Analyzing Gesture in Digital Art History

Impett, Leonardo

doi:10.4324/9780429505188-33

Cited by 3 publications

(9 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noticing that this loss is a non-Euclidean distance, since we are dealing with circular quantities, following the line already adopted in [17].…”

Section: Second Methodsmentioning

confidence: 99%

“…Coming to the third question, the author of [17] made important theoretical and contextual considerations. The first was that the relative positions of the human limbs are a quantitative parameter, and are therefore useful in the digital humanities, even though analyses based on this criterion are rare in the exclusive historical art domain.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

“…Looking for this statistical correspondence between Pathos and Formel, they applied both a K-Means and an Agglomerative Hierarchical Clustering with a non-Euclidean distance on more than 1600 annotated images. The same author of [17], taking up [23], investigated the temporality in gospel stories, focusing on the Madonna and Gabriel poses in the biblical episode of the Annunciation. In this work, the poses moved not through art-historical time, but across narrative time.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

“…However, how do we measure the similarity between two poses? Taking up the difference between the typology of measurable angles raised in [17], two strategies to fulfill this task are presented. First, a key advantage of our proposed methods is that no pre-processing is needed for the poses to be compared; they can have different scales and orientations.…”

Section: Pose Comparisonmentioning

confidence: 99%

“…Having defined a quantitative way to measure the similarity or distance between different poses, we set up a modified version of the K-Medians algorithm to cluster the selected poses and to compute the centroids for each cluster (code available at the following link: https://github.com/L9L4/POSE-ID-on, accessed on 1 February 2021), thus preserving the invariance to shift, rotation, and scale. However, the clustering approach establishes a powerful and innovative solution to the pose retrieval task (having been suggested only by [1,17] in the available literature), both in the formulation and the possibility to generate a limited number of centroids, which would significantly speed up a pose retrieval system.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

POSE-ID-on—A Novel Framework for Artwork Pose Clustering

Marsocci

Lastilla

2021

IJGI

View full text Add to dashboard Cite

In this work, we focus our attention on the similarity among works of art based on human poses and the actions they represent, moving from the concept of Pathosformel in Aby Warburg. This form of similarity is investigated by performing a pose clustering of the human poses, which are modeled as 2D skeletons and are defined as sets of 14 points connected by limbs. To build a dataset of properly annotated artwork images (that is, including the 2D skeletons of the human figures represented), we relied on one of the most popular, recent, and accurate deep learning frameworks for pose tracking of human figures, namely OpenPose. To measure the similarity between human poses, two alternative distance functions are proposed. Moreover, we developed a modified version of the K-Medians algorithm to cluster similar poses and to find a limited number of poses that are representative of the whole dataset. The proposed approach was also compared to two popular clustering strategies, that is, K-Means and the Nearest Point Algorithm, showing higher robustness to outliers. Finally, we assessed the validity of the proposed framework, which we named POSE-ID-on, in both a qualitative and in a quantitative way by simulating a supervised setting, since we lacked a proper reference for comparison.

show abstract

“…It is worth noticing that this loss is a non-Euclidean distance, since we are dealing with circular quantities, following the line already adopted in [17].…”

Section: Second Methodsmentioning

confidence: 99%

Section: Theoretical Backgroundmentioning

confidence: 99%

Section: Theoretical Backgroundmentioning

confidence: 99%

Section: Pose Comparisonmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

POSE-ID-on—A Novel Framework for Artwork Pose Clustering

Marsocci

Lastilla

2021

IJGI

View full text Add to dashboard Cite

show abstract

The Role of Culture in the Intelligence of AI

Bunz

2023

Edition Museum

View full text Add to dashboard Cite

Artificial intelligence has received a new boost from the recent hype about large lan- guage models. However, to avoid misconceptions, it is better to speak of 'machine intelligence'. In addition to reflecting on current processes, the cultural sector can benefit from very specific machine learning approaches to transfer literary me- thods such as 'distant readings' and find new connections in cultural data. In light of resource and exploitation problems, what is needed is a 'critical technical practice' (Agre) that brings together various actors, productively engages with AI's own logics and error cultures, and uses its potential to cope with the flood of information. Artificial intelligence has received a new boost from the recent hype about large lan- guage models. However, to avoid misconceptions, it is better to speak of 'machi- ne intelligence'. In addition to reflecting on current processes, the cultural sector can benefit from very specific machine learning approaches to transfer literary me- thods such as 'distant readings' and find new connections in cultural data. In light of resource and exploitation problems, what is needed is a 'critical technical practice' (Agre) that brings together various actors, productively engages with AI's own logics and error cultures, and uses its potential to cope with the flood of information.

show abstract

A Computational Approach to Hand Pose Recognition in Early Modern Paintings

2023

Self Cite

View full text Add to dashboard Cite

Hands represent an important aspect of pictorial narration but have rarely been addressed as an object of study in art history and digital humanities. Although hand gestures play a significant role in conveying emotions, narratives, and cultural symbolism in the context of visual art, a comprehensive terminology for the classification of depicted hand poses is still lacking. In this article, we present the process of creating a new annotated dataset of pictorial hand poses. The dataset is based on a collection of European early modern paintings, from which hands are extracted using human pose estimation (HPE) methods. The hand images are then manually annotated based on art historical categorization schemes. From this categorization, we introduce a new classification task and perform a series of experiments using different types of features, including our newly introduced 2D hand keypoint features, as well as existing neural network-based features. This classification task represents a new and complex challenge due to the subtle and contextually dependent differences between depicted hands. The presented computational approach to hand pose recognition in paintings represents an initial attempt to tackle this challenge, which could potentially advance the use of HPE methods on paintings, as well as foster new research on the understanding of hand gestures in art.

show abstract

Analyzing Gesture in Digital Art History

Cited by 3 publications

References 0 publications

POSE-ID-on—A Novel Framework for Artwork Pose Clustering

POSE-ID-on—A Novel Framework for Artwork Pose Clustering

The Role of Culture in the Intelligence of AI

A Computational Approach to Hand Pose Recognition in Early Modern Paintings

Contact Info

Product

Resources

About