dc.contributor.author |
Burke, Michael G
|
|
dc.date.accessioned |
2017-11-06T12:50:37Z |
|
dc.date.available |
2017-11-06T12:50:37Z |
|
dc.date.issued |
2017-10 |
|
dc.identifier.citation |
Burke, M.G. 2017. Leveraging Gaussian process approximations for rapid image overlay production. SAWACMMM '17- Proceedings of the ACM Multimedia 2017 Workshop on South African Academic Participation, Mountain View, California, USA, October 23 - 23, 2017 |
en_US |
dc.identifier.isbn |
978-1-4503-5505-6 |
|
dc.identifier.uri |
https://dl.acm.org/citation.cfm?id=3132715&CFID=822088833&CFTOKEN=19372045
|
|
dc.identifier.uri |
Doi>10.1145/3132711.3132715
|
|
dc.identifier.uri |
http://hdl.handle.net/10204/9726
|
|
dc.description |
Copyright: 2017 The Author. Paper presented at SAWACMMM '17- Proceedings of the ACM Multimedia 2017 Workshop on South African Academic Participation, Mountain View, California, USA, October 23 - 23, 2017 |
en_US |
dc.description.abstract |
Machine learning models trained using images can be used to generate image overlays by investigating which image areas contribute the most towards model outputs. A common approach used to accomplish this relies on blanking image regions using a sliding window and evaluating the change in model output. Unfortunately,this can be computationally expensive,as it requires numerous model evaluations. This paper shows that a Gaussian process approximation to this blanking approach produces outputs of similar quality,despite requiring significantly fewer model evaluations. This process is illustrated using a user-driven saliency generation problem. Here,pairwise image interest comparisons are used to infer underlying image interest and a Gaussian process model trained to predict the interest value of an image using image features extracted by a convolutional neural network. Interest overlays are generated by evaluating model change at blanking image regions selected using the prediction uncertainty of a Gaussian process regressor. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
ACM Digital Library |
en_US |
dc.relation.ispartofseries |
Worklist;19785 |
|
dc.subject |
Gaussian processes |
en_US |
dc.subject |
Saliency generation |
en_US |
dc.title |
Leveraging Gaussian process approximations for rapid image overlay production |
en_US |
dc.type |
Conference Presentation |
en_US |
dc.identifier.apacitation |
Burke, M. G. (2017). Leveraging Gaussian process approximations for rapid image overlay production. ACM Digital Library. http://hdl.handle.net/10204/9726 |
en_ZA |
dc.identifier.chicagocitation |
Burke, Michael G. "Leveraging Gaussian process approximations for rapid image overlay production." (2017): http://hdl.handle.net/10204/9726 |
en_ZA |
dc.identifier.vancouvercitation |
Burke MG, Leveraging Gaussian process approximations for rapid image overlay production; ACM Digital Library; 2017. http://hdl.handle.net/10204/9726 . |
en_ZA |
dc.identifier.ris |
TY - Conference Presentation
AU - Burke, Michael G
AB - Machine learning models trained using images can be used to generate image overlays by investigating which image areas contribute the most towards model outputs. A common approach used to accomplish this relies on blanking image regions using a sliding window and evaluating the change in model output. Unfortunately,this can be computationally expensive,as it requires numerous model evaluations. This paper shows that a Gaussian process approximation to this blanking approach produces outputs of similar quality,despite requiring significantly fewer model evaluations. This process is illustrated using a user-driven saliency generation problem. Here,pairwise image interest comparisons are used to infer underlying image interest and a Gaussian process model trained to predict the interest value of an image using image features extracted by a convolutional neural network. Interest overlays are generated by evaluating model change at blanking image regions selected using the prediction uncertainty of a Gaussian process regressor.
DA - 2017-10
DB - ResearchSpace
DP - CSIR
KW - Gaussian processes
KW - Saliency generation
LK - https://researchspace.csir.co.za
PY - 2017
SM - 978-1-4503-5505-6
T1 - Leveraging Gaussian process approximations for rapid image overlay production
TI - Leveraging Gaussian process approximations for rapid image overlay production
UR - http://hdl.handle.net/10204/9726
ER -
|
en_ZA |