WIDER Face and Pedestrian Challenge 2018: Methods and Results

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.

arXiv commentReport of ECCV 2018 workshop: WIDER Face and Pedestrian Challenge

References in corpus (8)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Deformable Convolutional Networks
• Residual Attention Network for Image Classification
• Face Attention Network: An Effective Face Detector for the Occluded Faces
• Single-Shot Refinement Neural Network for Object Detection
• Is Second-order Information Helpful for Large-scale Visual Recognition?
• SFace: An Efficient Network for Face Detection in Large Scale Variations

Cited by in corpus (7)

• RetinaFace: Single-stage Dense Face Localisation in the Wild
• Deep Learning for Generic Object Detection: A Survey
• Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
• MovieNet: A Holistic Dataset for Movie Understanding
• Drone LAMS: A Drone-based Face Detection Dataset with Large Angles and Many Scenarios
• Placepedia: Comprehensive Place Understanding with Multi-Faceted Annotations
• Online Multi-modal Person Search in Videos