recentpopularlog in

kintopp : images   237

« earlier  
Nicolas Gonthier
Je suis doctorant au sein de l’équipe IMAGES du LTCI de Télécom ParisTech. Mes intérêts de recherche sont l’apprentissage profond (Deep Learning) appliqué à l’histoire de l’art et aux données historiques en générale.
art  arthistory  france  images  history  analysis  deep 
28 days ago by kintopp
VISART IV
Paper submission is now open - please use this site to submit your paper! via Pocket
analysis  art  arthistory  cfp  conference  germany  images  ml  recognition 
28 days ago by kintopp
Computed Curation — Philipp Schmitt
Computed Curation is a photobook created by a computer. Taking the human editor out of the loop, it uses machine learning and computer vision tools to curate a series of photos from an archive of pictures. via Pocket
art  demos  images 
28 days ago by kintopp
Postdoc Job – Apply Now!
We’re hiring a postdoc in image processing and classification! Job Description DataLab is inviting applications for a full-time postdoctoral scholar in image processing and classification beginning Summer/Fall 2019. via Pocket
analysis  arthistory  deep  images  jobs 
28 days ago by kintopp
AI Portraits Ars
In the early 1500s Lorenzo Lotto and Giovan Battista Moroni began the psychological analysis through portraiture. From this moment, the focus on the sitter's identity becomes the leitmotif in the history of portrait. via Pocket
ai  art  demos  images 
29 days ago by kintopp
RDA und Sondermaterialien - rda-info - Deutsche Nationalbibliothek - Wiki
Bereits während des RDA-Implementierungsprojekts hat sich die deutschsprachige Community mit Sondermaterialien und deren Erschließung nach RDA beschäftigt und Kontakte zu weiteren Kultureinrichtungen wie Archiven und Museen aufgenommen. via Pocket
diglib  discussion  germany  images  standards  text 
5 weeks ago by kintopp
gepris.dfg.de
iART: Ein interaktives Analyse- und Retrieval-Tool zur Unterstützung von bildorientierten Forschungsprozessen
analysis  art  arthistory  germany  images  ml  munich  neural 
5 weeks ago by kintopp
Digital Mappa | an open-access DH platform
Digital Mappa (DM for short) is a freely available online environment for creating projects out of digital images and texts. via Pocket
annotation  images  infrastructure  interactive  text  tools 
8 weeks ago by kintopp
Content Based Image Recognition for Early Modern Images
Archv is a tool to search an imageset to find the best matches with your seed image. This page allows you to upload and compare an image of your choice with either the English Broadside Ballad Archive imageset or a curated image set from the British Library's Flickr. via Pocket
analysis  history  images  recognition  tools 
8 weeks ago by kintopp
Image and Ground Truth Resources - IMPACT Centre of Competence
The Impact Centre of Competence dataset contains more than half a million representative text-based images compiled by a number of major European libraries. via Pocket
datasets  digitization  images  ocr  text  ml 
may 2019 by kintopp
ArtMiner
Our goal in this paper is to discover near duplicate patterns in large collections of artworks. This is harder than standard instance mining due to differences in the artistic media (oil, pastel, drawing, etc), and imperfections inherent in the copying process. via Pocket
art  arthistory  iconography  images  recognition  search  deep 
march 2019 by kintopp
The photo archive as laboratory. Art history, photography, and materiality | Art Libraries Journal | Cambridge Core
Full text views reflects the number of PDF downloads, PDFs sent to Google Drive, Dropbox and Kindle and HTML full text views. via Pocket
archives  art  arthistory  images  italy  photography  preservation  research 
february 2019 by kintopp
Introduction: Re-viewing Digital Technologies and Art History /
