*****************************************************************************
ICCV International Workshop on Cross-domain Human Identification (CHI) 2017
In conjunction with ICCV 2017, Venice, Italy - October 29, 2017

Web: https://chi-workshop.github.io/
Contact: chiworkshop17@gmail.com
*****************************************************************************

_________________
IMPORTANT DATES
_________________

Submission Deadline*: July 3, 2017
Decision to Authors: August 4, 2017
Camera-Ready Paper Due: August 25, 2017
Workshop Date: October 29, 2017

*In case of rejection from ICCV, authors are allowed to re-submit their work to CHI by July 28, 2017

_________________
CALL FOR PAPERS
_________________

The increasing availability of images, videos and shared contents on social networks have emphasized the need for non-intrusive methods that, relying on biometric details (such as the face, body), can recognize the same person from different imagery under challenging conditions. Though identifying people remains a classic problem in vision, it is still far from being a solved problem, therefore establishing a clear, constant and recurrent topic in recent conferences.
This community effort is referred to, in general, as Human Identification in the wild.
The term in the wild emphasizes the difficult, intrinsic nature of analyzing this type of imagery, strongly affected by noise, due to changes in illumination, target pose, occlusion, and a variety of other challenges not present in controlled environments.
Although currently, the main applications for human identification remain video-surveillance, there is a plethora of other applications taking advantages from it.
Additionally, a novel effort emerged from recent works to use multiple cues for recognizing people from multiple viewpoints, under extreme conditions, by weighting the interplay between multiple recognition methods (face recognition, person re-identification, recognition through attributes). The aim of this workshop is to bring together leading researchers working on automatic human recognition to advocate and promote new research directions to video-surveillance as well as other, less obvious, domains such as entertainment, social network analysis, privacy preserving, customer behavior analysis, de-identification methods.

Topics of interest include (but are not limited to):
Face Recognition in the wild
Person Detection and Re-identification
Deep Learning for Human Recognition
Face Detection and Face Tracking to support recognition
Identification using soft-biometrics
Open-set Identification Methods
Gait-based Recognition
Identification techniques to deal with partial, corrupted and noisy data
Scalable methods for face and person recognition
Attributes that improve identification
Interplay and fusion between face and person re-identification methods
De-identification methods (how to preserve the identity)
Implication of human identification on social networks and social media
Datasets for human identification using multiple, different cues.
Theoretical studies showing integration of multi-recognition methods
Machine learning applied to identification
New evaluation metrics for open-world human identification


__________________
INVITED SPEAKERS
__________________

We are glad to have renowned speakers from academia and industry, working on the leading edge of face recognition and person re-identification:

Gerard Medioni, University of Southern California, USA / Amazon
Home Page: http://iris.usc.edu/people/medioni/

Stan Z. Li, Institute of Automation, Chinese Academy of Sciences
Home Page: http://www.nlpr.ia.ac.cn/users/szli/

Wanli Ouyang, The Chinese University of Hong Kong
Home Page: http://www.ee.cuhk.edu.hk/~wlouyang/

Chunhua Shen, University of Adelaide
Home Page: http://cs.adelaide.edu.au/~chhshen/

More international speakers to come.

_________________________
SUBMISSION AND REVISION
_________________________

All submissions will be handled electronically via the conference’s CMT Website (link will be provided soon).

The format for paper submission is the same as the ICCV main conference.
More info will be soon available on the CHI workshop website.

CHI workshop reviewing will be double-blind. Each submission will be reviewed by at least three reviewers for originality, significance, clarity, soundness, relevance and technical contents.

Papers that are not blind, or do not use the template, or have more than 8 pages (excluding references) will be rejected without review.

Submission Deadline*: July 3, 2017

*In case of rejection from ICCV, authors are allowed to re-submit their work to CHI by July 28, 2017

__________________
WORKSHOP CHAIRS
__________________

Giuseppe Lisanti, PhD, University of Florence, Italy giuseppe.lisanti@unifi.it
Iacopo Masi, PhD, University of Southern California (USC), CA, USA iacopoma@usc.edu
Tal Hassner, PhD, Open Univ. of Israel, Israel / USC ISI, CA, USA hassner@isi.edu
Shaogang Gong, PhD, Queen Mary University, London, UK s.gong@qmul.ac.uk

__________
CONTACTS
__________

Email: chiworkshop17@gmail.com
Website: https://chi-workshop.github.io/