Paying Attention to Style: Recognizing Photo Styles with Convolutional Attentional Units

John See*, Lai Kuan Wong, Magzhan Kairanbay

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationComputer Vision. ACCV 2018
EditorsGustavo Carneiro, Shaodi You
PublisherSpringer
Pages110-124
Number of pages15
ISBN (Electronic)9783030210748
ISBN (Print)9783030210731
DOIs
Publication statusPublished - 19 Jun 2019
Event14th Asian Conference on Computer Vision 2018 - Perth, Australia
Duration: 2 Dec 20186 Dec 2018

Publication series

NameLecture Notes in Computer Science
Volume11367
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference14th Asian Conference on Computer Vision 2018
Abbreviated titleACCV 2018
Country/TerritoryAustralia
CityPerth
Period2/12/186/12/18

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Paying Attention to Style: Recognizing Photo Styles with Convolutional Attentional Units'. Together they form a unique fingerprint.

Cite this