Learning from Video and Text via Large-Scale Discriminative Clustering
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F17%3A00318982" target="_blank" >RIV/68407700:21730/17:00318982 - isvavai.cz</a>
Result on the web
<a href="http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237824" target="_blank" >http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8237824</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICCV.2017.562" target="_blank" >10.1109/ICCV.2017.562</a>
Alternative languages
Result language
angličtina
Original language name
Learning from Video and Text via Large-Scale Discriminative Clustering
Original language description
Discriminative clustering has been successfully applied to a number of weakly supervised learning tasks. Such applications include person and action recognition, text-to-video alignment, object co-segmentation and co-localization in videos and images. One drawback of discriminative clustering, however, is its limited scalability. We address this issue and propose an online optimization algorithm based on the Block-Coordinate Frank-Wolfe algorithm. We apply the proposed method to the problem of weakly supervised learning of actions and actors from movies together with corresponding movie scripts. The scaling up of the learning problem to 66 feature-length movies enables us to significantly improve weakly supervised action recognition.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/EF15_003%2F0000468" target="_blank" >EF15_003/0000468: Intelligent Machine Perception</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2017 IEEE International Conference on Computer Vision (ICCV 2017)
ISBN
978-1-5386-1032-9
ISSN
1550-5499
e-ISSN
—
Number of pages
10
Pages from-to
5267-5276
Publisher name
IEEE
Place of publication
Piscataway
Event location
Venice
Event date
Oct 22, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000425498405037