(Apologies if you received multiple copies of this email)
Dear Colleague,
We are please to introduce the workshop on “Deep Learning on Irregular Domains” (DLID), hosted at the British Machine Vision Conference 2017 at Imperial College London.
***
WORKSHOP FOCUS:
Advances in learning spatially related features via convolutional neural network (CNN) architectures has resulted in strong performance gains within the image understanding domain. Many real world problems do not exhibit such a regular spatial domain, making it non-trivial to define a feature mining operator. Such domains may still exhibit spatial relationships that may be of use for learning; weather stations across a country, or joints on the human skeleton for example. The area of deep learning on irregular domains has attempted to make use of the intrinsic spatial information encoded in the domain to learn features on the problem at hand. They employ such methods as signal processing on the graph, graph-based CNNs and manifold-based heat kernels to learn a filtering on input data from a localised region of the domain.
This workshop aims to foster study into the understanding of implementing deep learning on spaces in which conventional CNN operations are ill-defined. It is hoped that the community will be able to engage in dedicated discussions into advancing state of the art performance for problem domains with an irregular topology.
***
CALL FOR PAPERS:
DLID is currently accepting submissions from a wide range of topics, including:
• Exploiting spatial relationships in non-Euclidean domains
• Data mining and signal processing on graphs
• Spectral graph methods
• Deep learning on irregular problems and graph structured data
• Feature extraction on graphs
• Applications of deep learning on novel domains
• Developing filters on manifolds, graphs and non-Euclidean spaces
• Learning domain topology
• Graph construction and pooling
• Domains with an irregular spatial relationships that would benefit from feature mining.
Alongside method papers, we also encourage submissions concerning application of such methods. This includes, but is not limited to, such domains as:
• Medical image analysis
• Text analysis
• Social media analysis
• Human action recognition
• Sensor network analysis
Submissions can be between 3 and 8 pages in length, with additional pages for references.
A selection of suitable best papers accepted to the workshop will be invited to submit to a special issue journal publication on the topic.
***
KEY DATES:
Paper Submission: 7th July 2017
Author Notification: 17th July 2017
Camera Ready Submission: 24th July 2017
Workshop Event: 7th September 2017
***
For further information regarding the DLID workshop, please visit: dlid.swansea.ac.uk
Best,
Mike Edwards
Computer Vision and Medical Image Analysis Group
402, Faraday Tower, Department of Computer Science
University of Swansea, Singleton Park
Swansea, SA2 8PP, UK
[log in to unmask]
csvision.swan.ac.uk
_ __ ___ ____ _____ ______ _____ ____ ___ __ _
To send a message to this list - email [log in to unmask]
To leave: [log in to unmask], leave vision
To join: [log in to unmask], join vision Firstname Lastname
To contact the list adminstrator, email [log in to unmask]
_ __ ___ ____ _____ ______ _____ ____ ___ __ _
|