:
Chinese Academy of Sciences, Beijing, China;Institute for Infocomm Research, Singapore;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;University of Newcastle, Newcastle, Australia
Venue:
Proceedings of the international workshop on Workshop on multimedia information retrieval
Year:
2007

Citing 22
Cited 8

Probabilistic latent semantic indexing

Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
Analyzing the effectiveness and applicability of co-training

Proceedings of the ninth international conference on Information and knowledge management
Unsupervised learning by probabilistic latent semantic analysis

Machine Learning
Retrieval of Commercials by Semantic Content: The Semiotic Perspective

Multimedia Tools and Applications
Shot Partitioning Based Recognition of TV Commercials

Multimedia Tools and Applications
On the detection and recognition of television commercials

ICMCS '97 Proceedings of the 1997 International Conference on Multimedia Computing and Systems
Scale & Affine Invariant Interest Point Detectors

International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Toward better weighting of anchors

Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval
Extraction and recognition of artificial text in multimedia documents

Pattern Analysis & Applications
Text Detection in Images Based on Unsupervised Classification of High-Frequency Wavelet Coefficients

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Scene Text Extraction in Natural Scene Images using Hierarchical Feature Combining and Verification

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Semi-Supervised Cross Feature Learning for Semantic Concept Detection in Videos

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
A Bayesian Hierarchical Model for Learning Natural Scene Categories

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Vector Boosting for Rotation Invariant Multi-View Face Detection

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Modeling Scenes with Local Descriptors and Latent Aspects

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Segmentation, categorization, and identification of commercial clips from TV streams using multimodal analysis

MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
The challenge problem for automated detection of 101 semantic concepts in multimedia

MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
SURF: speeded up robust features

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Scene classification via pLSA

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
A probabilistic framework for semantic video indexing, filtering,and retrieval

IEEE Transactions on Multimedia
A Thousand Words in a Scene

IEEE Transactions on Pattern Analysis and Machine Intelligence

A Lightweight Mobile TV Recommender

EUROITV '08 Proceedings of the 6th European conference on Changing Television Environments
Watch, Listen & Learn: Co-training on Captioned Images and Videos

ECML PKDD '08 Proceedings of the 2008 European Conference on Machine Learning and Knowledge Discovery in Databases - Part I
Modeling emotional context from latent semantics

Proceedings of the 1st international conference on Designing interactive user experiences for TV and video
Automatic text discovering through stroke-based segmentation and text string combination

MM '08 Proceedings of the 16th ACM international conference on Multimedia
Linking video ads with product or service information by web search

ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Personalized online video recommendation by neighborhood score propagation based global ranking

Proceedings of the First International Conference on Internet Multimedia Computing and Service
Is singular value decomposition useful for word similarity extraction?

Language Resources and Evaluation
Categorization of display ads using image and landing page features

Proceedings of the Third Workshop on Large Scale Data Mining: Theory and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a multi-modal approach to TV ads classification by advertised products/services. A bag-of-words representation is proposed to discover ad categories-related latent visual and textual concepts by probabilistic latent semantics analysis (PLSA). We use multi-modal concepts to represent ad categories in the latent semantics space. In particular, we resort to external resources (e.g., a brand list, encyclopedia) to expand sparse textual information. A semi-supervised co-training is finally employed to fuse visual and textual features for ad classification. Our experiments have achieved promising results in terms of classification accuracy and scalability to new ad categories. The resulting ad classifiers can be applied to digest ads from TV streams, which is useful for TV viewers to manage ads in a positive manner. The digested ads can be considered the video-based alert for emerging products/services. Thus the reachability and focus of TV ads can be improved.