WIDER Face and Person Challenge 2019

Workshop in conjunction with ICCV 2019, Seoul, Korea
October 28, 2019

Challenge Tracks

Overview

Following the success of the First WIDER Challenge Workshop , we organize a new round of challenge in conjunction with ICCV 2019. The challenge centers around the problem of precise localization of human faces and bodies, and accurate association of identities. It comprises of four tracks:

Datasets and Submission

Datasets are available at the Codalab site of each challenge track. Submissions to all phases will be done through the CodaLab site. Please register to the site and refer to the instructions on how to download the datasets and submit your results. Also the evaluation metrics of each track would be introduced there.

Link to Codalab: WIDER Face Detection -- WIDER Pedestrian Detection -- WIDER Cast Search by Portrait -- WIDER Person Search by Language

Prizes

The winner team of each track will receive cash prize and AWS credits. Challenge participants with the most successful and innovative methods will be invited to present at the workshop and to submit a paper to the workshop.

Terms and Conditions

Link to Terms and Conditions.

In the event of any inconsistency between the terms and details of this website and Codalab competition sites, the details on the Codalab sites shall prevail.

Contact

For more information, please contact us at wider-challenge@ie.cuhk.edu.hk.

SChedule

Time Programme Speaker
8:50-9:00                                     Opening Remarks
9:00-9:40 Invited Talk Person Imagery Search by Text Query
Shaogang Gong
9:40-9:50 Track Introduction Person Search by Language
Hongsheng Li
9:50-10:10 Spotlight on Winning Solution and Workshop Papers [First Place] Fusing Two Directions in Cross-domain Adaption for Real Life Person Search by Language.
Kai Niu, Yan Huang, Liang Wang
[Third Place] Cross-Modal Person Search: A Coarse-to-Fine Framework using Bi-directional Text-Image Matching.
Xiaojing Yu, Tianlong Chen, Yang Yang, Michael Mugo, Zhangyang Wang
[Workshop Paper] A Semi-Supervised Maximum Margin Metric Learning Approach for Small Scale Person Re-identification.
T M Feroz Ali, Subhasis Chaudhuri
10:10-10:20 Invited Paper CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval Zihao Wang, Xihui Liu, Hongsheng Li, Lu Sheng, Junjie Yan, Xiaogang Wang, Jing Shao
10:20-11:00 Coffee + Posters
11:00-11:40 Invited Talk Person Re-Identification and Tracking in Multiple Non-Overlapping Cameras.
Mubarak Shah
11:40-11:50 Track Introduction Cast Search by Portrait
Qingqiu Huang
11:50-12:15 Spotlight on Winning Solution and Workshop Papers [First Place]
First Place Winner Solution
Xingze Li
[Second Place]
Second Place Winner Solution
Ruiping Wang
[Third Place]
Cast Search via Two-Stream Label Propagation
Bing-Jhang Lin
12:15-12:25 Invited Paper Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification.
Yuqian Zhou
12:25-12:35 Invited Paper Deep Reinforcement Active Learning for Human-in-the-Loop Person Re-Identification.
Zimo Liu
12:35-14:00 Lunch
14:00-14:40 Invited Talk A history of thinking small
Larry Davis
14:40-14:50 Track Introduction Face Detection
Yuanjun Xiong
14:50-15:25 Spotlight on Winning Solution and Workshop Papers [First Place] First Place Winner Solution
Yang Liu
[Second Place] Single-stage Joint Face Detection and Alignment
Jia Guo
[Third Place] Third Place Winner Solution
Pengfei Luo
[Teasor Track Winner] TBD
Xiaojun Zhang
[Workshop Paper] A Densenet based Robust Face Detection Framework
Abhilash Nandy
15:25-15:35 AWS China Introduction
15:35-16:00 Coffee + Posters
16:00-16:40 Invited Talk Compositional Models for Activity Detection in Challenging Datasets
Alan Yuille
16:40-16:50 Track Introduction Pedestrian Detection
Wanli Ouyang
16:50-17:20 Spotlight on Winning Solution and Workshop Papers [First Place] First Place Winner Solution
Ze Chen
[Second Place] Second Place Winner Solution
Hongsong Wang
[Third Place] Third Place Winner Solution
Haien Zeng
[Workshop Paper] What Face and Body Shapes Can Tell Us About Height
Semih Günel, Helge Rhodin, Pascal Fua
[Workshop Paper] Bayesian Gait-based Gender Identification (BGGI) Network on Individuals Wearing Loosely Fitted Clothing
Amarjot Singh, Aman Kumar, Anisha Jain
17:20-17:30 Invited Paper Weakly Aligned Cross-Modal Learning for Multispectral Pedestrian Detection
Lu Zhang, Xiangyu Zhu, Xiangyu Chen, Xu Yang, Zhen Lei, Zhiyong Liu


