Humanist Discussion Group, Vol. 36, No. 57.
Department of Digital Humanities, University of Cologne
Hosted by DH-Cologne
www.dhhumanist.org
Submit to: humanist@dhhumanist.org
[1] From: Ben Brumfield <benwbrum@gmail.com>
Subject: event: Conversations on Quality in Crowdsourced Transcription (39)
[2] From: James Cummings <James.Cummings@newcastle.ac.uk>
Subject: ATNU Virtual Speaker -- Elisa Beshero-Bondar -- 2022-06-14 at 4pm BST "It's alive! The Frankenstein Variorum and adventures in machine-assisted collation" (73)
[3] From: Stuart James <stuart.james@iit.it>
Subject: [CFP] ECCV 2022 workshop: VISART VI "Where Computer Vision Meets Art" (103)
--[1]------------------------------------------------------------------------
Date: 2022-06-09 18:43:12+00:00
From: Ben Brumfield <benwbrum@gmail.com>
Subject: event: Conversations on Quality in Crowdsourced Transcription
Dear Colleagues,
We would like to invite you to the following webinar:
On Improving Error & Quality in Crowdsourced Transcription
Join Ben Brumfield (FromThePage) and Austin Mast (Florida State
University/iDigBio) for a discussion of error and quality in crowdsourced
transcription projects from digital humanities and citizen science. We’ll
start by defining the dimensions of quality: accuracy, fidelity, and
usability, then look at an analysis of causes of transcription errors
informed by textual criticism.
Some projects engage multiple people transcribing an item independently.
Others support collaboration between users editing a given piece of text.
Various methods can be used to assess the results of these very different
options. We’ll compare multi-track (i.e. many transcriptions of the same
bits) and arbitration approaches against single-track (i.e. collaborative
transcription) with statistical sampling and review. Next, we’ll discuss
how to quantify quality and how early intervention can improve transcriber
skill. Finally, we look forward to sharing possible next steps and an open
discussion with our audience.
The webinar is on June 16, 2022 at 12:00 PM EDT, 11:00 AM CDT, 9:00 AM PDT,
and 1700 BST/1800 CEST. Signing up will send you an invitation with
connection details and a follow up email with the recording.
Sign up link:
https://content.fromthepage.com/on-improving-error-quality-in-crowdsourced-
transcription/
Best regards,
Ben
--
Ben W. Brumfield
Partner. Brumfield Labs LLC
Creators of FromThePage <https://fromthepage.com/>
--[2]------------------------------------------------------------------------
Date: 2022-06-08 15:50:56+00:00
From: James Cummings <James.Cummings@newcastle.ac.uk>
Subject: ATNU Virtual Speaker -- Elisa Beshero-Bondar -- 2022-06-14 at 4pm BST "It's alive! The Frankenstein Variorum and adventures in machine-assisted collation"
ATNU Virtual Speaker Series - Elisa Beshero-Bondar - 2022-06-14
https://research.ncl.ac.uk/atnu/news/atnuvirtualspeakerseries-elisabeshero-
bondar-2022-06-14.html
Our next speaker in the ATNU Virtual Speaker Series is Elisa Beshero-
Bondar <https://behrend.psu.edu/person/elisa-beshero-bondar-phd> who will talk to
us about the delights and provocations of an experiment in collating five
versions of Mary Shelley’s Frankenstein to prepare a digital variorum edition.
She is Professor of Digital Humanities and Program Chair of Digital Media, Arts,
and Technology at Penn State Erie, The Behrend College.
Join us on Tuesday 14 June 2022 via Zoom at 4pm UK time (BST). (We will send the
zoom link to all registered attendees
shortly before the event.)
Register for this event!<https://forms.ncl.ac.uk/view.php?id=14671574>
"It's alive! The Frankenstein Variorum and adventures in machine-assisted
collation"
Dr Elisa Beshero-Bondar
Tuesday 14 June 2022
4pm (BST)
REGISTER HERE<https://forms.ncl.ac.uk/view.php?id=14671574>
Abstract: We have been working on a challenging experiment with automated text-
collation to compare and visualize five distinctly different versions of the
novel Frankenstein, by Mary Wollstonecraft Godwin Shelley. Working with
computer-aided collation involves much testing and refining as the process
inevitably does not run smoothly. In our case, the collation process is
complicated by our comparison of very differently-encoded digital editions: the
Shelley-Godwin Archive's diplomatic TEI edition (encoding page-by-page surfaces
and zones as well as marginal insertions and deletions), together with simpler
encodings of four other editions mainly representing print publications and
their semantic structures (encoded in chapters and letters). I will discuss how
we organized the collation process by “chunking” the documents along parallel
structures marked in each text, and also how we involve the TEI markup of
paragraph and chapter boundaries as well as deletions and insertions in the
process to make the markup part of the collated edition.
Most importantly, I want to discuss the necessity of good, clear documentation
to guide our testing of collation methods and analysis of what can go wrong and
how to resolve it. We are now working to determine the viability of Python-
assisted delivery of "flattened" markup to collation software as a stream of
text, since we have been struggling to contend with spacing errors in the output
collation. My students and I have been testing whether this process is
correctable (or worth correcting) and alternatively whether XSLT is the better
choice for handling the collation process within our edition production
pipeline. In the process of this testing, we are working hard to improve our
documentation so that our production methods are fully legible by our peers and
future scholars working on related projects.
