Rule-based video classification system for basketball video indexing

Zhou, Wensheng; Vellaikal, Asha; Kuo, C.‐C. Jay

doi:10.1145/357744.357941

Cited by 136 publications

(78 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Semantic video classification is one promising solution to bridge the semantic gap [1,2,4,5,12,14,33,41,42,44,51,52], but its performance largely depends on two inter-related issues: (1) suitable algorithms for video content representation and feature extraction; (2) effective algorithms for video classifier training.…”

Section: Bridging Semantic Gapmentioning

confidence: 99%

“…Two approaches are widely used to train video classifiers [1,2,4,5,12,14,20,27,33,41,42,44,51,52]: (a) GMM-based approach uses Gaussian mixture models to approximate the underlying distributions of video data; (b) SVM-based approach uses support vector machines to maximize the margin between the positive samples and the negative samples. As a generative model, the major advantage of the GMM-based approach is that prior knowledge can be effectively incorporated into training suitable concept models for accurate video classification and annotation by predefining part of the model structure.…”

Section: Bridging Semantic Gapmentioning

confidence: 99%

“…Our proposed work has significant differences from these existing works: (a) Rather than performing semantic video classification to achieve automatic news video content understanding, multi-modal content analysis results from multiple information sources are synchronized and integrated for indexing and exploring large-scale news video collections. Even though many video classification algorithms have been proposed [1,2,4,5,12,14,33,41,42,44,51,52], they cannot be used to achieve reliable classification of large-scale news video collections because of their huge diversities of visual properties and semantics. Most existing techniques for semantic video classification can perfectly work on same specific video domains with strong constraints of video contents.…”

Section: Bridging Semantic Gapmentioning

confidence: 99%

“…Most existing systems can only support automatic extraction of low-level visual features and search video clips via similarity matching according to their low-level visual features [1,2,5,30,33,41,42,44,51,52]. On the other hand, most users may not be familiar with the low-level visual features and they can only express their information needs via high-level video concepts (i.e., keywords for video concept interpretation) [16,17].…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, most users may not be familiar with the low-level visual features and they can only express their information needs via high-level video concepts (i.e., keywords for video concept interpretation) [16,17]. Due to huge diversities of visual properties and semantics in news videos, most existing tools for semantic video classification cannot directly be extended to achieve automatic analysis and exploration of largescale news video collections [1,2,5,9,33,41,42,44,51,52].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Integrating multi-modal content analysis and hyperbolic visualization for large-scale news video retrieval and exploration

Luo

Fan

Satoh

et al. 2008

Signal Processing: Image Communication

View full text Add to dashboard Cite

In this paper, we have developed a novel scheme to achieve more effective analysis, retrieval and exploration of large-scale news video collections by performing multi-modal video content analysis and synchronization. First, automatic keyword extraction is performed on news closed captions and audio channels to detect the most interesting news topics (i.e., keywords for news topic interpretation), and the associations among these news topics (i.e., contextual relationships among the news topics) are further determined according to their co-occurrence probabilities. Second, visual semantic items, such as human faces, text captions, video concepts, are extracted automatically by using our semantic video analysis techniques. The news topics are automatically synchronized with the most relevant visual semantic items. In addition, an interestingness weight is assigned for each news topic to characterize its importance. Finally, a novel hyperbolic visualization scheme is incorporated to visualize large-scale news topics according to their associations and interestingness. With a better global overview of large-scale news video collections, users can specify their queries more precisely and explore large-scale news video collections interactively. Our experiments on large-scale news video collections have provided very positive results.

show abstract

Section: Bridging Semantic Gapmentioning

confidence: 99%

Section: Bridging Semantic Gapmentioning

confidence: 99%

Section: Bridging Semantic Gapmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Integrating multi-modal content analysis and hyperbolic visualization for large-scale news video retrieval and exploration

Luo

Fan

Satoh

et al. 2008

Signal Processing: Image Communication

View full text Add to dashboard Cite

show abstract

Stereotype‐based versus personal‐based filtering rules in information filtering systems

Kuflik

Shapira

Shoval

2003

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

Rule-based information filtering systems maintain user profiles where the profile consists of a set of filtering rules expressing the user's information filtering policy. Filtering rules may refer to various attributes of the data items subject to the filtering process. In personal rulebased filtering systems, each user has his/her own personal filtering rules. In stereotype rule-based filtering systems, a user is assigned to a group of similar users (his/her stereotype) from which he/she inherits the stereotype's filtering profile. This study compares the effectiveness of the two alternative rule-based filtering methods: stereotype-based rules versus personal rules. We conducted a comparison between filtering effectiveness when using the personal rules or when using the stereotype-based rules. Although, intuitively, personal filtering rules seem to be more effective because each user has his own tailored rules, our comparative study reveals that stereotype filtering rules yield more effective results. We believe that this is because users find it difficult to evaluate their filtering preferences accurately. The results imply that by using a stereotype it is possible not only to overcome the problem of user effort required to generate a manual rule-based profile, but at the same time even provide a better initial user profile.

show abstract

Text‐based video content classification for online video‐sharing sites

Huang

Chen

2010

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

With the emergence of Web 2.0, sharing personal content, communicating ideas, and interacting with other online users in Web 2.0 communities have become daily routines for online users. User-generated data from Web 2.0 sites provide rich personal information (e.g., personal preferences and interests) and can be utilized to obtain insight about cyber communities and their social networks. Many studies have focused on leveraging usergenerated information to analyze blogs and forums, but few studies have applied this approach to video-sharing Web sites. In this study, we propose a text-based framework for video content classification of online-video sharing Web sites. Different types of user-generated data (e.g., titles, descriptions, and comments) were used as proxies for online videos, and three types of text features (lexical, syntactic, and content-specific features) were extracted. Three feature-based classification techniques (C4.5, Naïve Bayes, and Support Vector Machine) were used to classify videos. To evaluate the proposed framework, user-generated data from candidate videos, which were identified by searching user-given keywords onYouTube, were first collected.Then, a subset of the collected data was randomly selected and manually tagged by users as our experiment data.The experimental results showed that the proposed approach was able to classify online videos based on users' interests with accuracy rates up to 87.2%, and all three types of text features contributed to discriminating videos. Support Vector Machine outperformed C4.5 and Naïve Bayes techniques in our experiments. In addition, our case study further demonstrated that accurate video-classification results are very useful for identifying implicit cyber communities on video-sharing Web sites.

show abstract

Rule-based video classification system for basketball video indexing

Cited by 136 publications

References 3 publications

Integrating multi-modal content analysis and hyperbolic visualization for large-scale news video retrieval and exploration

Integrating multi-modal content analysis and hyperbolic visualization for large-scale news video retrieval and exploration

Stereotype‐based versus personal‐based filtering rules in information filtering systems

Text‐based video content classification for online video‐sharing sites

Contact Info

Product

Resources

About