[visionlist] BMVC 2016 Final Call for Papers (Deadline Extension)

BMVC 2016 Final Call for Papers (Deadline Extension)

27th British Machine Vision Conference

19-22 September 2016, York, UK


The British Machine Vision Conference (BMVC) is one of the major international conferences on computer vision and related areas. It is organised by the British Machine Vision Association (BMVA).The 27th BMVC will be held at the University of York, 19th-22nd September 2016. The university is set on the outskirts of the historic walled city of York which features Roman and Viking history and is home to a number of world renowned tourist attractions ranging from the gothic cathedral York Minster to the National Railway Museum.BMVC 2016 is a high quality single-track conference, comprising oral presentations and poster sessions (with oral acceptance <10% in the last 6 years). The conference features two keynote presentations and a conference tutorial, and has associated workshops on the last day of the conference, including a PhD student workshop.

Authors are invited to submit full-length high-quality papers in image processing and machine vision. Papers covering theory and/or application areas of computer vision are invited for submission. Submitted papers will be refereed on their originality, presentation, empirical results, and quality of evaluation. All papers will be reviewed *doubly blind*, normally by three members of our international programme committee.Topics include, but are not limited to:

• Statistics and machine learning for vision

• Stereo, calibration, geometric modelling and processing

• Face and gesture recognition

• Early and biologically inspired vision

• Motion, flow and tracking

• Segmentation and grouping

• Model-based vision

• Image processing techniques and methods

• Texture, shape and colour

• Video analysis

• Document processing and recognition

• Vision for quality assurance, medical diagnosis, etc.

• Vision for visualization, interaction, and graphics

• Object detection and recognition

• Shape-from-X

• Video analysis and event recognition

• Illumination and reflectance

Accepted papers will be included the conference proceedings published and DOI indexed by BMVA.


Submission instructions, paper templates and other details are available on the conference website: http://ift.tt/1NFn396

Paper submission is via CMT at: http://ift.tt/21yx8vM


The submission deadline has been extended to 13th May. Please note that the new deadline is firm. There will be no further extension.

Submission deadline (EXTENDED): 13th May 2016 (11.59pm, Pacific time)

Author notification: 15th July 2016

Camera ready deadline (including 1 page abstract): 29th July

Conference tutorial: Monday 19th September 2016

Main conference: Tuesday 20th – Thursday 22nd September 2016

JOURNAL SPECIAL ISSUE A selection of the best papers will appear in a special edition of the International Journal of Computer Vision (IJCV).


Katsushi IkeuchiUniversity of Tokyo Raquel UrtasunUniversity of Toronto


Abhijeet GhoshImperial College, LondonTopic: Measurement Based Appearance Modelling

[visionlist] Postdoctoral Research Position in retinal neurophysiology

[visionlist] [CFP] Emotion Recognition in the Wild challenge 2016

Apologies for cross-postingsCall for challenge participationFourth Emotion Recognition in the Wild (EmotiW) Challenge 2016https://sites.google.com/site/emotiw2016/@ ACM International Conference on Multimodal Interaction 2016, Tokyo

[visionlist] Postdoctoral position at UCSD

A postdoctoral
position is available in the Vision and Memory Lab of Dr. Timothy Brady (http://ift.tt/1rj7UXg). The lab is based in the UC San Diego Department of Psychology. Initial appointment is for one year, with
flexible start date and opportunity for renewal.


The lab’s research
lies at the intersection of visual cognition and memory. Particular research
topics include the nature of visual working memory capacity, the format of
visual long-term memory representations, and the relationship between ensemble
statistics and scene recognition. We use a variety of methodologies in the
lab, including psychophysics, computational modeling (connectionist, Bayesian, and information theoretic) and EEG.


We are seeking
highly qualified individuals with a recent or soon-to-be-acquired Ph.D. in a
relevant field (e.g., Psychology, Neuroscience, Cognitive Science, Computer
Science), strong quantitative and technical skills, and interests in visual
cognition, visual perception and/or memory. Experience with computational
modeling and/or EEG is desirable. Proficiency in programming is
necessary (e.g. Matlab, Python, Javascript, or R). 


candidates should send a CV, a brief statement of research interests, the
expected date of availability, and the names and contact info of at least two
references to timbrady@ucsd.edu.


