English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  CityPersons: A Diverse Dataset for Pedestrian Detection

Zhang, S., Benenson, R., & Schiele, B. (in press). CityPersons: A Diverse Dataset for Pedestrian Detection. In 30th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Zhang, Shanshan1, Author           
Benenson, Rodrigo1, Author           
Schiele, Bernt1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Content

show
hide
Free keywords: Computer Science, Computer Vision and Pattern Recognition, cs.CV
 Abstract: Convnets have enabled significant progress in pedestrian detection recently, but there are still open questions regarding suitable architectures and training data. We revisit CNN design and point out key adaptations, enabling plain FasterRCNN to obtain state-of-the-art results on the Caltech dataset. To achieve further improvement from more and better data, we introduce CityPersons, a new set of person annotations on top of the Cityscapes dataset. The diversity of CityPersons allows us for the first time to train one single CNN model that generalizes well over multiple benchmarks. Moreover, with additional training with CityPersons, we obtain top results using FasterRCNN on Caltech, improving especially for more difficult cases (heavy occlusion and small scale) and providing higher localization quality.

Details

show
hide
Language(s): eng - English
 Dates: 2017-02-182017
 Publication Status: Accepted / In Press
 Pages: 12 p.
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: Zhang_Benenson_Schiele2017
 Degree: -

Event

show
hide
Title: 30th IEEE Conference on Computer Vision and Pattern Recognition
Place of Event: Honolulu, HI, USA
Start-/End Date: 2017-07-22 - 2017-07-25

Legal Case

show

Project information

show

Source 1

show
hide
Title: 30th IEEE Conference on Computer Vision and Pattern Recognition
  Abbreviation : CVPR 2017
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -