Words and pictures in the news

Edwards, Jaety; White, Ryan M.; Forsyth, David

doi:10.3115/1119212.1119214

Cited by 15 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Names: We extract a lexicon of proper names from all the captions by identifying two or more capitalized words followed by a present tense verb ( [8]). Words are classified as verbs by first applying a list of morphological rules to present tense singular forms, and then comparing these to a database of known verbs (WordNet [25]).…”

Section: Datasetmentioning

confidence: 99%

Names and faces in the news

Berg

Edwards

et al.

Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.

284

296

View full text Add to dashboard Cite

We show quite good face clustering is possible for a dataset of inaccurately and ambiguously labelled face images. Our dataset is 44,773 face images, obtained by applying a face finder to approximately half a million captioned news images. This dataset is more realistic than usual face recognition datasets, because it contains faces captured "in the wild" in a variety of configurations with respect to the camera, taking a variety of expressions, and under illumination of widely varying color. Each face image is associated with a set of names, automatically extracted from the associated caption. Many, but not all such sets contain the correct name.We cluster face images in appropriate discriminant coordinates. We use a clustering procedure to break ambiguities in labelling and identify incorrectly labelled faces. A merging procedure then identifies variants of names that refer to the same individual. The resulting representation can be used to label faces in news images or to organize news pictures by individuals present.An alternative view of our procedure is as a process that cleans up noisy supervised data. We demonstrate how to use entropy measures to evaluate such procedures.

show abstract

Section: Datasetmentioning

confidence: 99%

Names and faces in the news

Berg

Edwards

et al.

Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.

284

296

View full text Add to dashboard Cite

show abstract

“…In the internet-domain, [9] and [10] collected over a halfmillion news images and associated captions and used clustering techniques to create a 28,000 image database of faces and name profiles, the only one of its kind to date.…”

Section: Related Workmentioning

confidence: 99%

Multi-Modal Person-Profiles from Broadcast News Video

Dagli

Rao

Huang

2007

Multimedia and Expo, 2007 IEEE International Conference On

View full text Add to dashboard Cite

The need to analyze and index large amounts of video information is becoming more important as the way people consume media continues to change. In recent years, the push to attack multi-media indexing and retrieval applications in a holistic, multi-modal way has garnered great attention. In this work we propose the holistic use of both audio, visual and textual information for the automatic indexing of broadcast news video to create person-profiles. Indexing videos in this matter helps facilitate a unique way to create multimedia person databases automatically, as well as for attacking existing video analysis tasks. We test our algorithm on news data from NBC and present areas for future exploration.

show abstract

“…Since then, a plethora of techniques from different fields have been studied. These include probabilistic frameworks [15], artificial neural networks [29], and others including those that seek to combine other modalities such as text into the search process [30]. In addition, algorithms from the text retrieval community like query-point-refinement [10] have been adapted to the problem in conjunction with pattern recognition techniques such as discriminant analysis [27], [31].…”

Section: A Relevance Feedbackmentioning

confidence: 99%

Active Learning for Interactive Multimedia Retrieval

et al. 2008

View full text Add to dashboard Cite

| As the first decade of the 21st century comes to a close, growth in multimedia delivery infrastructure and public demand for applications built on this backbone are converging like never before. The push towards reaching truly interactive multimedia technologies becomes stronger as our media consumption paradigms continue to change. In this paper, we will profile a technology leading the way in this revolution: active learning. Active learning is a strategy that helps alleviate challenges inherent in multimedia information retrieval through user interaction. We will show how active learning is ideally suited for the multimedia information retrieval problem by giving an overview of the paradigm and component technologies used with special attention given to the application scenarios in which these technologies are useful. Finally, we give insight into the future of this growing field and how it fits into the larger context of multimedia information retrieval.

show abstract

Words and pictures in the news

Cited by 15 publications

References 3 publications

Names and faces in the news

Names and faces in the news

Multi-Modal Person-Profiles from Broadcast News Video

Active Learning for Interactive Multimedia Retrieval

Contact Info

Product

Resources

About