1st International Workshop on Traditional Computer Vision in the Age of Deep Learning (TradiCV) Call for Papers

1st International Workshop on Traditional Computer Vision in the Age
of Deep Learning (TradiCV),

which will be held (virtually) in conjunction with the International
Conference on Computer Vision (ICCV). Selected papers published at the
workshop will be invited to submit an extended version to a Special
Issue on IJCV (stay tuned for details)

All the following information is also available at

Apologies if you receive this more than once.


About TradiCV


In the last 5-10 years we have witnessed that deep learning has
revolutionized Computer Vision, conquering the main scene in most
vision conferences. However, a number of problems and topics for which
deep-learned solutions are currently not preferable over classical
ones exist, that typically involve a strong mathematical model (e.g.,
camera calibration and structure-from-motion).

This workshop concentrates on algorithms and methodologies that
address Computer Vision problems in a “traditional” or
“classic” way, in the sense that analytical/explicit models are
deployed, as opposed to learned/neural ones. A particular focus will
be given to traditional approaches that perform better than neural
ones (for instance, in terms of generalization across different
domains) or that, although performing sub-par, provide clear
advantages with respect to deep learning solutions (for instance, in
terms of efforts to collect data, computational requirements, power
consumption or model compactness).

This workshop also encourages critical discussions about preferring a
traditional solution rather than a deep learning approach and also
explores relevant questions about how to bridge the gap between
learning and classic knowledge. We also expect an insightful
discussion about ethical implications of traditional vision in
comparison to deep learning approaches.


Call for Papers


All the Computer Vision topics are welcome as long as the proposed
method does not solely consist in training an end-to-end neural
model. Neural networks are not excluded, though: the workshop welcomes
learning solutions that exploit traditional computer vision as their
core or hybrid approaches that combine deep networks with classical





Two types of submissions are allowed:

    REGULAR PAPERS are meant for original, unpublished works. These
    papers will be limited to 8 pages (excluding references) and
    should follow the ICCV guidelines, including the double blind
    policy. These papers will undergo peer-reviewing and will be
    published in the workshop proceedings in case of
    acceptance. Papers will be selected based on the relevance to the
    workshop, significance and novelty of results, technical merit,
    and clarity of presentation.

    PRESENTATION PAPERS are meant for papers that have been already
    accepted at the main conference. These papers will undergo a soft
    reviewing process by the chairs to assess their relevance to the
    workshop and won't be included in the workshop proceedings.

Submission site: https://cmt3.research.microsoft.com/TradiCV2021  


Important Dates



Submission opening: ~ Early July, 2021

Paper submission deadline: July 26, 2021

Notification of acceptance: August 10, 2021

Camera-ready deadline: August 17, 2021


Invited Speakers



Hongdong Li, Australian National University

Venu Madhav Govindu, Indian Institute of Science

Kathlén Kohn, KTH Stockholm

David Suter, Edith Cowan University



Organizing Team



Matteo Poggi, University of Bologna, Italy

Federica Arrigoni, University of Trento, Italy

Andrea Fusiello, University of Udine, Italy

Stefano Mattoccia, University of Bologna, Italy

Adrien Bartoli, Université Clermont Auvergne, France

Torsten Sattler, Czech Technical University in Prague, Czech Republic

Tomas Pajdla, Czech Technical University in Prague, Czech Republic