[visionlist] MODVIS 2018 Program posted


Qasim Zaidi PhDSUNY Distinguished Professor Graduate Center for Vision Research, State University of New York College of Optometry,33 West 42nd St, New York, NY  10036.Office: 212-938-5542; Lab: 212-938-5756; Fax: 212-938-5537E-mail: qz@sunyopt.eduhttp://poseidon.sunyopt.edu/Zaidi/index.php


[visionlist] CVPR Workshop on Automatic Understanding of Visual Advertisements

We are happy to announce the first CVPR workshop on Automatic Understanding of Visual Advertisements:


As part of the workshop, we are organizing a challenge where the goal is to predict which statements accurately describe the implicit/explicit message that an advertisement conveys, e.g. “I should buy this car because it is spacious”, “I should drink
this coffee because it will keep me awake”, “I should eat this ice-cream because it’s made of natural ingredients”, “I should not pollute because it’s bad for the animals”, or “I should care about safety because human lives are fragile.” Inferring all of these
statements requires recognition of creatively portrayed objects, their relationships and connotations, and performing common-sense reasoning. We are hosting the challenge on EvalAI:


Understanding advertisements is an AI-complete task, and can only be solved with expertise from a
large number of areas, some of which do not at the surface seem to be related to ads. Thus, as another part of the workshop, we invite submission of
2-page abstracts (works in progress, previously published or unpublished work) in any of these areas:

    Visual persuasion, politics and social media

    Metaphors and rhetoric in images or language

    Recognition of objects in non-photorealistic datasets and domain adaptation

    Modeling physical forces

    Abnormality and surprise detection


    Knowledge representation for visual question answering

    Motivations of humans

    Visual attention and memorability


    Analyzing infographics, charts and comics

    Other areas related to understanding persuasive creative imagery

If you are interested in this or related topics, please participate in our challenge, submit your 2-page abstract, or reach out to the organizers about other ways to become involved!

[visionlist] CFP DLMIA 2018 – 4th Workshop on Deep Learning in Medical Image Analysis

DLMIA 2018 – 4th Workshop on Deep Learning in Medical Image Analysis (in conjunction with MICCAI 2018)

Call for Papers

The workshop DLMIA has become one of the most successful MICCAI satellite events, with hundreds of attendees and more than 70 paper submissions in 2017. The 4th edition of DLMIA will be dedicated to the presentation of papers focused on the design and use of deep learning methods in medical image analysis applications. We believe that this workshop is setting the trends and identifying the challenges of the use of deep learning methods in medical image analysis. Another important objective of the workshop is to continue and increase the connection between software developers, researchers and end-users from diverse fields related to Medical Image and Signal Processing, which are the main scopes of MICCAI.

The proceedings will be published by SPRINGER under the “Lecture Notes in Computer Science” book series.


– Medical imaging-based analysis using deep learning

– Medical signal-based analysis using deep learning

– Medical image reconstruction using deep learning

– Deep learning-oriented applications in medicine

– Image description and synthesis using deep learning techniques

– Deep learning model selection in medical imaging

– Multi-modal and multi-dimensional deep learning (3D, 4D, and beyond)

– Learning with noisy labels ( eg. crowdsourcing annotations, imperfect ground truth etc.)

– Integration of clinical variables with imaging data

– Deep learning for interventional image analysis

– Benchmarking and Evaluation of deep learning in clinical settings

– Active Deep Learning for medical imaging

– Reinforcement learning and Meta-learning in Medical Image Analysis

Important Dates:

– May 22nd : results released for MICCAI’18 papers

– June 11th (11:59pm PST) : DLMIA’18 paper submission deadline

– July 11th : DLMIA’18 paper notification of acceptance

– July 17th : DLMIA’18 Camera-ready version submission

– Workshop Date: TBD (Full Day)

Invited Speakers:

Prof. Hayit Greenspan (Tel Aviv University)

Prof. Alison Noble (University of Oxford) – To be confirmed

Dr. Christopher Semturs (Google Research) – Deep Learning for Retinal Imaging




Gustavo Carneiro, University of Adelaide, Australia

João Manuel R. S. Tavares, Universidade do Porto, Portugal

Andrew P. Bradley, University of Queensland, Australia

João Paulo Papa, Universidade Estadual Paulista, Brazil

Jacinto C. Nascimento, Instituto Superior Tecnico, Portugal

Vasileios Belagiannis, OSRAM, Germany

Zhi Lu, Guangdong University of Technology, China

[visionlist] PhD position: *(deep) learning and Bayesian models of human behavior*

=== PhD position: *(deep) learning and Bayesian models of human behavior* ====

The Department of Psychology at the University of Marburg,
Group of Prof. Dr. Endres, is currently accepting applications for a

Research Assistant (PhD student).

The position is a part of the project C6 (sensorimotor primitives) of the DFG-funded Collaborative
Research Center CRC/TRR 135 “Cardinal Mechanisms of Perception”. More Information on the CRC
can be found at https://ift.tt/1aUKHC2. This CRC is embedded in vibrant
research communities at Marburg and Giessen, inclunding the international research training
group IRTG 1901 ‘The brain in action’, see https://ift.tt/2GZROLk,
and the newly founded ‘Center for Mind, Brain and Behavior’, https://ift.tt/2E7VkA0

Duties include the independent the development, implementation and execution of virtual reality
and real world experiments for the validation of *(deep) learning and Bayesian models of human behavior* and percep-
tion, the development, implementation and analysis of these models, contributions to scientific pub-
lications and regular and active participation in the CRC’s scientific program.

The starting date is as soon as possible. The position is offered until 31.12.2021, if no former times of
qualification must be considered. The position is part-time (65 % of regular working hours) with sala-
ry and benefits commensurate with a public service position in the state Hesse, Germany (TV-H E 13,
65 %).

The position is limited to a time period deemed adequate for the completion of a doctoral degree. As
part of the assigned duties, there will be ample opportunity to conduct the independent scientific
research necessary for the completion of a doctorate. The limitation complies with § 2, 1 WissZeitVG.
Formal requirements are a qualified degree in psychology, cognitive science, computer science,
engineering or physics (Master, Diploma, or comparable) as well as demonstrable programming expe-
rience in a high-level language, e.g. Python or Matlab. We expect you to be interested in the topic of
the project (to be documented in a motivation letter (1 page max), in which you may refer to prior
experiences, for instance, a thematically pertinent thesis, student research assistant positions, etc.),
developing virtual-reality scenarios and technology for research purposes as well as quantitative
modelling. Advantageous qualifications are prior exposure to machine learning, Bayesian statistics,
experience with human behavioral experiments as well as willingness to acquire basic German
language skills. Disposition to own scientific qualification is expected.
Feel free to contact Prof. Dr. Dominik Endres at


for more information.

We actively support the professional development of junior researchers, e.g. by the offers of Mar-
burg Research Academy (MARA), the International Office, the Higher Education Didactics Office and
the Human Resources Development Office.
We support women and strongly encourage them to apply. In areas where women are underrepre-
sented, female applicants will be preferred in case of equal qualifications. Applicants with children
are welcome – Philipps-University is certified as a family-friendly university. Sharing a full-time
position (§ 8 Abs. 2 S. 1 HGlG) as well as a reduction of working time is possible. Applicants with a
disability as described in SGB IX (§ 2 Abs. 2, 3) will be preferred in case of equal qualifications.
Application and interview costs can not be refunded.

Please send your application (including a project-specific motivation letter in English, copies of
relevant diplomas, curriculum vitae and contact details of two potential referees) mentioning
reference no. fb04-0017-wmz-2018 only as a single PDF file to dominik.endres@uni-marburg.de
before April 27th 2018.

The official job advert can be found at

[visionlist] Call for Papers: Vision Research Special Issue “Visual Factors in Reading”


Vision Research Special Issue: Visual Factors in Reading


Reading is a visual task that is essential for full participation in modern society. A major goal of vision research is to understand the visual processing required to read.

Most people rarely think about the complexity of the reading process. We know that our visual system quickly decodes black marks on a page into meaningful words. But how?

The past thirty years have seen a growth of research on the role of vision in reading, including effects of type design, typography, and writing system. These studies address both sensory mechanisms and brain pathways involved in reading, and the impact of visual disorders. At the same time, methods have improved for measuring reading performance and enhancing reading.

The goal of this special issue is to attract papers in this multidisciplinary area of reading, with an emphasis on the interplay between reading and vision. Submissions could include new results from original research, targeted reviews, and interesting viewpoints. The special issue will have a broad scope encompassing experimental, theoretical, computational, and clinical studies, as well as methodological approaches.

Publication Schedule

Submissions Open: Already openedSubmission Deadline: May 31, 2018Acceptance date: December 1, 2018The expected publication date: February – March, 2019

We have already received several submissions, so please do not wait till the deadline.  The earlier you submit, the earlier your work could be accepted for publication.  All accepted work will be assigned a DOI, complete with page numbers, soon after it’s accepted for publication, so that it can be citable right away!

Special Issue Guest Editors

Dr. Susana Chung*Dr. Gordon LeggeDr. Denis PelliDr. Cong Yu

* Managing guest editor

Submission instructions

EES submission link:https://ift.tt/2EpnniT

Authors to select “VSI: Reading” as article type when submitting their special issue paper in EES.

Guide for Authors for more details is https://ift.tt/2BhIv8F

[visionlist] Symposium on Applied Perception in Vancouver, Canada: 3nd Call for Papers and Posters; Abstract deadline April 3rd, Paper deadline April 10th.

Symposium on Applied Perception 3nd Call for Papers and Posters

The ACM Symposium on Applied Perception (ACM SAP) aims to advance and promote research that crosses the boundaries between perception and disciplines such as graphics, visualization, computer vision, haptics, acoustics, and augmented, mixed, and virtual reality. These fields can benefit from the exchange of ideas. The scope of the conference includes applications and algorithms in any area of research that incorporates elements of perception and computer science.

Our fifteenth annual event provides an intimate, immersive forum for exchanging ideas about areas of overlapping interests. The ACM SAP 2018 conference will be held in downtown Vancouver, BC, Canada on the 10th and 11th of August, 2018. We aim to further promote communication between the core perception and computer graphics communities.

We invite submissions of original work in all areas of applied perception. Relevant areas include:

Modeling, rendering, and animation


Computational aesthetics

Haptic rendering, haptic input and perception

Perception of virtual characters

Color vision and color appearance modeling

Perception of high dynamic range scenes and images

Interaction techniques and interfaces

Augmented, mixed, and virtual reality

Virtual worlds

Display technologies

Auditory display and interfaces

Perceptual auditory coding

Spatialized sound

Speech synthesis and recognition

Sensory integration

Multimodal rendering

Spatial and temporal vision

Attention and eye movements

Statistical learning and perception of natural scenes

Perception of shapes, surfaces, and materials

Biosensing including EEG


Research can be submitted as a long paper (up to 8 pages and up to 20 minute talk), a short paper (up to 4 pages and up to 15 minute talk), or as a poster presentation (1 page abstract). All submissions should follow the general SIGGRAPH formatting guidelines. Page limits include all references. Diagrams and images should be represented in color where appropriate. Papers that are not accepted will be considered for the poster session. Authors of posters accepted by this route will, of course, have the option to decline the opportunity to present a poster.


The posters program at SAP provides an informal venue for authors to share their research achievements and further discuss them with others. In that spirit, we encourage all types of scholarly submissions that fit the scope of ACM-SAP. In particular, we explicitly welcome poster submissions on work-in-progress and on work that may have been previously published elsewhere but for which additional dissemination and discussion is desired. The poster session is an integral part of SAP and the SAP program will include a dedicated time slot for poster viewing and discussion. All poster presenters will also have the opportunity to give a one-minute presentation on their work during a poster fast-forward session.

NOTE: SAP poster abstracts are NOT considered to be archival publications, and as such will NOT appear in the ACM Digital Library so should not interfere with future paper publications. Poster abstracts WILL be included in the conference USB drive. Poster abstracts should follow the general SIGGRAPH formatting guidelines, except that they should be 1 page long.

Further details

All papers will be carefully reviewed by our International Program Committee. SAP follows a double blind review process. Papers will be evaluated as submitted, given limited time between submission and printing of final versions. Under a recent agreement with the ACM Transactions on Applied Perception (TAP) and the ACM Publications Board, the strongest accepted papers will be offered publication as full papers in the ACM journal TAP. Authors of such special issue papers must agree to present the paper at ACM SAP. As has always been the case, authors of regular ACM SAP papers can still submit to TAP regular issues with appropriate additions. Papers that have been recommended for acceptance in the ACM TAP journal will undergo a second review cycle, during which the authors will revise the paper to address reviewer concerns (similar to conditional acceptances at ACM SIGGRAPH). Please note that TAP referrals are conditional. The TAP reviewers may recommend bringing the paper back to the SAP proceedings if the quality of the revision is inadequate. Therefore, it is very important to incorporate as many reviewer comments as possible into the revision.

The revised paper has to be submitted in TAP format to Manuscript Central and must include a cover letter stating that the submission is for the SAP special issue. The cover letter should also document the list of changes made to the paper to address the reviewer concerns. Reformatting an 8-page paper from the SAP format to the TAP format typically adds a few pages so we expect the final papers will have somewhere between 10-15 pages. TAP papers must not exceed 20 pages in length. Complete TAP author guidelines and templates are available at https://ift.tt/2mIsPQL.

Conference Organization

Conference Chairs

Cindy Grimm, Oregon State University

Pete Willemsen, University of Minnesota Duluth

Program Chairs

Bernhard Riecke, Simon Fraser University

Joe Kearney, University of Iowa

Poster Chair:

Betsy Sanders, Rhodes College



Tuesday, April 3: Mandatory abstract submission

Tuesday, April 10: Paper submission deadline

Tuesday, May 15: Decisions announced

Tuesday, May 29: Final papers due

Papers recommended for TAP

May 29: Camera-ready revisions to TAP recommended papers due (in TAP format)

June 15: Final review recommendations from second review cycle sent to TAP authors

June 26th: Final revisions due for papers selected for the  TAP Special Issue after second review process


Tuesday, May 29: Poster submission

Tuesday, June 5: Decisions announced

Tuesday, June 12: Camera ready version of 1-page abstract due

[visionlist] Postdoctoral position in Visual Neuroscience, UC Berkeley

I am looking for a postdoctoral researcher to join my team investigating how the visual system adapts to the natural environment. 

The work in my lab spans a number of topics in vision science, for which we employ a combination of human perceptual experiments and computational techniques. More information about our research can be found at my lab website: http://www.

This specific job opening is for a researcher who will join a multi-year, multi-site investigation into the neural processing of natural 3D motion. The project scope includes the design of novel camera/display systems for field work, analysis of motion from natural video, and collaboration with a team of neurobiologists to model and interpret visual circuit responses to natural motion. The researcher will be expected to pursue additional research areas of mutual interest. Strong mathematical, digital imaging, and programming skills are necessary, as well as strong communication skills and a record of research productivity. Applicants must also have finished their Ph.D. in neuroscience, vision science, engineering, computer science, or related fields.

The start date is flexible, preferably in the summer or fall of 2018. Applicants should send a brief statement of interest, CV, and names of three references (letters requested later) to Prof. Emily Cooper (emilycooper@berkeley.edu).