TY - GEN
T1 - Paying Attention to Style
T2 - 14th Asian Conference on Computer Vision 2018
AU - See, John
AU - Wong, Lai Kuan
AU - Kairanbay, Magzhan
N1 - Funding Information:
This work is supported in part by Shanghai ‘Belt and Road’ Young Scholar Exchange Grant (17510740100), Shanghai Jiao Tong University and Multimedia University.
Publisher Copyright:
© 2019, Springer Nature Switzerland AG.
Copyright:
Copyright 2019 Elsevier B.V., All rights reserved.
PY - 2019/6/19
Y1 - 2019/6/19
N2 - The notion of style in photographs is one that is highly subjective, and often difficult to characterize computationally. Recent advances in learning techniques for visual recognition have encouraged new possibilities for computing aesthetics and other related concepts in images. In this paper, we design an approach for recognizing styles in photographs by introducing adapted deep convolutional neural networks that are attentive towards strong neural activations. The proposed convolutional attentional units act as a filtering mechanism that conserves activations in convolutional blocks in order to contribute more meaningfully towards the visual style classes. State-of-the-art results were achieved on two large image style datasets, demonstrating the effectiveness of our method.
AB - The notion of style in photographs is one that is highly subjective, and often difficult to characterize computationally. Recent advances in learning techniques for visual recognition have encouraged new possibilities for computing aesthetics and other related concepts in images. In this paper, we design an approach for recognizing styles in photographs by introducing adapted deep convolutional neural networks that are attentive towards strong neural activations. The proposed convolutional attentional units act as a filtering mechanism that conserves activations in convolutional blocks in order to contribute more meaningfully towards the visual style classes. State-of-the-art results were achieved on two large image style datasets, demonstrating the effectiveness of our method.
UR - http://www.scopus.com/inward/record.url?scp=85068483538&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-21074-8_10
DO - 10.1007/978-3-030-21074-8_10
M3 - Conference contribution
AN - SCOPUS:85068483538
SN - 9783030210731
T3 - Lecture Notes in Computer Science
SP - 110
EP - 124
BT - Computer Vision. ACCV 2018
A2 - Carneiro, Gustavo
A2 - You, Shaodi
PB - Springer
Y2 - 2 December 2018 through 6 December 2018
ER -