A widespread opinion within the academic community is that art historians have been left behind by the digital turn in the humanities (see Greenhalgh 2004, Zorich 2012, and the in this issue). via Pocket
analysis  arthistory  images  paper  tools 
february 2019 by kintopp
About | Network Realism
Network Realism. Making knowledge from images in digital infrastructure is a research programme of the Virtual Knowledge Studio in Amsterdam.  The Virtual Knowledge Studio (VKS) is an institute of the Royal Netherlands Academy of Arts and Sciences. via Pocket
art  artist  culture  database  images  netherlands  networks 
february 2019 by kintopp
gepris.dfg.de
iArt: Ein interaktives Analyse- und Retrieval-Tool zur Unterstützung von bildorientierten Forschungsprozessen
analysis  art  arthistory  germany  images  munich  ml  deep 
february 2019 by kintopp
ARTigo – Social Image Tagging [Dataset and Images]
ARTigo is a platform that uses crowdsourcing to gather annotations (tags) on works of art (see http://www.artigo.org/). The dataset is compromised of 54.497 objects, which are associated with 18.492 artists (11.519 of which are either anonymous or unknown), 295. via Pocket
art  classification  crowdsourcing  datasets  germany  images  munich 
december 2018 by kintopp
Arkyves
A toolbox and a platform for researchers, working in the field of the arts, literature, and visual communication. It is a single access point for thematic searches across a wide variety of cultural heritage collections.
arthistory  database  iconography  images  resources  search  text 
december 2018 by kintopp
DSI - Database of Scientific Illustrators
Our online database, fully functioning since 2011, now already covers more than 12460 illustrators in natural history, medicine, technology and various sciences in more than 100 countries, active between c.1450 and 1950.
biography  history  images  people  resources  artist 
november 2018 by kintopp
GitHub - coneda/kor: ConedaKOR – store.manage.retrieve.
ConedaKOR allows you to store arbitrary documents and interconnect them with relationships. You can build huge semantic networks for an unlimited amount of domains. This integrates a sophisticated ontology management tool with an easy to use media database. via Pocket
database  germany  images  text  tools 
november 2018 by kintopp
[1611.05118] The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives
Authors:Mohit Iyyer, Varun Manjunatha, Anupam Guha, Yogarshi Vyas, Jordan Boyd-Graber, Hal Daumé III, Larry Davis v1), last revised 7 May 2017 (this version, v2)) Abstract: Visual narrative is often a combination of explicit information and judicious omissions, relying on the vie via Pocket
comics  datasets  images  learn  ml  narrative  paper  text 
november 2018 by kintopp
Archetype
Helping straight from the outset, Archetype’s batch uploading allows you to bring multiple digital images into your repository in a single pass, avoiding repetitive and error-prone manual uploads. via Pocket
annotation  classification  handwriting  images  manuscripts  recognition  text  tools  ml 
november 2018 by kintopp
DCGAN for Archaeologists – Electric Archaeology
Melvin Wevers has been using neural networks to understand visual patterns in the evolution of newspaper advertisements in Holland. He and his team developed a tool for visually searching the newspaper corpus. via Pocket
images  newspapers  recognition  deep 
november 2018 by kintopp
Weakly Supervised Object Detection in Artworks
We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed. This enables one to learn new classes on-the-fly from globally annotated databases, avoiding the tedious task of manually marking objects. We also introduce a new database, IconArt, on which we perform detection experiments on classes that could not be learned on photographs, such as Jesus Child or Saint Sebastian. 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.
art  iconography  images  paper  recognition  arthistory  ml 
november 2018 by kintopp
TensorFlow For Poets
TensorFlow is an open source library for numerical computation, specializing in machine learning applications. In this codelab, you will learn how to run TensorFlow on a single machine, and will train a simple classifier to classify images of flowers. via Pocket
classification  humanities  images  learn  python  ml 
november 2018 by kintopp
PUBLIC LECTURE: INGRID DAUBECHIES (​FRANCE) - YouTube
Mathematics can help Art Historians and Art Conservators in studying and understanding art works, their manufacture process and their state of conservation. The presentation will review several instances of such collaborations in the last decade or so. Some of them led (and are still leading) to int via Pocket
analysis  art  images  mathematics  talk 
august 2018 by kintopp
Ingrid Daubechies' Publication List
All "papers" (including various book chapters, a book, and a video) are listed in the chronological order of their creation. Boldface titles indicate original research results in refereed research journals or books. The other titles contain these same results in a different form (Ph.D. via Pocket
analysis  art  bibliography  mathematics  images 
august 2018 by kintopp
GitHub - sul-cidr/histonets: Histonets is an application to convert images of scanned maps into digital networks
Histonets is an application to convert images of scanned maps into digital networks. Histonets uses riiif for IIIF image api support. This requires imagemagick.
images  maps  tools  networks  iiif 
july 2018 by kintopp
VISART IV
Where Computer Vision Meets Art
4th Workshop on Computer Vision for Art Analysis
9th September 2018, Munich, Germany
analysis  art  arthistory  cfp  conference  deep  germany  images  recognition  ml 
july 2018 by kintopp
Visual Dialog
Visual Dialog is a novel task that requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Specifically, given an image, a dialog history, and a follow-up question about the image, the agent has to answer the question. via Pocket
analysis  dialog  images  language  ml 
july 2018 by kintopp
Mechanical Kubler: Visual Paths Through Time - Matthew Lincoln, PhD
Mechanical Kubler: Visual Paths Through Time I finally got the chance to push through a little idea about walking through visual time with a new Twitter bot I’m calling @MechaKubler. A pathway generated by Mechanical Kubler. via Pocket
art  images  recognition  analysis 
june 2018 by kintopp
One-shot object detection
This is more advanced than classification, which only tells you what the “main subject” of the image is — whereas object detection can find multiple objects, classify them, and locate where they are in the image. via Pocket
analysis  images  learn  recognition  classification  ml  deep 
june 2018 by kintopp
Sapping Attention: Meaning chains with word embeddings
Matthew Lincoln recently put up a Twitter bot that walks through chains of historical artwork by vector space similarity. https://twitter.com/matthewdlincoln/status/1003690836150792192. The idea comes from a Google project looking at paths that traverse similar paintings. via Pocket
analysis  demos  graphs  images  visualization  text 
june 2018 by kintopp
Wekinator | Software for real-time, interactive machine learning
The Wekinator is free, open source software originally created in 2009 by Rebecca Fiebrink. It allows anyone to use machine learning to build new musical instruments, gestural game controllers, computer vision or computer listening systems, and more. via Pocket
analysis  art  games  images  interactive  tools  ml 
june 2018 by kintopp
A gentle guide to deep learning object detection - PyImageSearch
I went through your previous blog post on deep learning object detection along with the followup tutorial for real-time deep learning object detection. Thanks for those. Ezekiel isn’t the only reader with those questions. via Pocket
howto  images  neural  python  recognition 
may 2018 by kintopp
GitHub - dhlab-epfl/dhSegment: Generic framework for historical document processing
dhSegment allows you to extract content (segment regions) from different type of documents. See some examples here. The corresponding paper is now available on arxiv. via Pocket
images  deep 
may 2018 by kintopp
arsexplorer.martinnadal.eu
A machine learning powered experiment that finds 'connections' between artworks from the Ars Electronica Archive.
art  demos  images  recognition  visualization  ml 
may 2018 by kintopp
Crowdsourcing Platform | Digirati
Originally implemented for the National Library of Wales as a set of modules for the Omeka S collection management system, our crowdsourcing platform lets you build your own projects from any source IIIF material, define the information you want your users to capture from that material, and save t via Pocket
crowdsourcing  iiif  images  omeka  uk 
may 2018 by kintopp
Workshop „Sehen in der digitalen Kunstgeschichte“, 8. Juni 2018 › Digitale Geistes- und Sozialwissenschaften
Die technischen Paradigmenwechsel in der Herstellung und Reproduktion von Bildern waren für die Kunstgeschichte immer unmittelbar wissenschaftsgeschichtlich bedeutend. Heute vollziehen sich die Bildbeschaffung, -speicherung, -rezeption und -präsentation in großen Teilen digital. via Pocket
art  arthistory  cognition  discussion  germany  images  methodology  workshop 
may 2018 by kintopp
Where Computer Vision Meets Art (Munich, 8-14 Sep 18) - ArtHist.net: Netzwerk für Kunstgeschichte / Archiv
Following the success of the previous editions of the Workshop on Computer VISion for ART Analysis held in 2012, 2014 and 2016, we present the VISART IV workshop, in conjunction with the 2018 European Conference on Computer Vision (ECCV 2018). via Pocket
analysis  art  arthistory  cfp  conference  germany  images  recognition 
may 2018 by kintopp
Visualizing Cultural Collections
Marian Dörk, Christopher Pietsch, Gabriel Credico Information Design Journal. 23:1, July 2017 Katrin Glinka, Christopher Pietsch, Marian Dörk DHQ: Digital Humanities Quarterly. 11:2 2017 via Pocket
culture  datasets  humanities  interactive  visualization  text  art  images 
may 2018 by kintopp
Program | AVinDH SIG
Please find below the preliminary schedule of the workshop including links to the full abstracts of the presenters. We will start by introducing basic notions about the challenges of computer vision. Also we will get a feeling of the simple, low level operations necessary for the next stage. via Pocket
analysis  art  arthistory  conference  images  ml  netherlands 
may 2018 by kintopp
Holding Out for a CV Hero: The Frick Computer Vision Symposium - Matthew Lincoln, PhD
16 Apr 2018What follows are some informal notes I jotted down after moderating a symposium at The Frick Collection’s Digital Art History Lab called “Searching Through Seeing: Optimizing Computer Vision Technology for the Arts” Everyone wants visual search, and a lot of people are doing it. via Pocket
analysis  arthistory  conference  images  ml  report  usa 
may 2018 by kintopp
CFP Art History + Data Science Conference
Data mining and knowledge discovery from large and complex data sets including visual images have advanced significantly in the past several years. via Pocket
analysis  art  arthistory  cfp  conference  germany  images  metadata  ml 
may 2018 by kintopp
What is dhSegment? | dhSegment
It is a generic approach for Historical Document Processing. It relies on a Convolutional Neural Network to do the heavy lifting of predicting pixelwise characteristics. Then simple image processing operations are provided to extract the components of interest (boxes, polygons, lines, masks, …) via Pocket
analysis  images  manuscripts  ocr  deep 
april 2018 by kintopp
Digital Mappa
Digital Mappa (DM for short) is a freely available online environment for creating projects out of digital images and texts. via Pocket
annotation  images  interactive  text  tools 
april 2018 by kintopp
GitHub - SeguinBe/DHWorkshop2017: Code for the hands-on of the Computer Vision and Digital Humanities Workshop DHCONF2017
This repository contains the code used for the hands-on session of the "Computer Vision for Digital Humanities" Workshop on the 7th of August during the DHCONF2017. via Pocket
art  demos  images  learn  workshop  deep 
april 2018 by kintopp
Linked Canvas
LINKED CANVAS is an easy-to-use tool designed for the cultural heritage community as well as schools and colleges to build interactive educational resources. LINKED CANVAS helps people to explore artworks and artefacts visually, conceptually and contextually.
