Conference item icon

Conference item

It's in the bag: stronger supervision for automated face labelling

Abstract:

The objective of this work is automatic labelling of characters in TV video and movies, given weak supervisory information provided by an aligned transcript. We make four contributions: (i) a new strategy for obtaining stronger supervisory information from aligned transcripts; (ii) an explicit model for classifying background characters, based on their face-tracks; and (iii) employing new ConvNet based face features. Each of these contributions delivers a significant boost in performance, an...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Oxford college:
Brasenose College
Role:
Author
Publisher:
International Conference on Computer Vision Publisher's website
Journal:
ICCV 2015 Journal website
Host title:
ICCV 2015
Publication date:
2015-12-31
Acceptance date:
2015-04-22
Event location:
Santiago, Chile
Source identifiers:
678969
Keywords:
Pubs id:
pubs:678969
UUID:
uuid:4c488040-6c9e-4549-a1a4-b7b6d98813db
Local pid:
pubs:678969
Deposit date:
2017-02-09

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP