Object-Specific Style Transfer Based on Feature Map Selection Using CNNs
| Title | Object-Specific Style Transfer Based on Feature Map Selection Using CNNs |
| Publication Type | Conference Paper |
| Year of Publication | 2017 |
| Authors | Shinya, A., Tung, N. D., Harada, T., Thawonmas, R. |
| Conference Name | 2017 Nicograph International (NicoInt) |
| Date Published | June 2017 |
| Publisher | IEEE |
| ISBN Number | 978-1-5090-5332-2 |
| Keywords | CNN, Computer vision, Conferences, convolutional neural networks, Dogs, feature map selection, feature selection, image content, image processing, image style, machine learning, Metrics, neural nets, Neural networks, neural style transfer, object-specific style transfer, Pattern recognition, pubcrawl, resilience, Resiliency, Scalability, style transfer, visualization |
| Abstract | We propose a method for transferring an arbitrary style to only a specific object in an image. Style transfer is the process of combining the content of an image and the style of another image into a new image. Our results show that the proposed method can realize style transfer to specific object. |
| URL | https://ieeexplore.ieee.org/document/8047407 |
| DOI | 10.1109/NICOInt.2017.39 |
| Citation Key | shinya_object-specific_2017 |
- Metrics
- visualization
- style transfer
- Scalability
- Resiliency
- resilience
- pubcrawl
- Pattern recognition
- object-specific style transfer
- neural style transfer
- Neural networks
- neural nets
- CNN
- machine learning
- image style
- Image Processing
- image content
- Feature Selection
- feature map selection
- Dogs
- convolutional neural networks
- Conferences
- computer vision