annotation  art  images  interactive  interface  software  teach 
march 2018 by kintopp
Seebibyte Project
As the project progresses we will add full details on this website about our new software releases. In advance, here is a taster of previous software demonstrations. via Pocket
images  oxford  recognition  ml 
march 2018 by kintopp
Neural networks and deep learning
The human visual system is one of the wonders of the world. Consider the following sequence of handwritten digits: Most people effortlessly recognize those digits as 504192. That ease is deceptive. via Pocket
images  learn  recognition  deep 
march 2018 by kintopp
Nanne van Noord publications
Nanne van Noord. Postdoc, University of Amsterdam
Machine Learning Computer Vision Representation Learning
analysis  art  images  netherlands  ml  deep 
january 2018 by kintopp
Eric Postma | Artificial Intelligence Researcher | JADS & Tilburg University
Eric Postma (1961) is a professor in Artificial Intelligence at the Cognitive Science & AI department at Tilburg University and at the Jheronimus Academy of Data Science in ‘s-Hertogenbosch. He received his M.Sc. via Pocket
analysis  art  images  netherlands  research  ml  deep 
january 2018 by kintopp
Sudoku with Computer Vision, Machine Learning, and AR
A few weeks ago my company, Hatchlings, released Magic Sudoku for iOS11. It’s an app that solves sudoku puzzles using a combination of Computer Vision, Machine Learning, and Augmented Reality. You can try the app by downloading it from the App Store on your iPhone 6S (or newer) or iPad Pro. via Pocket
analysis  dev  images  ios  ml 
december 2017 by kintopp
Insight – Intelligent Neural Systems as InteGrated Heritage Tools
The recently started BELSPO-funded INSIGHT project (Intelligent Neural Systems as Integrated Heritage Tools) organizes a launch event on 9 November 2017. via Pocket
analysis  art  arthistory  belgium  culture  deep  images 
december 2017 by kintopp
Nanne
N van Noord, E Postma (2017) A learned representation of artist specific colourisation. ICCV Workshop on e-Heritage. Link N van Noord, E Postma (2017) Learning scale-variant and scale-invariant features for deep image classification. Pattern Recognition. Link via Pocket
analysis  art  culture  images  ml 
december 2017 by kintopp
Iconclass and AI – Iconclass Blog
Examples from a development project (2015 / 2016) at The National museum of Art, Architecture and Design in Oslo, section for Digital Collection Management. via Pocket
art  datasets  iconography  images  ml 
november 2017 by kintopp
3D Face Reconstruction
Aaron S. Jackson, Adrian Bulat, Vasileios Argyriou and Georgios Tzimiropoulos Computer Vision Laboratory, The University of Nottingham This is an online demo of our paper Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression. via Pocket
3d  analysis  demos  images  tools 
october 2017 by kintopp
An Excavation Of One Of The World’s Greatest Art Collections | FiveThirtyEight
About 4,000 years ago, an Egyptian senior government official named Meketre rode up the Nile, his dozen oarsmen straining against the prevailing northerly winds. Meketre was a kind of data collector, tasked with accounting the comings and goings of royal goods. via Pocket
analysis  art  datasets  images  metadata  museums 
august 2017 by kintopp
[WMP17] Convert Pixel Image into Vector Graphics - Online Technical Discussion Groups—Wolfram Community
As part of my Wolfram Mentorship Program, I chose to work on this interesting and challenging project that combines image processing, artificial intelligence, graph theory and Wolfram Language (who can think of better combination?!). via Pocket
images  tools  vectors 
august 2017 by kintopp
Computed Curation — Office of Philipp Schmitt
Computed Curation is a photobook created by a computer. Taking the human editor out of the loop, it uses machine learning and computer vision tools to curate a series of photos from an archive of pictures. via Pocket
art  deep  demos  images 
july 2017 by kintopp
GitHub - phillipi/pix2pix: Image-to-image translation with conditional adversarial nets
Image-to-Image Translation with Conditional Adversarial Networks Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, Alexei A. Efros In arxiv, 2016. On some tasks, decent results can be obtained fairly quickly and on small datasets. via Pocket
images 
june 2017 by kintopp
