4th Data Challenge Workshop on Recognizing Families In the Wild (RFIW) Call for Papers
EEE international workshop on in conjunction with 2020 FG
4th Data Challenge Workshop on Recognizing Families In the Wild (RFIW)
-- Automatic Modeling and Analysis of Kinship
Project Page
Overview
We are pleased to announce the fourth large-scale kinship recognition
data competition, Recognizing Families In the Wild (RFIW), in
conjunction with the 2020 FG. RFIW has been made possible with the
release of the largest and most comprehensive image database for
automatic kinship recognition, Families in the Wild (FIW) dataset.
All submissions (i.e., challenge papers, general paper submissions,
and Brave New Ideas) will be peer-reviewed for publication as part of
RFIW2020 in the IEEE International Conference on Automatic Face and
Gesture Recognition (2020 AMFG) proceedings. Also, paper
presentations, either oral and or poster, along with special guest
keynote speakers, are in store for the workshop and award ceremony
agenda at the 2020 AMFG conference on 18-22 May in Buenos Aire,
Argentina. Updates
All three challenges are live on codalab! CMT open for paper
registration and submission: papers on novel work in automatic kinship
recognition and Brave New Ideas.
2019-12-11 Konica Minolta donated to award the best paper. Thank you, and welcome to our first sponsor!
2019-12-11 Competition portal for track 3 now open! (Codalab (T3))
Search & Retrieval of Missing Children (many-to-many)
Can you generate a ranked list of predicted relatives provided a gallery of faces for different subjects?
2019-12-11 Test date pushed back! Phase 3 for all tracks scheduled for 13-20 January 2020.
2019-12-04 Competition portal for track 2 now open! (Codalab (T2))
Verify Tri-subjects (two-to-one, i.e., parents-child)
Father/Mother-Son; Father/Mother-Daughter.
2019-11-14 Competition portal for track 1 now open! (Codalab (T1))
Verify Kinship (e.g., grandfather-to-granddaughter)
11 different pairwise types and largest set of pairs yet
2019-11-03 Call for Papers (submission link)
Call For Papers
Call for general papers and Brave New Ideas on original work in
automatic kinship and or match the interest of the AMFG community. We
added this to ignite the creativity of the community outside the
controlled settings of evaluations-- where assessments are great for
structuring problems such that researchers and practitioners have a
testbed for fair comparisons of algorithms and reproducible
experiments/analysis. However, this alone limits the scope of
use-cases and studies on kinship, as seen in the visual domain, and
beyond. Especially with the data made available with the latest
version of FIW. We hope to see light shed on one or more of the
following ways:
To advance the state-of-the-art for kinship verification and
family classification.
To benchmark new tasks for FIW, like fine-grain classification,
large-scale search, and retrieval, tri-subject verification.
To propose generative models for family photos, relative faces,
photo albums, such.
To explore and understand multimodal uses of text captions
accompanying the family photos of FIW.
To pitch cluster, multi-view, and various types of problems.
To treat kinship as a soft attribute for higher-level tasks (e.g.,
facial recognition, group understanding, social media analysis).
Much more.
Previous RFIW Workshops
Ever since the first RFIW Challenge Workshop as part of the 2017 ACM
MM in Mountain View, CA, USA, we have seen great progress. After three
successful RFIWs (along with a recent Kaggle competition) and great
research strides from the community, we aim for great leaps for this
4th edition. Let's continue to close the gap between
research-and-reality for the highly applicable technology of automatic
kinship recognition.
Taking a look back, here are the homepages of previous RFIW are listed
as follows:
FIW on Kaggle, https://www.kaggle.com/c/Recognizing-Faces-in-the-Wild
RFIW2017: https://web.northeastern.edu/smilelab/RFIW2017/
RFIW2018: https://web.northeastern.edu/smilelab/RFIW2018/
RFIW2019: https://web.northeastern.edu/smilelab/RFIW2019/
Important Dates
1st CFP: 3 Nov 2019
Challenge begins: 8 Nov
Challenge ends: 13 Jan 2020
Papers due: 20 Jan
Author notifications (i.e., oral or poster): 5 Feb
Camera Ready due: 26 Feb
Paper presentations & awards, 2020 FG Conference: May 18-22
Or People
Honorary Chairs
Rama Chellappa, University of Maryland
Matthew A. Turk, Toyota Technical Institute of Chicago (TTIC)
General Chair
Yun Fu, Northeastern University, USA
Workshop Chairs
Joseph P. Robinson, Northeastern University, USA
Ming Shao, University of Massachusetts (Dartmouth)
Siyu Xia, Southeast University (China)
Mike Stopa, Konica Minolta
Samson Timoner, ISMConnect
Yu Yin, Northeastern University, USA
Web and Publicity Co-Chair
Zaid Khan, Northeastern University, USA
Author Guidelines
Submissions made via CMT:
Following the guidelines of IEEE FG:
long: 8 pages (including references); short: 4 pages (+1 for references)
Anonymous
Using FG template [ Latex, Word ]
Contact
For general inquiries, such as requests, ideas, and concerns, please
email the following correspondents:
Joseph Robinson (robinson.jo@husky.neu.edu)
Department of Electrical and Computer Engineering, Northeastern University,
Boston, MA, USA
Ming Shao (mshao@umassd.edu)
Computer and Information Science, University of Massachusetts Dartmouth,
Dartmouth, MA, USA