Accepted Papers

ID Title Authors
2 Cross-Modal Person Search: A Coarse-to-Fine Framework using Bi-directional Text-Image Matching Xiaojing Yu, Tianlong Chen, Yang Yang, Michael Mugo, Zhangyang Wang
3 What Face and Body Shapes Can Tell Us About Height Semih Günel, Helge Rhodin, Pascal Fua
5 Part Matching with Multi-level Attention for Person Re-Identification Jiaze Wang
6 Fusing Two Directions in Cross-domain Adaption for Real Life Person Search by Language Kai Niu, Yan Huang, Liang Wang
7 Single-stage Joint Face Detection and Alignment Jiankang Deng, Jia Guo, Stefanos Zafeiriou
8 A Semi-Supervised Maximum Margin Metric Learning Approach for Small Scale Person Re-identification T M Feroz Ali, Subhasis Chaudhuri
9 A Densenet based Robust Face Detection Framework Abhilash Nandy
14 Bayesian Gait-based Gender Identification (BGGI) Network on Individuals Wearing Loosely Fitted Clothing Amarjot Singh, Aman Kumar, Anisha Jain
16 Cast Search via Two-Stream Label Propagation Jhih-Ciang Wu, Tyng-Luh Liu, Bing-Jhang Lin


Leaderboard

Face Detection

Rank Score Team Name Affiliation Team Members
1 0.5713 BAIDU VIS Baidu Inc.;
North China Electric Power University;
Institute of Automation, CAS
Yang Liu, Xu Tang, Zhihang Li, Bin He, Bi Li,
Kangkang Wang, Ran He, Xin Ai, Jingtuo Liu,
Junyu Han
2 0.5666 InsightFace InfiniVision;
Imperial College
Jia Guo, Jiankang Deng, Yi Jiang
3 0.5634 cv3ifly University of Science and Technology of China;
iFLYTEK
Pengfei Luo, Yuxin Gu, Changfeng Xi, Ziyang Wu


Pedestrian Detection

Rank Score Team Name Affiliation Team Members
1 0.6725 R4D Megvii Inc.;
Peking University;
Beijing University of Posts and Telecommunications
Ze Chen, Chu Li, Yan Chen, Zhiyuan Li,
Hongkai Zhang, Boxun Li, Zhicheng Wang,
Gang Yu
2 0.6569 IIAI_VOS Inception Institute of Articial Intelligence Hongsong Wang, Jinpeng Li, Haibo Jin,
Shengcai Liao, Ling Shao
3 0.6362 Z Sun Yat-sen University Haien Zeng, Yiran Ding, Wentao Zhang,
Xun Liu, Pai Peng


