Filters








308 Hits in 2.7 sec

Weakly Supervised Object Detection in Artworks [article]

Nicolas Gonthier, Yann Gousseau, Said Ladjal, Olivier Bonfait
2018 arXiv   pre-print
We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed.  ...  To the best of our knowledge, these are the first experiments dealing with the automatic (and in our case weakly supervised) detection of iconographic elements in paintings.  ...  Weakly supervised detection by transfer learning In this section, we propose our approach to the weakly supervised detection of visual category in paintings.  ... 
arXiv:1810.02569v1 fatcat:pmxnyrxwzfbkhmp36dkgzdgjry

Weakly Supervised Object Detection in Artworks [chapter]

Nicolas Gonthier, Yann Gousseau, Said Ladjal, Olivier Bonfait
2019 Landolt-Börnstein - Group III Condensed Matter  
We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed.  ...  To the best of our knowledge, these are the first experiments dealing with the automatic (and in our case weakly supervised) detection of iconographic elements in paintings.  ...  Weakly supervised detection by transfer learning In this section, we propose our approach to the weakly supervised detection of visual category in paintings.  ... 
doi:10.1007/978-3-030-11012-3_53 fatcat:xyf6rztlcjg3vbgi5vfeys3noq

Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts [article]

Nicolas Gonthier and Saïd Ladjal and Yann Gousseau
2020 arXiv   pre-print
Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years.  ...  The object detection problem (recognize and locate an object) in artworks has been less studied.  ...  None of these authors use the approach for weakly supervised object detection.  ... 
arXiv:2008.01178v4 fatcat:eae2lctf6fb3jdm6maprmstvzy

Comparing CAM Algorithms for the Identification of Salient Image Features in Iconography Artwork Analysis

Nicolò Oreste Pinciroli Pinciroli Vago, Federico Milani, Piero Fraternali, Ricardo da Silva Torres
2021 Journal of Imaging  
images can be exploited to support the much harder task of object detection.  ...  Iconography studies the visual content of artworks by considering the themes portrayed in them and their representation.  ...  supervised object detectors in artwork images.  ... 
doi:10.3390/jimaging7070106 fatcat:5ahrrnd2h5bhhdd6wtopwk3cse

Deep learning approaches to pattern extraction and recognition in paintings and drawings: an overview

Giovanna Castellano, Gennaro Vessio
2021 Neural computing & applications (Print)  
AbstractThis paper provides an overview of some of the most relevant deep learning approaches to pattern extraction and recognition in visual arts, particularly painting and drawing.  ...  Recent advances in deep learning and computer vision, coupled with the growing availability of large digitized visual art collections, have opened new opportunities for computer science researchers to  ...  To overcome this problem, the authors proposed a ''weakly supervised'' approach that can learn to detect objects based only on image-level annotations.  ... 
doi:10.1007/s00521-021-05893-z fatcat:elqzw3hzbzgodotie6ndih537u

Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation

Naoto Inoue, Ryosuke Furuta, Toshihiko Yamasaki, Kiyoharu Aizawa
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
In this paper, we present a framework for a novel task, cross-domain weakly supervised object detection, which addresses this question.  ...  Can we detect common objects in a variety of image domains without instance-level annotations?  ...  Furuta is supported by the Grants-in-Aid for Scientific Research (16J07267) from JSPS.  ... 
doi:10.1109/cvpr.2018.00525 dblp:conf/cvpr/InoueFYA18 fatcat:g66l47zivbgl7li3p373pe5jxa

Machine Learning for Cultural Heritage: A Survey

Marco Fiorucci, Marina Khoroshiltseva, Massimiliano Pontil, Arianna Traviglia, Alessio Del Bue, Stuart James
2020 Pattern Recognition Letters  
We analyse the dominant divides within ML, Supervised, Semi-supervised and Unsupervised, and reflect on a variety of algorithms that have been extensively used.  ...  From such an analysis, we give a critical look at the use of ML in CH and consider why CH has only limited adoption of ML.  ...  Supplementary material Supplementary material associated with this article can be found, in the online version, at doi: 10.1016/j.patrec.2020.02.017 .  ... 
doi:10.1016/j.patrec.2020.02.017 fatcat:smayxo3wcbfmhm33c6q4rnmr6i

Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation [article]

Naoto Inoue, Ryosuke Furuta, Toshihiko Yamasaki, Kiyoharu Aizawa
2018 arXiv   pre-print
In this paper, we present a framework for a novel task, cross-domain weakly supervised object detection, which addresses this question.  ...  Can we detect common objects in a variety of image domains without instance-level annotations?  ...  Furuta is supported by the Grants-in-Aid for Scientific Research (16J07267) from JSPS.  ... 
arXiv:1803.11365v1 fatcat:54p7yqkf6fcrhdqnadcwn2gcma

Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image Translation [article]

Matteo Tomei, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
2019 arXiv   pre-print
Our architecture can generate natural images by retrieving and learning details from real photos through a similarity matching strategy which leverages a weakly-supervised semantic understanding of the  ...  Experimental results show that the proposed technique leads to increased realism and to a reduction in domain shift, which improves the performance of pre-trained architectures for classification, detection  ...  [13] : in this approach, a network is trained to predict semantic masks from a large set of categories, by leveraging the partial supervision given by detections.  ... 
arXiv:1811.10666v3 fatcat:fmhdvwafezfzxgctskprte33ke

Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-To-Image Translation

Matteo Tomei, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Our architecture can generate natural images by retrieving and learning details from real photos through a similarity matching strategy which leverages a weakly-supervised semantic understanding of the  ...  Experimental results show that the proposed technique leads to increased realism and to a reduction in domain shift, which improves the performance of pre-trained architectures for classification, detection  ...  [13] : in this approach, a network is trained to predict semantic masks from a large set of categories, by leveraging the partial supervision given by detections.  ... 
doi:10.1109/cvpr.2019.00600 dblp:conf/cvpr/TomeiCBC19 fatcat:kyx5vakxfrcmtbbxlto6marbqa

Linked Open Images: Visual similarity for the Semantic Web

Lukas Klic, Mehwish Alam, Victor de Boer, Eero Hyvönen, Albert Meroño Peñuela, Harald Sack
2022 Semantic Web Journal  
, style detection, gesture analysis, among others.  ...  The field of Digital Art History stands to benefit a great deal from computer vision, as numerous projects have already made good progress in tackling issues of visual similarity, artwork classification  ...  Bonfait, Weakly supervised object detection in artworks, in: Computer Vision – ECCV 2018 TE Workshops, L. Leal-Taixé and S.  ... 
doi:10.3233/sw-212893 fatcat:fx3c3wffrjf7xlmi4rjl3bwk2e

The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs [article]

Hongping Cai and Qi Wu and Tadeo Corradi and Peter Hall
2015 arXiv   pre-print
Emulating the remarkable human ability to recognise objects in an astonishingly wide variety of depictive forms is likely to advance both the foundations and the applications of Computer Vision.  ...  Rather, we find the methods that have strong models of spatial relations between parts tend to be more robust and therefore conclude that such information is important in modelling object classes regardless  ...  Some work is very specific -Crowley and Zisserman take a weakly supervised approach, using a DPM to learn figurative art on Greek vases [13] .  ... 
arXiv:1505.00110v1 fatcat:clku4qa7aje6hoi2pwutqaojj4

Cross-depiction problem: Recognition and synthesis of photographs and artwork

Peter Hall, Hongping Cai, Qi Wu, Tadeo Corradi
2015 Computational Visual Media  
Emulating the remarkable human ability to recognise and depict objects in an astonishingly wide variety of depictive forms is likely to advance both the foundations and the applications of computer vision  ...  In this paper we motivate the cross-depiction problem, explain why it is difficult, and discuss some current approaches.  ...  and detection (an object of class X is at this place in this image).  ... 
doi:10.1007/s41095-015-0017-1 fatcat:i7injiewqfdtdhbmgve3kd6imu

A deep learning approach to clustering visual arts [article]

Giovanna Castellano, Gennaro Vessio
2021 arXiv   pre-print
Clustering artworks is difficult for several reasons. On the one hand, recognizing meaningful patterns based on domain knowledge and visual perception is extremely hard.  ...  DELIUS can be useful for several tasks related to art analysis, in particular visual link retrieval and historical knowledge discovery in painting datasets.  ...  (Cai et al, 2015a; Westlake et al, 2016) , also focusing on weakly supervised approaches (Gonthier et al, 2018) or near duplicate detection tasks (Shen et al, 2019) .  ... 
arXiv:2106.06234v1 fatcat:lhtgmr2i4rgknnjo7muw4hqx24

A Saliency-Based Patch Sampling Approach for Deep Artistic Media Recognition

Heekyung Yang, Kyungha Min
2021 Electronics  
We present a saliency-based patch sampling strategy for recognizing artistic media from artwork images using a deep media recognition model, which is composed of several deep convolutional neural network-based  ...  supervised, weakly supervised and adversarial methods.  ...  We select robust background detection schemes that emphasize objects in stronger saliency values. Among the various robust background detection schemes [29] [30] [31] [32] , we select Zhu et al.'  ... 
doi:10.3390/electronics10091053 fatcat:pmy4iuhfbjhrvfwlxlq346qmve
« Previous Showing results 1 — 15 out of 308 results