A System That Learns to Tag Videos by Watching Youtube

Ulges, Adrian; Schulze, Christian; Keysers, Daniel; Breuel, Thomas M.

doi:10.1007/978-3-540-79547-6_40

Cited by 26 publications

(48 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second one is an slightly modified version of the first one that uses sliding temporal windows of three seconds. The last method is called motion histograms and it is based on the work by Ulges [43]. Within [43] the motion vectors are extracted directly from the MPEG compressed domain by the XViD encoder.…”

Section: Motion Periodicitymentioning

confidence: 99%

“…The last method is called motion histograms and it is based on the work by Ulges [43]. Within [43] the motion vectors are extracted directly from the MPEG compressed domain by the XViD encoder. After that the area of the motion vectors is divided in 12 blocks and inside each of them an histogram of the 2D components for every vector within is generated.…”

Section: Motion Periodicitymentioning

confidence: 99%

See 1 more Smart Citation

Adult Video Content Detection Using Machine Learning Techniques

Ochoa

Yayilgan

Cheikh

2012

2012 Eighth International Conference on Signal Image Technology and Internet Based Systems

View full text Add to dashboard Cite

Automatic adult video detection is a problem of interest for many organizations around the globe aiming to restrict the availability of potentially harmful material for young audiences. Being most of the existing techniques a mere extension of the image categorization problem. In the present work we employ video genre classification techniques applied specifically for adult content detection by considering cinematic principles. Shot structure and camera motion in the temporal domain are used as the main features while skin detection and color histograms representation in the spatial domain are utilized as complementary features. Using a data set of more than 7 hours of video, our experiments comparing two different SVM algorithms achieve a high accuracy of 94.44%.

show abstract

Section: Motion Periodicitymentioning

confidence: 99%

Section: Motion Periodicitymentioning

confidence: 99%

Adult Video Content Detection Using Machine Learning Techniques

Ochoa

Yayilgan

Cheikh

2012

2012 Eighth International Conference on Signal Image Technology and Internet Based Systems

View full text Add to dashboard Cite

show abstract

“…Li et al propose a system of this type that is able to classify the scene, segment each object, and annotate the image with a list of tags [13]. Ulges et al apply a generative model to build a system for tag recommendation of videos [28]. The results corresponding to a certain query can be ranked according to some confidence scores associated to the words that form the query.…”

Section: Related Workmentioning

confidence: 99%

Finding meaning on YouTube: Tag recommendation and category discovery

Toderici

Aradhye

Paşca

et al. 2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

We present a system that automatically recommends tags for YouTube videos solely based on their audiovisual content. We also propose a novel framework for unsupervised discovery of video categories that exploits knowledge mined from the World-Wide Web text documents/searches. First, video content to tag association is learned by training classifiers that map audiovisual content-based features from millions of videos on YouTube.com to existing uploadersupplied tags for these videos. When a new video is uploaded, the labels provided by these classifiers are used to automatically suggest tags deemed relevant to the video. Our system has learned a vocabulary of over 20,000 tags. Secondly, we mined large volumes of Web pages and search queries to discover a set of possible text entity categories and a set of associated is-A relationships that map individual text entities to categories. Finally, we apply these is-A relationships mined from web text on the tags learned from audiovisual content of videos to automatically synthesize a reliable set of categories most relevant to videos -along with a mechanism to predict these categories for new uploads. We then present rigorous rating studies that establish that: (a) the average relevance of tags automatically recommended by our system matches the average relevance of the uploader-supplied tags at the same or better coverage and (b) the average precision@K of video categories discovered by our system is 70% with K=5.

show abstract

“…Some recent research as examined techniques for propagating preference information through a three-month snapshot of viewing data [2]. Other works have examined the unique properties of web videos [48] and the use of online videos as training data [44]. In contrast, we are interested in addressing the video annotation problem using a combination of visual feature analysis and a text model.…”

Section: The Web Collaborative Annotation and Youtubementioning

confidence: 99%

YouTube Scale, Large Vocabulary Video Annotation

Morsillo

Mann

Pal

2010

Video Search and Mining

View full text Add to dashboard Cite

As video content on the web continues to expand, it is increasingly important to properly annotate videos for effective search and mining. While the idea of annotating static imagery with keywords is relatively well known, the idea of annotating videos with natural language keywords to enhance search is an important emerging problem with great potential to improve the quality of video search. However, leveraging web-scale video datasets for automated annotation also presents new challenges and requires methods specialized for scalability and efficiency. In this chapter we review specific, state of the art techniques for video analysis, feature extraction and classification suitable for extremely large scale automated video annotation. We also review key algorithms and data structures that make truly large scale video search possible. Drawing from these observations and insights, we present a complete method for automatically augmenting keyword annotations to videos using previous annotations for a large collection of videos. Our approach is designed explicitly to scale to YouTube sized datasets and we present some experiments and analysis for keyword augmentation quality using a corpus of over 1.2 million YouTube videos. We demonstrate how the automated annotation of webscale video collections is indeed feasible, and that an approach combining visual features with existing textual annotations yields better results than unimodal models.

show abstract

A System That Learns to Tag Videos by Watching Youtube

Cited by 26 publications

References 14 publications

Adult Video Content Detection Using Machine Learning Techniques

Adult Video Content Detection Using Machine Learning Techniques

Finding meaning on YouTube: Tag recommendation and category discovery

YouTube Scale, Large Vocabulary Video Annotation

Contact Info

Product

Resources

About