WIDER Face and Pedestrian Challenge 2018: Methods and Results

TL;DR

This paper reviews the 2018 WIDER Challenge on face and pedestrian detection, highlighting innovative methods, summarizing results from 73 teams, and discussing future research directions in these areas.

Contribution

It provides a comprehensive overview of the challenge's methods, results, and open problems, advancing understanding of state-of-the-art approaches in face and pedestrian detection.

Findings

73 teams submitted valid solutions

Summary of winning methods across tracks

Discussion of open problems and future directions

Abstract

This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian. The challenge focuses on the problem of precise localization of human faces and bodies, and accurate association of identities. It comprises of three tracks: (i) WIDER Face which aims at soliciting new approaches to advance the state-of-the-art in face detection, (ii) WIDER Pedestrian which aims to find effective and efficient approaches to address the problem of pedestrian detection in unconstrained environments, and (iii) WIDER Person Search which presents an exciting challenge of searching persons across 192 movies. In total, 73 teams made valid submissions to the challenge tracks. We summarize the winning solutions for all three tracks. and present discussions on open problems and potential research directions in these topics.