[robotics-worldwide] [meetings] Call for participation: Linguistics Meets Image and Video Retrieval Workshop and Fashion IQ Challenge (ICCV 2019)

ICCVWorkshop 2019 iccvworkshop2019 at gmail.com
Wed Jul 24 21:57:17 PDT 2019

Call for Participation

ICCV 2019
October 28th, 2019
Seoul, South Korea

Image and video retrieval systems have been one of the most widely studied
areas in computer vision for decades. With the tremendous growth of
searchable visual media in recent years, the need for effective retrieval
systems has intensified, finding its use in many application domains, such
as e-commerce, surveillance and Internet search. Over the past few years,
the advent of deep learning has propelled the research of visual content
retrieval and the field has been evolving at a fast pace. Amongst progress
on core topics in image retrieval, there has been a burgeoning trend on
exploiting natural language understanding in the context of visual media

The initial attempts at the intersection of visual content retrieval
systems and natural language understanding have explored topics such as
interactive search using natural language feedback, image and video
retrieval based on natural language queries, and task-oriented visual
dialog agents for image retrieval. These recent works are opening up new
paths forward. The goal of the workshop is to bring together emerging
research interest in this area, discuss open challenges and opportunities
ahead. This workshop is an initial attempt at studying the different
synergistic relations in this interdisciplinary area of information
retrieval, natural language understanding and computer vision. Linking
these three areas together is especially relevant in today’s setting as
most real-world applications in different domains (retail, travel,
healthcare, education etc.) require interactions through different
modalities: searching or retrieving multimodal information and interacting
through multimodal responses.

We provide two ways of participating in the workshop: challenge track and
abstract paper track. We offer prizes for both tracks!
(1) Paper track: We solicit abstract paper submissions on novel approaches
for visual media retrieval which leverages language understanding, external
knowledge, and multimodal user interactions, etc.
(2) Fashion IQ challenge: We introduce a novel dataset and challenge for
interactive image retrieval based on natural language feedback. The task is
to retrieve a target image based on a reference image and the associated
relative captions which describe the visual differences between the target
and the reference image.

Important Dates:
* Paper submission deadline: September 15th (11:59PM PST)
* Challenge submission deadline: September 30th (11:59PM PST)

For detailed information on paper submission, challenge rules and speaker
information, please visit: https://urldefense.proofpoint.com/v2/url?u=https-3A__sites.google.com_view_lingir&d=DwIFaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=HShnAQyffjygeXl8JKMVImnRgN8NocJPtyc7WVByaU0&s=COcVAfEAK4GwXpSgSPtLefBtNPbjT_H_OZ0EoSpzweQ&e= 

*Hui Wu*
Research Staff Member
Computer Vision and Multimedia
IBM Research AI

More information about the robotics-worldwide mailing list