2016
DOI: 10.1007/978-3-319-46604-0_57
|View full text |Cite
|
Sign up to set email alerts
|

Detecting People in Artwork with CNNs

Abstract: CNNs have massively improved performance in object detection in photographs. However research into object detection in artwork remains limited. We show state-of-the-art performance on a challenging dataset, People-Art, which contains people from photos, cartoons and 41 different artwork movements. We achieve this high performance by fine-tuning a CNN for this task, thus also demonstrating that training CNNs on photos results in overfitting for photos: only the first three or four layers transfer from photos to… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
76
0

Year Published

2018
2018
2021
2021

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 68 publications
(76 citation statements)
references
References 50 publications
0
76
0
Order By: Relevance
“…In Table 3, one can see that our approach MI-max yields detection results that are very close to the fully supervised results from [52], despite a much lighter training procedure. In particular, as already explained, our procedure can be trained directly on large, globally annotated database, for which manually entering instance-level annotations is tedious and time-costly.…”
Section: Experiments 1 : Watercolor2kmentioning
confidence: 62%
See 3 more Smart Citations
“…In Table 3, one can see that our approach MI-max yields detection results that are very close to the fully supervised results from [52], despite a much lighter training procedure. In particular, as already explained, our procedure can be trained directly on large, globally annotated database, for which manually entering instance-level annotations is tedious and time-costly.…”
Section: Experiments 1 : Watercolor2kmentioning
confidence: 62%
“…In [41], it is shown that the YOLO network trained on natural images can, to some extend, be used for people detection in cubism. In [52], it is proposed to perform people detection in a wide variety of artworks (through a newly introduced database) by fine-tuning a network in a supervised way. People can be detected with high accuracy even though the database has very large stylistic variations and includes paintings that strongly differs from photographs in the way they represent people.…”
Section: Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…For evaluating the cross-domain object detection method, the existing datasets for detecting common objects in various domains seem to have limitations. People-Art [37] is used only for single-class detection in an artwork. Photo-Art [39] assumes only one instance per image, which is unrealistic.…”
Section: Cross-domain Object Detectionmentioning
confidence: 99%