Bio: Elisa Beshero-Bondar<https://behrend.psu.edu/person/elisa-beshero-bondar-
phd> explores and teaches document data modelling with the XML family of
languages at Penn State Erie, The Behrend College<https://behrend.psu.edu/>,
where she is a Professor of Digital Humanities and Program Chair of Digital
Media, Arts, and Technology. She serves on the TEI Technical Council and is the
founder and organizer of the Digital Mitford
project<https://digitalmitford.org/> and its usually annual coding
school<https://digitalmitford.github.io/DigMitCS/>. She experiments with
visualizing data from complex document structures like epic poems and with
computer-assisted collation of differently encoded editions of
Frankenstein<https://frankensteinvariorum.github.io/viewer/>. Her ongoing
adventures with markup technologies are documented on her development site at
newtfire.org<https://newtfire.org/>.
===
--
Dr James Cummings, Senior Lecturer in Late-Medieval Literature and Digital
Humanities,
School of English, Newcastle University
In-Person Office Hours: https://jamescummings.youcanbook.me/
Zoom Office Hours: https://jamescummings-zoom.youcanbook.me/
--[3]------------------------------------------------------------------------
Date: 2022-06-08 06:39:40+00:00
From: Stuart James <stuart.james@iit.it>
Subject: [CFP] ECCV 2022 workshop: VISART VI "Where Computer Vision Meets Art"
VISART VI "Where Computer Vision Meets Art"
https://visarts.eu
*******************************************************
6th Workshop on Computer VISion for ART Analysis
In conjunction with the 2022 European Conference on Computer Vision (ECCV),
Tel-Aviv, Israel
IMPORTANT DATES
Full & Extended Abstract Paper Submission: 27th June 2022
Notification of Acceptance: 8th August 2022
Camera-Ready Paper Due: 15th August 2022
Workshop: TBA (23-24th October)
*******************************************************
CALL FOR PAPERS
Following the success of the previous editions of the Workshop on Computer
VISion for ART Analysis held in 2012, `14, `16, `18 and 20 we present the
VISART VI workshop, in conjunction with the 2022 European Conference on
Computer Vision (ECCV 2022). VISART will continue its role as a forum for
the presentation, discussion and publication of Computer Vision (CV)
techniques for the analysis of art. As with the previous edition, VISART VI
offers two tracks:
1. Computer Vision for Art - technical work (standard ECCV submission,
14 pages excluding references)
2. Uses and Reflection of Computer Vision for Art (Extended abstract, 4
pages, excluding references)
The recent explosion in the digitisation of artworks highlights the
concrete importance of application in the overlap between CV and art; such
as the automatic indexing of databases of paintings and drawings, or
automatic tools for the analysis of cultural heritage. Such an encounter,
however, also opens the door both to a wider computational understanding of
the image beyond photo-geometry, and to a deeper critical engagement with
how images are mediated, understood or produced by CV techniques in the
`Age of Image-Machines' (T. J. Clark). Submissions to our first track
should primarily consist of technical papers; our second track, therefore,
encourages critical essays or extended abstracts from art historians,
artists, cultural historians, media theorists and computer scientists.
The purpose of this workshop is to bring together leading researchers in
the fields of computer vision and the digital humanities with art and
cultural historians and artists, to promote interdisciplinary
collaborations, and to expose the hybrid community to cutting-edge
techniques and open problems on both sides of this fascinating area of
study.
This workshop, in conjunction with ECCV 2022, calls for high-quality,
previously unpublished, works related to Computer Vision and Cultural
History. Submissions for both tracks should conform to the ECCV 2022
proceedings style and will be double-blind peer-reviewed by at least three
reviewers. However, extended abstracts will not appear in the conference
proceedings. Papers must be submitted online through the CMT submission
system at:
https://cmt3.research.microsoft.com/VISART2022/
TOPICS include but are not limited to:
- Art History and Computer Vision
- Image and visual representation in art
- Approaches for generative art
- 3D reconstruction from visual art or historical sites
- 2D and 3D human pose and gesture estimation in art
- Multi-modal multimedia systems and human-machine interaction
- Multimedia databases and digital libraries for artistic research
- Visual Question & Answering (VQA) or Captioning for Art
- Interactive 3D media and immersive AR/VR for cultural heritage
- Computer Vision and cultural heritage
- Big-data analysis of art
- Media content analysis and search
- Security and legal issues in the digital presentation and distribution of
cultural information
- Surveillance and Behavior analysis in Galleries, Libraries, Archives and
Museums
INVITED SPEAKERS
- Prof. Béatrice Joyeux-Prunel, University of Geneva
- Prof. John Collomosse, Principal Scientist, Adobe Research & Professor of
Computer Vision, CVSSP, University of Surrey
- Prof. Ohad Ben-Shahar, Ben Gurion University
ORGANIZERS:
- Alessio Del Bue, Istituto Italiano di Tecnologia (IIT)
- Leonardo Impett, University of Cambridge
- Peter Bell, Philipps-Universität Marburg
- Noa Garcia, IDS, Osaka University
- Stuart James, Istituto Italiano di Tecnologia (IIT) & UCL DH
--
Dr Stuart James
Researcher (Assistant Professor), Visual Geometry and Modelling (VGM)
Istituto Italiano di Tecnologia (IIT)
Honorary Research Associate, University College London (UCL)
Affiliate Team member, UCL Centre for Digital Humanities (UCLDH)
Genova, Italy
Website: https://stuart-james.com
Meet me: http://meetme.stuart-james.com
_______________________________________________
Unsubscribe at: http://dhhumanist.org/Restricted
List posts to: humanist@dhhumanist.org
List info and archives at at: http://dhhumanist.org
Listmember interface at: http://dhhumanist.org/Restricted/
Subscribe at: http://dhhumanist.org/membership_form.php
