Presentation

Learning Multimodal Affinities for Textual Editing in Images
SessionSummary and Q&A: Style and Color in Images
Authors
Or Perel
Oron Anschel
Omri Ben-Eliezer
Shai Mazor
Hadar Averbuch-Elor
Event Type
Technical Paper
Recordings
This session WILL be recorded.
Interest Areas
Research & Education
Registration Levels
Ultimate Supporter
Ultimate Attendee
Exhibitor Ultimate
TimeWednesday, 11 August 20217am - 8am PDT
Location
DescriptionWe present an unsupervised method to learn multimodal affinities of textual entities in document images, considering their style, syntax, semantics, and geometry, and we demonstrate its applicability to various editing operations.
Authors
Or Perel
Amazon Web Services
Oron Anschel
Amazon Web Services
Omri Ben-Eliezer
Harvard University
Shai Mazor
Amazon Web Services
Hadar Averbuch-Elor
Cornell-Tech Cornell University