Salary is based on
research experience. UCSD is an equal
opportunity employer and all qualified applicants will receive consideration
for employment without regard to race, religion, color, national origin, sex,
sexual orientation, gender identity, age, status as a protected veteran, or
status as a qualified individual with a disability.  

[visionlist] 3 Fully Funded PhD Positions at the Cognitive Robotics and Interaction Lab of the Robotics, Brain and Cognitive Sciences Department at the Italian Institute of Technology

Apologies for cross-posting

PhD Openings at the Cognitive Robotics and Interaction Lab Robotics, Brain
and Cognitive Sciences Department Italian Institute of Technology

In the spirit of the doctoral School on Bioengineering and Robotics the PhD
Program for the curriculum “Cognitive Robotics, Interaction and
Rehabilitation Technologies” offers interdisciplinary training at the
interface between technology and life-sciences. The objective of the PhD
program is to form scientists and research technologists capable of working
in multidisciplinary teams on projects where human factors play a crucial
role in technological development and design.  Robotics and neuroscience
researchers in RBCS share, as a fundamental scientific objective, the study
of physical and social interaction in humans and machines (www.iit.it/rbcs

Among the different research themes proposed I would like to advertise these
three topics:



The ideal candidates are students with a higher level university degree
willing to invest extra time and effort in blending into a multidisciplinary
team composed of neuroscientists, engineers, psychologists, physicists
working together to investigate brain functions and realize intelligent
machines, rehabilitation protocols and advanced prosthesis.

The successful candidate will also have the opportunity to spend part of
his/her PhD at the Osaka University and the University of Tokyo in the
framework of the Marie Curie IRSES project CODEFROR (www.codefror.eu) , with
the purpose of integrating his/her knowledge with the different expertise
available at these institutes.

International applications are encouraged and will receive logistic support
with visa issues, relocation, etc.

Below you can find more details related to the position and the instructions
on how to apply.

Application deadline: *****10 June 2016, Noon,  Italian time*****

Best regards,
Alessandra Sciutti

[visionlist] Fwd: CfP for ICML 2016 Workshop on Anomaly Detection




ICML 2016 Anomaly Detection Workshop

Date: June 24th, 2016

Location: New York, USA

Website: http://ift.tt/23qJ8SJ

Important dates:

Submission deadline: May 1st, 2016.

Acceptance decisions: May 10th, 2016.



Anomaly, outlier and novelty detection methods are crucial tools in any data scientist’s inventory and are critical components of many real-world applications. Abnormal user activities can be used to detect credit card fraud, network intrusions or other security breaches. In computational biology, characterization of systematic anomalies in gene expression can be translated into clinically relevant information. With the rise of Internet-of-Things, the task of monitoring and diagnostics of numerous autonomous systems becomes intractable for a human and needs to be outsources to a machine. Early detection of an upcoming earthquake or tsunami can potentially save human lives. These applications make anomaly detection methods increasingly relevant in the modern world.

However, with the advent of Big Data, new challenges and questions are introduced, which will need to be addressed by the next generation of the anomaly and outlier detection algorithms. The goal of our workshop is to survey the existing techniques and discuss new research directions in this area:

1. How can one detect anomalies in streaming data?

2. How to address non-stationarity in data when the data distribution (and anomalies) is changing with time?

3. How to detect anomalies as early as possible?

4. How to perform “structured anomaly detection”? I.e., how to detect anomalies that are sequences, trees, graphs, or in general, data that violates the IID assumptions?

5. Can weakly labeled or partially labeled data help? If so, then how do we take advantage of this labeled data?

6. How can we deal with huge data sizes?

7. Can we learn meaningful data representations for anomaly detection?

8. How can we accurately evaluate performance in settings with strongly unbalanced datasets or positive (and unlabeled) examples only?

9. Can we perform “significant anomaly detection” (e.g., using p-values)?

10. What is an “anomaly”? How does it compare to outliers, novelties and the like and can they be tackled with the same methodologies?

