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

Cai, Hongping; Wu, Qi; Corradi, Tadeo; Hall, Peter M.

doi:10.48550/arxiv.1505.00110

Cited by 11 publications

(14 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We perform experiments on a large variety of object detection datasets including the PASCAL VOC 2007 dataset [9], the PASCAL VOC 2012 dataset, the People-Art dataset [3], and the COCO dataset [23].…”

Section: Methodsmentioning

confidence: 99%

Point Linking Network for Object Detection

Wang¹,

Chen²,

Huang³

et al. 2017

Preprint

View full text Add to dashboard Cite

Object detection is a core problem in computer vision. With the development of deep ConvNets, the performance of object detectors has been dramatically improved. The deep ConvNets based object detectors mainly focus on regressing the coordinates of bounding box, e.g., Faster-R-CNN, YOLO and SSD. Different from these methods that considering bounding box as a whole, we propose a novel object bounding box representation using points and links and implemented using deep ConvNets, termed as Point Linking Network (PLN). Specifically, we regress the corner/center points of bounding-box and their links using a fully convolutional network; then we map the corner points and their links back to multiple bounding boxes; finally an object detection result is obtained by fusing the multiple bounding boxes. PLN is naturally robust to object occlusion and flexible to object scale variation and aspect ratio variation. In the experiments, PLN with the Inception-v2 model achieves state-of-the-art single-model and singlescale results on the PASCAL VOC 2007, the PASCAL VOC 2012 and the COCO detection benchmarks without bells and whistles. The source code will be released.

show abstract

Section: Methodsmentioning

confidence: 99%

Point Linking Network for Object Detection

Wang¹,

Chen²,

Huang³

et al. 2017

Preprint

View full text Add to dashboard Cite

show abstract

“…The authors developed a CNN-based system that can learn object classifiers from Google images and use these classifiers to find previously unseen objects in a large painting database. Other works, focusing on object recognition and detection in artworks, have also been reported [20,21,22,23,24,25]. The main issue to be addressed in this kind of research is the so-called cross-depiction problem, that is the problem of recognizing visual objects regardless of whether they are photographed, painted, drawn, etc.…”

Section: Related Workmentioning

confidence: 99%

Deep Convolutional Embedding for Digitized Painting Clustering

Castellano

Vessio

2021

2020 25th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

Clustering artworks is difficult because of several reasons. On one hand, recognizing meaningful patterns in accordance with domain knowledge and visual perception is extremely hard. On the other hand, the application of traditional clustering and feature reduction techniques to the highly dimensional pixel space can be ineffective. To address these issues, we propose a deep convolutional embedding model for clustering digital paintings, in which the task of mapping the input raw data to an abstract, latent space is optimized jointly with the task of finding a set of cluster centroids in this latent feature space. Quantitative and qualitative experimental results show the effectiveness of the proposed method. The model is also able to outperform other state-of-the-art deep clustering approaches to the same problem. The proposed method may be beneficial to several art-related tasks, particularly visual link retrieval and historical knowledge discovery in painting datasets.

show abstract

“…Several works focus on object recognition and detection in artworks [19,20,21,22,23,24]. A first attempt to use deep neural networks for object recognition in visual arts is presented in [5].…”

Section: Related Workmentioning

confidence: 99%

Towards a Tool for Visual Link Retrieval and Knowledge Discovery in Painting Datasets

Castellano

Vessio

2020

Digital Libraries: The Era of Big Data and Data Science

View full text Add to dashboard Cite

Visual arts have invaluable importance for the cultural, historic and economic growth of our societies. One of the building blocks of most analysis in visual arts is to find similarities among paintings of different artists and painting schools. To help art historians better understand visual arts, the present paper presents a framework for visual link retrieval and knowledge discovery in digital painting datasets. The proposed framework is based on a deep convolutional neural network to perform feature extraction and on a fully unsupervised nearest neighbor approach to retrieve visual links among digitized paintings. The fully unsupervised strategy makes attractive the proposed method especially in those cases where metadata are either scarce or unavailable or difficult to collect. In addition, the proposed framework includes a graph analysis that makes it possible to study influences among artists, thus providing historical knowledge discovery.

show abstract

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

Cited by 11 publications

References 57 publications

Point Linking Network for Object Detection

Point Linking Network for Object Detection

Deep Convolutional Embedding for Digitized Painting Clustering

Towards a Tool for Visual Link Retrieval and Knowledge Discovery in Painting Datasets

Contact Info

Product

Resources

About