Finding Person X: Correlating Names with Visual Appearances

Yang, Jun; Chen, Mingyu; Hauptmann, Alexander G.

doi:10.1007/978-3-540-27814-6_34

Cited by 49 publications

(45 citation statements)

References 6 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This baseline allows us to assess to what extent the visual processing improves accuracy over the use of text alone. It is interesting to note that in previous work [8] which combined transcripts of news footage with Eigenface-based face recognition, only small improvements in accuracy were obtained by incorporating visual face recognition.…”

Section: Naming Accuracymentioning

confidence: 98%

“…In [8], transcripts (spoken text without the identity of the speaker) and video of news footage were combined to recognize faces. Much attention was directed at how to predict from a name appearing in the transcript (typically spoken by a news anchor-person) when (relatively) the person referred to might appear in the video; addition of a standard face recognition method to this information gave small improvements in accuracy.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Taking the bite out of automated naming of characters in TV video

Everingham

Šivic

Zisserman

2009

Image and Vision Computing

164

168

View full text Add to dashboard Cite

We investigate the problem of automatically labelling appearances of characters in TV or film material with their names. This is tremendously challenging due to the huge variation in imaged appearance of each character and the weakness and ambiguity of available annotation. However, we demonstrate that high precision can be achieved by combining multiple sources of information, both visual and textual. The principal novelties that we introduce are: (i) automatic generation of time stamped character annotation by aligning subtitles and transcripts; (ii) strengthening the supervisory information by identifying when characters are speaking. In addition we incorporate complementary cues of face matching and clothing matching to propose common annotations for face tracks, and consider choices of classifier which can potentially correct errors made in the automatic extraction of training data from the weak textual annotation. Results are presented on episodes of the TV series "Buffy the Vampire Slayer".

show abstract

Section: Naming Accuracymentioning

confidence: 98%

Section: Related Workmentioning

confidence: 99%

Taking the bite out of automated naming of characters in TV video

Everingham

Šivic

Zisserman

2009

Image and Vision Computing

164

168

View full text Add to dashboard Cite

show abstract

“…Face information has been combined with text information for face or person retrieval in video [21,111,53,112,84]. In [111], multimodal content in videos, including names occurred in the transcript, face information, anchor scenes, and the timing pattern between names and appearances of people, are exploited to find specific persons in broadcast news videos.…”

Section: Face Retrieval In Videomentioning

confidence: 99%

“…In [111], multimodal content in videos, including names occurred in the transcript, face information, anchor scenes, and the timing pattern between names and appearances of people, are exploited to find specific persons in broadcast news videos. However, face information was given very small weight in their system.…”

Section: Face Retrieval In Videomentioning

confidence: 99%

Face Recognition and Retrieval in Video

Shan¹

2010

Video Search and Mining

View full text Add to dashboard Cite

Abstract. Automatic face recognition has long been established as one of the most active research areas in computer vision. Face recognition in unconstrained environments remains challenging for most practical applications. In contrast to traditional still-image based approaches, recently the research focus has shifted towards videobased approaches. Video data provides rich and redundant information, which can be exploited to resolve the inherent ambiguities of image-based recognition like sensitivity to low resolution, pose variations and occlusion, leading to more accurate and robust recognition. Face recognition has also been considered in the content-based video retrieval setup, for example, character-based video search. In this chapter, we review existing research on face recognition and retrieval in video. The relevant techniques are comprehensively surveyed and discussed.

show abstract

“…The recent researches show that combining textual and visual information increases the correctness of face-name association [1,2] and this method is also used in this study in order to name the faces in their large dataset. Images that are taken from news images with their associated captions are named with simple natural language and clustering 50 techniques.…”

Section: Related Workmentioning

confidence: 99%

Recognizing faces in news photographs on the web

Zitouni

Bulut

Duygulu

2009

2009 24th International Symposium on Computer and Information Sciences

View full text Add to dashboard Cite

Abstract-We propose a graph based method in order to recognize the faces that appear on the web using a small training set. First, relevant pictures of the desired people are collected by querying the name in a text based search engine in order to construct the data set. Then, detected faces in these photographs are represented using SIFT features extracted from facial features. The similarities of faces are represented in a graph which is then used in random walk with restart algorithm to provide links between faces. Those links are used for recognition by using two different methods.

show abstract

Finding Person X: Correlating Names with Visual Appearances

Cited by 49 publications

References 6 publications

Taking the bite out of automated naming of characters in TV video

Taking the bite out of automated naming of characters in TV video

Face Recognition and Retrieval in Video

Recognizing faces in news photographs on the web

Contact Info

Product

Resources

About