11. How can we explain decisions of anomaly detectors to guide human experts?

Submission instructions:

We solicit submission of research papers in the area of anomaly, outlier and novelty detection with the focus on the topics outlined above. Relevant papers that have been recently published or presented elsewhere are allowed, provided that previous publications are explicitly acknowledged. Submission must adhere to ICML 2016 style format and max. 4 pages long, including figures (+additional fifth page containing cited references, supplementary material can be provided). As the review process is not blind authors may reveal their identity during submission process. Please submit your manuscripts to icml2016ad@gmail.com.

All accepted papers will have a poster presentation and the best papers will be selected for an oral presentation.

Invited speakers:

 Leman Akoglu, Stony Brook University

 Thomas Dietterich, Oregon State University

 Klaus-Robert Mueller, Berlin Institute of Technology

 Clayton Scott, University of Michigan

 Bernhard Schoelkopf*, Max Planck Institute for Intelligent Systems

 * tentative


 Nico Goernitz (Berlin Institute of Technology)

 Marius Kloft (Humboldt University of Berlin)

 Vitaly Kuznetsov (Courant Institute)

[visionlist] VSS 2016 | Ken Nakayama Medal for Excellence Recipient Announced

[visionlist] CFP – Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV), ECCV 2016

## Call for Papers ##
ECCV workshop on Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV) 2016
Amsterdam, the Netherlands during 8-16 October, 2016

Workshop site: http://ift.tt/1WRW2HT

Important Dates
Submission deadline: June 15th, 2016
Author notification: July 18th, 2016
Camera-ready due: July 25th, 2016
Workshop date: TBD (During 8-16 October)

This workshop aims at bringing together computer vision and multimedia researchers interested in domain adaptation and knowledge transfer techniques, which are receiving increasing attention in computer vision and multimedia research.

During the first decade of the XXI century, progress in machine learning has had an enormous impact in computer vision. The ability to learn models from data has been a fundamental paradigm in image classification, object detection, semantic segmentation or tracking.
A key ingredient of such a success has been the availability of visual data with annotations, both for training and testing, and well-established protocols for evaluating the results.

However, most of the time, annotating visual information is a tiresome human activity prone to errors. This represents a limitation for addressing new tasks and/or operating in new domains. In order to scale to such situations, it is worth finding mechanisms to reuse the available annotations or the models learned from them.

This also challenges the traditional machine learning theory, which usually assumes that there are sufficient labeled data of each task, and the training data distribution matches the test distribution.

Therefore, transferring and adapting source knowledge (in the form of annotated data or learned models) to perform new tasks and/or operating in new domains has recently emerged as a challenge to develop computer vision methods that are reliable across domains and tasks.

Besides, transfer learning has also gained interests from the multimedia community in many applications, such as video concept detection, image/video retrieval, and socialized video recommendation.
The workshops in previous years can be found via the links, http://ift.tt/1Qzj7rd, and http://ift.tt/1WRW02w.

TASK-CV aims to bring together research in transfer learning and domain adaptation for computer vision as a workshop hosted by the ECCV 2016. We invite the submission of research contributions such as:
•TL/DA learning methods for challenging paradigms like unsupervised, and incremental or on-line learning.
•TL/DA focusing on specific visual features, models or learning algorithms.
•TL/DA jointly applied with other learning paradigms such as reinforcement learning.
•TL/DA in the era of deep neural networks (e.g., CNNs), adaptation effects of fine-tuning, regularization techniques, transfer of architectures and weights, etc.
•TL/DA focusing on specific computer vision tasks (e.g., image classification, object detection, semantic segmentation, recognition, retrieval, tracking, etc.) and applications (biomedical, robotics, multimedia, autonomous driving, etc.).
•Comparative studies of different TL/DA methods.
•Working frameworks with appropriate CV-oriented datasets and evaluation protocols to assess TL/DA methods.
•Transferring knowledge across modalities (e.g., learning from 3D data for recognizing 2D data, and heterogeneous transfer learning)
•Transferring part representations between categories.
•Transferring tasks to new domains.
•Solving domain shift due to sensor differences (e.g., low-vs-high resolution, power spectrum sensitivity) and compression schemes.
•Datasets and protocols for evaluating TL/DA methods.
This is not a closed list; thus, we welcome other interesting and relevant research for TASK-CV.