Mapping Paintings (provenance records)
Mapping Paintings Explore the provenance records of hundreds of paintings and visualize your own research across time and space Explore Data Start Project Artists Paintings Owners via Pocket
arthistory  images  search  provenance 
june 2017 by kintopp
Project Principal Components - The National Museum
Two of the results in the project are described in more detail below. As a starting point in attempting to train an algorithm to analyze our images, we used a neural network trained on ImageNet, written in Caffe [1], developed by Autonomous Perception Research Lab at Berkeley [2]. via Pocket
art  images  ml  recognition  search 
june 2017 by kintopp
Coding Da Vinci
Der Kulturhackathon Coding da Vinci Berlin ist zurück und geht 2017 ins vierte Jahr! Am 21. und 22. Oktober starten wir in Berlin mit unserem Kick-Off den 4. Kulturhackthon. via Pocket
art  datasets  demos  dev  images 
may 2017 by kintopp
Image Analysis for Archival Discovery
Image Analysis for Archival Discovery (Aida) responds to two issues within the digital humanities and digital library communities: First, that we leverage little of the information potential of the millions of images that we are creating as we digitize the cultural record. via Pocket
analysis  images  ocr  tools 
may 2017 by kintopp
Call for Abstracts | AVinDH SIG
Although the majority of Digital Humanities scholars still focus on textual analysis, we see an increasing number of studies using digitised visual sources and taking the first steps in the field of ‘Visual Big Data’ (Ordelman et al, 2014). via Pocket
canada  cfp  conference  deep  images  ml 
april 2017 by kintopp
Font Map · An AI Experiment by IDEO
Using artificial intelligence to surface new relationships across fonts. This interactive map of more than 750 fonts has been organized using machine learning. via Pocket
demos  fonts  images  typography  ml 
april 2017 by kintopp
Creating a Modern OCR Pipeline Using Computer Vision and Deep Learning | Dropbox Tech Blog
In this post we will take you behind the scenes on how we built a state-of-the-art Optical Character Recognition (OCR) pipeline for our mobile document scanner. via Pocket
analysis  deep  images  ocr  report  ml 
april 2017 by kintopp
GitHub - sotojuan/get-met-url: Get a Met Museum image URL by Object ID
The Met recently open sourced a huge CSV file of their collection. The problem is that it doesn't include the direct link to the image of a specific artwork. This module solves that problem. Return a Promise of either the direct image link or an error. via Pocket
art  datasets  images  metadata  museums 
april 2017 by kintopp
Deep Learning Applied to Computer Vision - YouTube
For the latest information, please visit:http://ift.tt/2ltwqoY: Mattias OdisioWolfram developers and colleagues discussed the latest in innovative technologies for cloud computing, interactive deployment, mobile devices, and more. via Pocket
deep  images  talk  video  wolfram 
april 2017 by kintopp
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Jun-Yan Zhu* Taesung Park* Phillip Isola Alexei A. Efros UC Berkeley [Paper] [GitHub] Abstract Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. via Pocket
art  images  paper  deep 
april 2017 by kintopp
Amazon Rekognition – Deep learning-based image analysis
Amazon Rekognition is a service that makes it easy to add image analysis to your applications. With Rekognition, you can detect objects, scenes, and faces in images. You can also search and compare faces. via Pocket
analysis  api  images  recognition 
april 2017 by kintopp
Vision API - Image Content Analysis  |  Google Cloud Platform
Google Cloud Vision API enables developers to understand the content of an image by encapsulating powerful machine learning models in an easy to use REST API. It quickly classifies images into thousands of categories (e.g. via Pocket
api  images  recognition 
april 2017 by kintopp
Tropy
Take control of your research photos with Tropy, a tool that shortens the path from finding archival sources to writing about them. Spend more time using your research photos, and less time searching for them. Organize your photos so they’re easy to find, easy to edit, and easy to analyze. via Pocket
art  arthistory  database  images  research  search  tools 
april 2017 by kintopp
« earlier      
per page:    204080120160

Copy this bookmark:





to read