**Perception and Understanding of Urban Driving Scenes**One-year position starting on September 1st, 2014 – CNRS / University of Technology of Compiegne, France.
**Project description**Depending on his/her abilities and interests, the post-doctoral fellow will be involved in at least one of the following actions:1 – Real-time perception for intelligent road vehicles in dynamic urban environments by fusing multimodal sensing with prior knowledge (e.g. geo-referenced maps). This action includes SLAM with moving object detection and tracking, etc.
2 – Offline reasoning and scene understanding from sensing with uncertainty and contextual information. This action includes pixel-wise object class segmentation, learning of semantic models of the driving scene and human activities, such as categorization of simple behaviors, interaction patterns among dynamic objects or between the dynamic ones and infrastructure.
3 – Test-bed integration, experiments and evaluations. This action includes integration of core algorithms in a test-bed vehicle and evaluations on real-world data. **Context** http://ift.tt/1rk8Us9
The post-doctoral fellow will be based in Heudiasyc laboratory in Compiegne (50 minutes north of Paris, in the Oise department) and join the ASER or DI teams headed respectively by Philippe Bonnifait and Yves Grandvalet. Heudiasyc is a joint laboratory with the University of Technology of Compiegne and the French governmental agency for research, CNRS. In 2011, it was rated A+ (the highest rate) by the French Research evaluation agency. Heudiasyc fosters interdisciplinary research on information sciences and technology including machine learning, uncertain reasoning, networking, optimization, robotics (including intelligent vehicles) and knowledge management. It has strong and direct research partnerships with the two French carmakers, in the domain of autonomous vehicles. In 2011 Heudiasyc was awarded with an Excellence Lab (LabEx) from the Ministry, on the « Control of Technological Systems of Systems ».
The one-year fellowship is funded through an ANR/NSFC Sino-French project with Peking University in China, and will start on September 1st, 2014 (~ 2500 euros per month, gross salary, CNRS). **Requirements**The candidate should have a PhD or equivalent in computer science or applied mathematics. The following qualities are desirable: strong interests in computer vision, machine learning, multi-sensor data fusion, target tracking or embedded systems; excellent record of academic and/or professional achievement; strong programming skills; good written and spoken communication skills in English. **Contact and application**Applicants should send (preferably as a single PDF file):* a CV* a brief statement of research interests* references (with email and phone number)* a sample of strongest publicationsContact persons: Franck.DAVOINE@hds.utc.fr and Vincent.FREMONT@hds.utc.fr
The Center for Visual
the University of Rochester is seeking a programmer to develop
vision research. The position involves working with faculty,
fellows, and graduate students on the development of novel and
applications to study visual information processing in the eye
and brain (for
example, see http://ift.tt/1kLHJ4u). An
would have familiarity with both Macintosh and PC operating
graphics (ideally OpenGL), Matlab, C++, and hardware/software
real-time control of data acquisition. The successful candidate
considerable independence, working in a vigorous and exciting
commensurate with experience. Please send applications or
queries about the
position to Debbie Shannon. (firstname.lastname@example.org).
[visionlist] Bernstein Workshop “Characterizing Natural Scenes”: Second Call for Abstracts/Contributed TalksPosted: May 28, 2014
Second Call for Abstracts/Contributed Talks
You are invited to participate in the pre-conference Bernstein workshop
“Characterizing Natural Scenes: Retinal Coding and Statistical Theory”,
taking place in Göttingen, Germany, on September 2-3, 2014. Please find
the preliminary schedule at workshop URL:
The workshop chairs will select a couple of abstracts for short oral
presentation at the workshop. All the abstracts will be presented as
posters during the Bernstein conference on September 3-4. However, the
workshop could hold a separate poster session based on the number and
quality of abstracts that we receive.
To participate in the workshop please submit the abstract (an extended
version is preferred) as a PDF attachment via email to Jian Liu
(email@example.com) or Arno Onken (firstname.lastname@example.org). The
deadline for submission is August 1.
Please note that abstract submission for the main conference is already
closed while abstract submission for this workshop is still open.
Please refer to the Bernstein Conference 2014 for registration and venue
How does the retina process natural visual inputs? What role do the many
types of retinal ganglion cells (RGCs) play in this? Experiments with
specific artificial stimuli have suggested that individual types of RGCs
may have specific functional roles in visual processing, yet it is not
clear how these simplified functional investigations relate to the
processing of natural images and movies. An important ingredient for
future analysis will be a better understanding of the complex
statistical properties of natural scenes, as revealed by theoreticians.
The relationship between natural visual statistics and retinal coding
provides a promising direction for improving our understanding of the
visual system. But we still lack a systematic framework for
understanding the underlying mechanisms of how relevant features of
natural scenes are encoded by the retina.
In this workshop, we expect mutual benefits for both natural scene
statistics and retinal coding. We will bring together experimentalists
and theoreticians in order to highlight recent progress, encourage
exchange of insights, and stimulate new ideas for future work with the
following core questions:
1) How can we develop useful descriptions of the statistics of natural
scenes that are relevant for retinal coding?
2) How can we characterize the functional roles of different RGC types
in processing natural scenes?
3) Which coding strategies are present at the level of RGC populations?
4) How can we unify the acquired knowledge of natural scenes and neural
data to develop better tools for analysis?
* Vijay Balasubramanian (University of Pennsylvania)
* Philipp Berens (BCCN, Tübingen)
* Thomas Euler (University of Tübingen)
* Felix Franke (ETH Zurich)
* Olivier Marre (Vision Institute, Paris)
* Aman Saleem (University College London)
* Maneesh Sahani (University College London)
* Rava A. da Silveira (ENS, Paris)
We are looking forward to seeing you in Göttingen.
Jian Liu (University Medical Center Göttingen and BCCN Göttingen)
Arno Onken (Center for Neuroscience and Cognitive Systems