Cast Search by Portrait

Rank Score Team Name Affiliation Team Members
1 0.8730 MCC_USTC University of Science and Technology of China;
iFLYTEK
Xingze Li, Qiaokang Xie, Ziyang Wu, Lei Lu,
Wengang Zhou
2 0.8515 VIPL_ICT Institute of Computing Technology, CAS;
University of Chinese Academy of Sciences
Ruiping Wang, Ruikui Wang, Xiaodong Wu,
Ziyi Bai, Shiguang Shan,Xilin Chen
3 0.8137 IIS_CVL Institute of Information Science, Academia Sinica;
National Taiwan University
Bing-Jhang Lin, Bing-Yuan Zeng, Jhih-Ciang Wu,
Tyng-Luh Liu, Li-Chen Fu, Chiou-Shann Fuh


Person Search by Language

Rank Score Team Name Affiliation Team Members
1 0.2307 Plan-Six Institute of Automation, CAS Kai Niu, Yan Huang, Da Li, Liang Wang
2 0.1314 ZJU-Challenger Zhejiang University Kuncai Zhang, Xuemei Yi
3 0.1275 SummerWalrus Texas A&M University;
Walmart Technology
Xiaojing Yu, Tianlong Chen, Yang Yang,
Michael Mugo


Special Track: Face Detection Runtime

Rank Score Team Name Affiliation Team Members
1 0.2792 WeFace WeBank Xiaojun Zhang, Yuchong Gu, Zhenwen Zhu
2 0.1759 Airia RuntimeFace Nanjing Artificial Intelligence Chip Research,
Institute of Automation, CAS
Qinghao Hu, Sujuan Wang, Tian Liang,
Qiang Chen, Cong Leng, Jian Cheng
3 0.1619 Less Institute of Automation, CAS Anda Cheng, Mingchen Zhu, Lei Yin, Qiman Wu

Call for Papers

WIDER Challenge 2019 will be hosted in the beautiful city of Seoul, Korea and it inherits the tradition of previous workshop in providing a fertile ground for leading engineers and scientists from around the world to disseminate their research outcomes and push forward the frontiers of knowledge within these and related areas. The WIDER Challenge Workshop 2019 topics cover but are not limited to:

  • Face detection
  • Pedestrian detection
  • Person search (language-based and image-based)
  • Person re-identification
  • Face analysis
  • Benchmark evaluation

Papers accepted must be registered and presented to ensure their inclusion in the IEEE Xplore Library. All accepted papers will be presented at the poster session. Selected papers will be presented at the oral session. The format for submission is the same as the ICCV 2019 requirement .

Paper submission and review site: Submission Site .

Important Dates

Click the following tab to see the timetable of the challenge and the workshop.

Event Date (Always 11:59 PM Pacific Time)
Site Online May 8, 2019
Release of train data and validation data May 15, 2019
Validation server online May 15, 2019
Final test data release, test server online June 25, 2019
Test results submission deadline, test server closed (except Face Detection Track) Aug. 1, 2019
Test results submission deadline, test server closed for Face Detection Track Aug. 8, 2019
Fact sheets submission deadline - Template Aug. 12, 2019
Final test results release to the participants Aug. 13, 2019
Event Date (Always 11:59 PM Pacific Time)
Site Online May 8, 2019
CMT online July 1, 2019
Paper submission deadline Aug. 17, 2019    Aug. 28, 2019
Notification to authors Aug. 24, 2019    Sep. 20, 2019
Camera ready deadline Aug. 29, 2019    Sep. 27, 2019
Workshop date Oct. 28, 2019

Invited Speakers

  • Generic placeholder image
    Mubarak Shah
    Trustee Chair Professor of Computer Science, University of Central Florida
  • Generic placeholder image
    Alan L. Yuille
    Bloomberg Distinguished Professor of Cognitive Science and Computer Science at Johns Hopkins University
  • Generic placeholder image
    Larry S. Davis
    Professor of the Institute for Advanced Computer Studies and the Department of Computer Science at University of Maryland
  • Generic placeholder image
    Shaogang Gong
    Professor of Visual Computation at Queen Mary University of London

Organizers

  • Generic placeholder image
    Dahua Lin
    The Chinese University of Hong Kong

Sponsors