You are in : Home » Results & submissions » Select UOA » 11 - Computer Science and Informatics » View submission: Queen Mary University of London » Outputs » Detail

Output details

11 - Computer Science and Informatics

Queen Mary University of London

Return to search Previous output Next output

Output 31 of 83 in the submission

Article title

Identifying Rare and Subtle Behaviors: A Weakly Supervised Joint Topic Model

Type

D - Journal article

DOI

10.1109/TPAMI.2011.81

Title of journal

IEEE Transactions on Pattern Analysis and Machine Intelligence

Article number

Volume number

Issue number

First page of article

2451

ISSN of journal

2160-9292

Year of publication

2011

URL

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5765988

Number of additional authors

Additional information

<23>Provides the first framework for identifying behaviours from sparse and subtle (few pixels) examples with weak supervision. These key missing capabilities prevent existing systems' deployment for security/safety according to user partners (gary.butcher@met.pnn.police.uk) in the FP7 project (FP7-217899) for which this is an output. It is an extension of highly cited earlier work (ICCV'09). It resulted in: invitation as an expert panel member to FP7 HIDE project (irma.vanderploeg@zuyd.nl) on surveillance ethics, invited seminars at Oxford (eric@robots.ox.ac.uk) and Microsoft Research (pkohli@microsoft.com). It also won development contracts from US DOD through QMUL spin-out VSL (rpkoger@visionsemantics.com) and was part of a NewScientist feature http://bit.ly/63AtFW.

Interdisciplinary

Cross-referral requested

Research group

None

Citation count

Proposed double-weighted

Double-weighted statement

Reserve for a double-weighted output

Non-English

English abstract