Beyond Context: Exploring Semantic Similarity for Tiny Face Detection

Yue Xi, Jiangbin Zheng, Xiangjian He, Wenjing Jia, Hanhui Li

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

Tiny face detection aims to find faces with high degrees of variability in scale, resolution and occlusion in cluttered scenes. Due to the very little information available on tiny faces, it is not sufficient to detect them merely based on the information presented inside the tiny bounding boxes or their context. In this paper, we propose to exploit the semantic similarity among all predicted targets in each image to boost current face detectors. To this end, we present a novel framework to model semantic similarity as pairwise constraints within the metric learning scheme, and then refine our predictions with the semantic similarity by utilizing the graph cut techniques. Experiments conducted on three widely-used benchmark datasets have demonstrated the improvement over the-state-of-the-arts gained by applying this idea.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE Computer Society
Pages1907-1911
Number of pages5
ISBN (Electronic)9781479970612
DOIs
Publication statusPublished - 29 Aug 2018
Externally publishedYes
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: 7 Oct 201810 Oct 2018

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
Country/TerritoryGreece
CityAthens
Period7/10/1810/10/18

Keywords

  • Graph-cut
  • Metric learning
  • Semantic information
  • Tiny face detection

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'Beyond Context: Exploring Semantic Similarity for Tiny Face Detection'. Together they form a unique fingerprint.

Cite this