Best Paper Award
As in previous workshops, we are going to award 1-2 best papers of this year’s workshop, subject to the availability of sponsors. Details will be provided in the workshop site.

•All submissions will be handled via the CMT website http://ift.tt/1Qzj7rf.
•The format of the papers is the same as the ECCV main conference. The contributions will consist in Extended Abstracts (EA) of 6 pages (excluding the references).
•Submissions will be rejected without review if they: exceed the page limitation or violate the double-blind policy.
•Manuscript templates can be found at the main conference website: http://ift.tt/1TgxSUf
•The accepted papers will be linked in the TASK-CV webpage.

Workshop Chairs
•Wen Li, ETH Zurich, Switzerland
•Tatiana Tommasi, University of North Carolina at Chapel Hill, NC, USA
•Francesco Orabona, Yahoo Research, NY, USA.
•David Vázquez, Computer Vision Center & U. Autònoma de Barcelona, Spain.
•Antonio M. López, Computer Vision Center & U. Autònoma de Barcelona, Spain.
•Jiaolong Xu, Computer Vision Center & U. Autònoma de Barcelona, Spain.
•Hugo Larochelle, Twitter Cortex, USA.

[visionlist] Postdoc opportunity at FDA

[visionlist] Postdoctoral Opportunity in Adaptive Optics Ophthalmoscopy at UC Berkeley

Postdoctoral Research Opportunity at the University of California, Berkeley


We are looking for a capable and innovative postdoc to be part of a team in Austin Roorda’s lab at UC Berkeley to develop and use advanced scanning laser ophthalmoscopy and optical-coherence-gated imaging systems with adaptive optics and high speed eye tracking. We have two NIH-funded projects: one involves the development and use of a system for advanced vision testing (eg. single-cone psychophysics) and the second involves the development a novel system for optically recording from individual retinal neurons in vivo. 

We are pioneers in the development and use of advanced optical systems for imaging the retina and measuring visual function on a cellular scale. The systems are used for a wide range of applications, from monitoring the efficacy of treatments to slow eye disease to elucidating the circuits in the retina that underlie human spatial and color vision. For more details on Austin Roorda’s lab, link to http://ift.tt/1TbWgE6


Required Qualifications

Minimum of a PhD degree

Demonstrated experience with complete systems, including optics, electronics, hardware and software

Preferred Qualifications

Programming skills, especially FPGA programming

Experience with OCT systems, expecially phase-reolved

Experience with adaptive optics, eye tracking, ophthalmic imaging and scanning laser imaging systems

Scientific and/or technical publication record

Effective written and verbal communication skills

Why Berkeley?

The Vision Science Group at Berkeley (http://ift.tt/1RrNK7D) is a group of over 40 PhD students, 20 postdocs, and over 30 faculty in a wide range of disciplines spanning the entire campus. The University of California, Berkeley (http://ift.tt/eS3uZp) is one of the world’s most iconic teaching and research institutions. Since 1868, Berkeley has fueled a perpetual renaissance, generating unparalleled intellectual, economic and social value in California, the United States and the world. Berkeley’s culture of openness, freedom and acceptance—academic and artistic, political and cultural—make it a very special place for students, faculty and staff.  


Salary & Benefits

Salary is commensurate with experience.

Health, dental and vision care benefits are offered as per guidelines listed here: http://ift.tt/1RrNK7F


How to Apply

Please submit a cover letter, a full CV, and names and contact information for at least three possible reference letter writers to Peter Illes (email: peter.illes@berkeley.edu).

and Austin Roorda (aroorda@berkeley.edu). Inquiries about the position can be made directly to Austin Roorda (email: aroorda@berkeley.edu )


Equal Employment Opportunity

The University of California is an Equal Opportunity/Affirmative Action Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or protected veteran status. For the complete University of California nondiscrimination and affirmative action policy see:http://ift.tt/1ZeCOfc you’d like more information about your EEO rights as an applicant under the law, please see:  http://ift.tt/1oONeAT