GVC9 - The 9th Workshop on Fine-Grained Visual Categorization Call for Papers

GVC9 - The 9th Workshop on Fine-Grained Visual Categorization
19th June 2022 @ CVPR 2022
Website: https://sites.google.com/view/fgvc9
Twitter: @fgvcworkshop
Email: fgvcworkshop@googlegroups.com

This workshop brings together researchers to explore visual
recognition across the continuum between basic level categorization
(object recognition) and identification of individuals (face
recognition, biometrics). Participants are encouraged to submit short
papers and to take part in a set of competitions organized in
conjunction with the workshop - details below. We will also have an
exciting lineup of invited speakers from computer vision through to
domain experts.


We invite submission of 4 page (excluding references) extended
abstracts on topics related to fine-grained recognition. Reviewing of
abstract submissions will be double-blind. The purpose of this
workshop is not specifically as a venue for publication so much as a
place to gather together those in the community working on or
interested in FGVC. The workshop proceedings will not appear in the
official CVPR 2022 workshop proceedings. Submissions of work which has
been previously published, including papers accepted to the main CVPR
2022 conference are allowed.


* Deadline for Submission - 25th March 2022
* Notification of Acceptance - 25th April 2022
* Camera Ready - 6th May 2022
* Submission will be via CMT


The purpose of this workshop is to bring together researchers to
explore visual recognition across the continuum between basic level
categorization and identification of individuals within a category
population. Topics of interest include:

Fine-grained categorization -
 Novel datasets and data collection strategies for fine-grained categorization
 Low/few shot learning
 Self-supervised learning
 Semi-supervised learning
 Attribute and part based approaches
 Taxonomic prediction
 Long-tailed learning

Human-in-the-loop -
 Fine-grained categorization with humans in the loop
 Embedding human expertsí knowledge into computational models
 Machine teaching
 Interpretable fine-grained models

Multi-modal learning -
 Using audio and video data
 Using metadata e.g. geographical priors
 Learning shape

Fine-grained applications -
 Product recognition
 Animal biometrics and camera traps
 Museum collections

We will also be hosting several fine-grained computer vision
challenges covering a range of fine-grained tasks. The competitions
will be hosted on Kaggle and will be announced on our website soon.

Sara Beery - Caltech
Serge Belongie - Cornell
Elijah Cole - Caltech
Xiangteng He - Peking University
Christine Kaeser-Chen - DeepMind
Oisin Mac Aodha - University of Edinburgh
Subhransu Maji - University of Massachusetts, Amherst
Abby Stylianou - Saint Louis University
Jong-Chyi Su - University of Massachusetts, Amherst
Grant Van Horn - Cornell
Kimberly Wilber - Google