CHI-ANNOUNCEMENTS Archives

ACM SIGCHI General Interest Announcements (Mailing List)

CHI-ANNOUNCEMENTS@LISTSERV.ACM.ORG

Options: Use Forum View

Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Bogdan Ionescu <[log in to unmask]>
Reply To:
Bogdan Ionescu <[log in to unmask]>
Date:
Sat, 17 Feb 2018 23:08:52 +0200
Content-Type:
text/plain
Parts/Attachments:
text/plain (126 lines)
[Apologies for multiple postings]

***********************************************************************
1st CALL FOR PARTICIPATION
Multimedia Information Processing for Personality & Social Networks
Analysis Challenge
2018 International Conference on Pattern Recognition
August 20-24, Beijing, China
Web site: http://chalearnlap.cvc.uab.es/challenge/27/description/
************************************************************************

Multimedia information processing is a fruitful research topic which
addressed a hefty number of tasks, among them, those focusing on the
analysis of human behavior. Although great advances have been made in
the so-called Looking At People field, it is only recently that
attention from this area is targeting problems that have to do with
more complex behaviors. For instance, personality and social behaviors
are just starting to be explored from a multimedia information
processing perspective.

In this context, the ICPR 2018 Multimedia Information Processing for
Personality & Social Networks Analysis challenge prospective
participants on the analysis of non-obvious human behavior with two
tasks:

***DivFusion***
Information fusion for social image retrieval and diversification.
Diversification of image search results is now a hot research problem
in multimedia. Search engines are now fostering techniques that allow
for providing the user with a diverse representation of his search
results, rather than providing redundant information, e.g. the same
perspective of a monument, or location etc. The DivFusion task builds
on the MediaEval Retrieving Diverse Social Images Tasks and challenges
the participants to develop highly effective information fusion
techniques. The participants will be provided with several query
results, content descriptors and output of various existing
diversification systems. They are to employ fusion strategies to
refine the retrieval results thus to improve even more the
diversification. The data consist of hundreds of Flickr image query
results (>600 queries, both single- and multi- topic) and include:
images (up to 300 images per query), social metadata, descriptors for
visual, text, social information as well as deep learning features,
expert annotations for image relevance and diversification (i.e.
clustering of images according to the similarity of their content) and
more than 180 diversification system outputs.

***HWxPI***
Estimating the personality traits of users from their handwritten
texts and the corresponding transcripts (image and text modalities).
The challenge comprises two phases: a development and a final phase.
For the first phase, the participants should develop their systems
using a set of development pairs of handwritten essays, including
image and text from 418 subjects. Each subject has an associated class
(either 1 or 0) corresponding to the presence of a high pole or a low
pole of a specific personality trait. The traits correspond to the Big
Five personality models used in psychology: Extraversion,
Agreeableness, Conscientiousness, Emotional stability, and Openness to
experience. Participants will have to develop a classifier to predict
the pole of each trait by including both modalities (i.e. text and
visual). For the final evaluation phase, an independent set of 293
unlabeled samples will be provided to the participants, who will have
to provide predictions using the models trained on the development
data.


***********************
Target communities
***********************
Both tracks lie at the frontier of research on Looking At People and
multimedia information processing, and target communities such as (but
are not limited to): information retrieval (text, vision, multimedia,
social media, etc.), information fusion, machine learning, deep
learning, data mining, natural language processing, image and text
processing.

The challenges will run in the CodaLab platform (http://codalab.org/),
and results will be presented at the IAPR ICPR 2018 conference in
Beijing, China (http://www.icpr2018.org/). Participants obtaining the
best results will be invited to submit a paper to a dedicated Special
Issue organized with a top tier journal from the field (TBA).


******************************
Important dates (tentative)
******************************
- Competition starts (& release of the data): February 25, 2018
- Competition ends: April 24, 2018
- Challenge award ceremony: August 21, 2018 (@ ICPR 2018)


***********************
Overall coordination
***********************
Hugo Jair Escalante, Instituto Nacional de Astrofisica, Optica y
Electronica, Mexico ([log in to unmask])
Bogdan Ionescu, University Politehnica of Bucharest, Romania
Esaú Villatoro, Universidad Autonoma Metropolitana, campus Cuajimalpa, Mexico
Gabriela Ramírez, Universidad Autonoma Metropolitana, campus Cuajimalpa, Mexico
Sergio Escalera, Computer Vision Center & University of Barcelona,
Barcelona, Spain
Martha Larson, Delft University of Technology, Netherlands
Henning Müller, University of Applied Sciences Western Switzerland
(HES-SO), Switzerland


On behalf of the Organizers,

Prof. Bogdan IONESCU
ETTI - University Politehnica of Bucharest
http://campus.pub.ro/lab7/bionescu/

Research Center CAMPUS
http://www.campus.pub.ro
https://facebook.com/upbcampus
https://twitter.com/upbcampus

    ---------------------------------------------------------------
    For news of CHI books, courses & software, join CHI-RESOURCES
     mailto: [log in to unmask]

    To unsubscribe from CHI-ANNOUNCEMENTS send an email to
     mailto:[log in to unmask]

    For further details of CHI lists see http://listserv.acm.org
    ---------------------------------------------------------------

ATOM RSS1 RSS2