Recognizing Families In the Wild Data Challenge (4th Edition) in conjunction with FG 2020

Organized by jvision - Current server time: Dec. 5, 2019, 4:52 p.m. UTC

Previous

Training
Nov. 14, 2019, midnight UTC

Current

Validation
Dec. 1, 2019, midnight UTC

Next

Challenge
Jan. 3, 2020, midnight UTC

FG 2020 Recognizing Families In the Wild (RFIW2020) Challenge

Kinship Verification (Track I)

LOGO

Overview

This is the 4th large-scale kinship recognition data competition, in conjunction with FG 2020. This is made possible with the release of the largest and most comprehensive image database for automatic kinship recognition,  Families in the Wild (FIW).

RFIW2020 will support 3 laboratory-style evaluation protocols: (1) repeated; (2) and (3) supported for the first time.

  1. Kinship Verification (one-to-one)
  2. Tri-subject Verification (one-to-two) 
  3. Search and Retrieval  (one-to-many)

 
Additionally, we will have a general paper submission track (more to come).


The best paper award will be awarded will be included in the 2020 IEEE Proceedings of Automatic Face and Gesture Recognition (AMFG). Note that individuals and/or teams can participate in just one or all tasks. In any case, standings will be determined for each task separately.

Important dates

  • 2019.11.13 Team registration opens.
  • 2019.11.13 Training and validation data made available (Phase I).
  • 2019.1.14 Validation server online.
  • 2019.12.01 Validation labels released (Phase II).
  • 2020.01.03 Test "blind" set and labels for validation set are released; validation server closed (Phase III).
  • 2020.01.13 Test results and README(s) (i.e., brief descriptions of each submission) are due.
  • 2020.01.14 Results will be made public and standings listed on the leader-board.
  • 2020.01.20 Paper submission for task evaluations and general paper submissions are due.
  • 2020.02.05 Notification.
  • 2020.02.26 Camera-ready due.
  • 2020.05.[18-22] RFIW Challenge in conjunction with FG 2020.

Background

Automatic kinship recognition holds promise to an abundance of applications, like to aid forensic investigations as a powerful cue to narrow the search space (e.g., perhaps knowing that the Boston Bombers were brothers we may have identified the suspects sooner). There are many beneficiaries of such technologies, whether the consumer (e.g., automatic photo library management), the scholar (e.g., historic lineage & genealogical studies), the data analyzer (e.g., social-media-based analysis), or the investigator (e.g., cases of missing children and human trafficking).

A fair question to ask-- if so applicable, why is visual kinship recognition technology not found, or even prototyped, in real-world products? Reasons for this are two-fold:

  1. Other image datasets for kinship recognition tasks do not capture nor reflect the true data distributions of the families of the world. Furthermore, other collections are small in size.
  2. Kin-based relationships are less discriminant than other, more conventional face-based problems, as there exist many hidden factors that affect the facial appearances amongst different family members.

Both points were addressed with the introduction of our FIW database, with data distributions to properly represent real-world scenarios available at scales much larger than ever before. FIW now allows researchers and practitioners to employ complex, modern-day data-driven methods (i.e., deep learning) in ways not possible before.

In the end, we hope FIW serves as a rich resource to further bridge the semantic gap of facial recognition-based problems to the broader human-computer interaction incentive.

Participants can submit in one or all tasks-- note standings will be determined for each task separately. We next introduce the 3 tasks of 2020 RFIW.

T-1: Kinship Verification

Kinship verification aims to determine whether a pair of facial images are blood relatives of a certain type (e.g., parent-child). This is a classical Boolean problem with system responses being either KIN or NON-KIN (i.e., related or unrelated, respectfully). Thus, this task tackles the one-to-one view of automatic kinship recognition.

More details are found in the data section of the competition.

T-2: Tri-Subject Verification

(COMING SOON) Tri-Subject Verification focuses on a slightly different view of kinship verification– the goal is to decide whether a child is related to a pair of parents. This is a more realistic assumption, as having knowledge of one parent typically means knowledge of the other is accessible. This is the first time this was done using FIW data.

More details are found in the data section of the competition.

T-3: Search & Retrieval

(COMING SOON).

Provided Resources

  • Scripts: Scripts will be provided to facilitate the reproducibility of the images and performance evaluation results on, Github.
  • Contact: You can use the forum on the data description page (highly recommended!) or directly contact the challenge organizers by email (robinson.jo [at] husky.neu.edu and mshao [at] umassd.edu) if you have doubts or any question.

Contact Joseph Robinson (robinson.jo [at] husky [dot] neu [dot] edu, robinson.jo@husky.neu.edu) and Ming Shao (mshao [at] umassd [dot] edu, mshao@umassd.edu) for all inquiries pertaining to 2020 RFIW and FIW.

More information about FIW dataset is provided on the project page: https://web.northeastern.edu/smilelab/fiw/

RFIW Workshop and Challenge @ FG 2020

LOGO

Large-Scale Kinship Recognition Data Challenge: Kinship Verification (Track 1)

Overview

The goal of kinship verification is to determine whether or not a pair of facial images are blood relatives of a particular type (e.g., parent-child): a classical boolean problem with classes kin and non-kin (i.e., related and unrelated, respectfully). In other words, the one-to-one view of automatic kinship recognition.

Prior research efforts have considered mainly considered parent-child kinship types, i.e., father-daughter (F-D), father-son (F-S), mother-daughter (M-D), mother-son (M-S). While far less, but still some, attention has been given to sibling pairs, i.e., Sister-Sister (S-S), Brother-Brother (B-B), and siblings of the opposite sex (SIBS). As research in both psychology and computer vision revealed, different kin relations render different familial features and, hence, the four kin relations are generally treated differently during the model training. Thus, additional kinship relations (i.e., pairwise types) would further both our understanding and capabilities of automatic kinship recognition. With the release of FIW, the number of facial pairs accessible for kinship verification has greatly increased; along with four additional relationship types (i.e., grandparent-grandchild) were made available (see the middle column of the image below).


Data Splits

FIW includes a total of >500,000 pairs of faces from the 11 different types of kinship. Thus, the range of modern-day data-driven approaches (i.e., deep learning models) that is now possible opens doors to possibilities in terms of proposed solutions to the problem of kinship verification.

The data for kinship verification is partitioned into 3 disjoint sets referred to as Train, Validation, and Test sets-- ground truth for the former will be provided during Phase 1 for self-evaluation, while runs on the Validation can be submitted for scoring. Ground truth for Validation will be made available during Phase 2. The "blind" test set will be released during Phase 3. No labels will be provided for the Test set until the challenge is adjourned and results are reported. Teams will be asked to only process the Test set to generate submissions and, hence, any attempt of analyzing or understanding the Test set is prohibited. All sets will be made-up of an equal number of positive and negative pairs. Lastly, note that there is no family or subject identity overlapping between any of the sets.

Source code and trained models can be found at https://github.com/visionjo/pyfiw.

Links to download data will be provided to registered participants. Register and access data.

Evaluation Settings and Metrics

As conventional face verification, we offer 3 modes, which are listed & described as follows:

  1. Unsupervised: No labels are given, i.e., no prior knowledge about kinship or subject IDs.
  2. Image-restricted: Kin/ non-kin labels given for training set, with no family overlap between training and test sets.
  3. Image-unrestricted: Kinship labels & IDs given– allows mining for additional negative pairs.

Participants will be allowed to make up to 6 submissions of different runs for each mode (i.e., teams participating in all 3 settings will be allowed to submit up to 18 sets of results). Note that runs must be processed independently of one another.

For all modes, the underlying metric used is accuracy, which is averaged across the five folds. Also, ROC curves will also be used when reporting results.

Contact Joseph Robinson (robinson.jo [at] husky [dot] neu [dot] edu, robinson.jo@husky.neu.edu) and Ming Shao (mshao [at] umassd [dot] edu, mshao@umassd.edu) for all inquiries pertaining to 2020 RFIW and FIW.

More information about FIW dataset is provided on the project page: https://web.northeastern.edu/smilelab/fiw/

RFIW Workshop and Challenge @ FG 2020

LOGO

Data Agreement

If you're using or participating in either Challenge or using FIW data please cite the following papers:

Joseph P. Robinson, Ming Shao, Yue Wu, Hongfu Liu, Timothy Gillis, Yun Fu, "Visual kinship recognition of families in the wild." In IEEE TPAMI, 2018.
@article{robinson2018visual,
title = {Visual kinship recognition of families in the wild},
author = {Robinson, Joseph P and Shao, Ming and Wu, Yue and Liu, Hongfu and Gillis, Timothy and Fu, Yun},
journal = {IEEE transactions on pattern analysis and machine intelligence},
volume = {40},
number = {11},
pages = {2624--2637},
year = {2018},
publisher = {IEEE}
}


Joseph P. Robinson, Ming Shao, Handong Zhao, Yue Wu, Timothy Gillis, Yun Fu, "Recognizing Families In the Wild (RFIW): Data Challenge Workshop in conjunction with ACM MM 2017." In RFIW '17: Proceedings of the 2017 Workshop on Recognizing Families In the Wild, 2017.
@inproceedings{Fu:2017:3134421,
title = {Recognizing Families In the Wild (RFIW): Data Challenge Workshop in conjunction with ACM MM 2017},
author = {Robinson, Joseph P and Shao, Ming and Zhao, Handong and Wu, Yue and Gillis, Timothy and Fu, Yun},
booktitle = {RFIW '17: Proceedings of the 2017 Workshop on Recognizing Families In the Wild},
pages = {5--12},
location = {Mountain View, California, USA},
publisher = {ACM},
address = {New York, NY, USA},
year = {2016}
}


S. Wang, J. P. Robinson, and Y. Fu, "Kinship Verification on Families In The Wild with Marginalized Denoising Metric Learning." In 12th IEEE AMFG, 2017.
@inproceedings{kinFG2017,
author = {Wang, Shuyang and Robinson, Joseph P and Fu, Yun},
title = {Kinship Verification on Families in the Wild with Marginalized Denoising Metric Learning},
booktitle = {Automatic Face and Gesture Recognition (FG), 2017 12th IEEE International Conference and Workshops on}
}


Joseph P. Robinson, Ming Shao, Yue Wu, and Yun Fu, "Families in the Wild (FIW): Large-scale Kinship Image Database and Benchmarks." In Proceedings of the ACM on Multimedia Conference, 2016.
@inproceedings{robinson2016fiw,
title = {Families in the Wild (FIW): Large-Scale Kinship Image Database and Benchmarks},
author = {Robinson, Joseph P and Shao, Ming and Wu, Yue and Fu, Yun},
booktitle = {Proceedings of the 2016 ACM on Multimedia Conference},
pages = {242--246},
year = {2016},
organization = {ACM}
}

Submissions

 

 
See https://web.northeastern.edu/smilelab/rfiw2020/submissions.html for more information on submissions (i.e., continued terms and conditions, along with links to templates, portal for authors, and more).



RFIW Workshop and Challenge @ FG 2020

LOGO

Organizers

Honorary Chairs

 

 
Rama Chellappa
University of Maryland
Picture
 
 
Matthew A. Turk
Toyota Technological Institute at Chicago (TTIC)
https://www.ttic.edu/mtur

 

 

General Chair

Picture
 
Yun Fu
Northeastern University

  

Workshop Chairs

Picture
 
Joseph Robinson
Northeastern University
http://www.jrobsvision.com
Picture
 
Ming Shao
University of Massachusetts (Dartmouth)
http://www.cis.umassd.edu/~mshao/
Picture
 
Siyu Xia
Southeast University (China), Nanjing
Picture
 
Mike Stopa
Picture
 
Samson Timoner
ISMConnect
Picture
 
Yu Yin
Northeastern University

Web and Publicity Co-Chairs

Picture
 
Zaid Khan
Northeastern University

RFIW2020 supports the traditional verification task, along with two new evaluations (i.e., Tri-Subject Verification and Search & Retrieval); also, General Paper Submission and Brave New Ideas tracks. See Challenge Page for more details.

Contact Joseph Robinson (robinson.jo [at] husky [dot] neu [dot] edu, robinson.jo@husky.neu.edu) and Ming Shao (mshao [at] umassd [dot] edu, mshao@umassd.edu ) for all inquiries pertaining to 2020 RFIW and FIW.

More information about FIW dataset is provided on the project page: https://web.northeastern.edu/smilelab/fiw/

Training

Start: Nov. 14, 2019, midnight

Description: Training and validation data made available. Labels available for Training; sever will be open for scoring Validation

Validation

Start: Dec. 1, 2019, midnight

Description: Labels for Validation made available. Evaluation scripts provided to participants. Validation will still be open for those that rather upload results for automatic scoring and or those looking to make sure the submissions are formatted properly.

Challenge

Start: Jan. 3, 2020, midnight

Description: Test data release. Validation server closed. Open for final submissions.

Competition Ends

Jan. 13, 2020, midnight

You must be logged in to participate in competitions.

Sign In