Location
Please note that the workshops are at TU München at Arcisstraße 21 Room 1200 (Carl-von-Linde Hörsaal). To get there, enter the building with registration that is facing Arcisstraße (the first building), go upstairs through the stairs, and turn right. After going past some office buildings there will be a sign towards 1200 Carl-von-Linde Hörsaal, follow the sign.
Schedule
08:40-08:45 Introduction
08:45-09:15 Invited Talk, Learning to segment moving objects.
             
Cordelia Schmid (INRIA)
09:15-09:30 Invited short talk
Two years of DAVIS: what we've learnt and what's next in video object segmentation
             
Jordi Pont-Tuset (Google Research)
09:30-10:00 Invited talk: Bayesian Inference in the Age of Deep Learning
              Daniel Cremers (Technische Universitat Munchen)
10:00-10:15 Short talk, Video Object Segmentation with Referring Expressions
              Anna Khoreva (MPI Informatics), Anna Rohrbach (UC Berkeley), Bernt Schiele (MPI Informatics)
10:15 - 10:45 Coffee break
10:45-11:15 Invited Talk
Video Segmentation with less Supervision
             
Bernt Schiele (MPI Informatics)
11:15 - 11:30 Short talk, Fast Semantic Segmentation on Video Using Motion
              Samvit Jain and Joseph Gonzalez (UC Berkeley)
11:30-12:00 Invited Talk: What is video segmentation for?
              Vladlen Koltun (Intel Research)
12:00 - 12:30 Panel Discussions
Co-located with the workshop YouTube-VOS: A Large-Scale Benchmark for Video Object Segmentation which includes a fascinating challenge of video segmentation on 4000+ videos! Our workshop will be in the morning, which will contain invited talks, paper presentations and a panel discussion, while their workshop will be in the afternoon located at the same room.
Invited Speakers
Daniel Cremers received Bachelor degrees in Mathematics (1994) and Physics (1994), and a Master's degree in Theoretical Physics (1997) from the University of Heidelberg. In 2002 he obtained a PhD in Computer Science from the University of Mannheim, Germany. Subsequently he spent two years as a postdoctoral researcher at the University of California at Los Angeles (UCLA) and one year as a permanent researcher at Siemens Corporate Research in Princeton, NJ. From 2005 until 2009 he was associate professor at the University of Bonn, Germany. Since 2009 he holds the chair for Computer Vision and Pattern Recognition at the Technical University, Munich. His publications received several awards, including the 'Best Paper of the Year 2003' (Int. Pattern Recognition Society), the 'Olympus Award 2004' (German Soc. for Pattern Recognition) and the '2005 UCLA Chancellor's Award for Postdoctoral Research'. For pioneering research he received a Starting Grant (2009), a Proof of Concept Grant (2014) and a Consolidator Grant (2015) by the European Research Council. Professor Cremers has served as associate editor for several journals including the International Journal of Computer Vision, the IEEE Transactions on Pattern Analysis and Machine Intelligence and the SIAM Journal of Imaging Sciences. He has served as area chair (associate editor) for ICCV, ECCV, CVPR, ACCV, IROS, etc, and as program chair for ACCV 2014. He serves as general chair for the European Conference on Computer Vision 2018 in Munich. In December 2010 he was listed among “Germany's top 40 researchers below 40” (Capital). On March 1st 2016, Prof. Cremers received the Gottfried Wilhelm Leibniz Award, the biggest award in German academia. He is Managing Director of the TUM Department of Informatics. According to Google Scholar, Prof. Cremers has an h-index of 74 and his papers have been cited 22283 times.
Vladlen Koltun is a Senior Principal Researcher and the director of the
Intelligent Systems Lab at Intel. His lab conducts high-impact basic
research on intelligent systems. Vladlen received a PhD in 2002 for new
results in theoretical computational geometry, spent three years at UC
Berkeley as a postdoc in the theory group, and joined the Stanford Computer
Science faculty in 2005 as a theoretician. He joined Intel in 2015 to
establish a new lab devoted to basic research.
Bernt Schiele is Max-Planck-Director at MPI Informatics and Professor at Saarland University since 2010.
He studied computer science at the University of Karlsruhe, Germany. He worked on his master thesis in the field of robotics in Grenoble, France, where he also obtained the "diplome d'etudes approfondies d'informatique". In 1994 he worked in the field of multi-modal human-computer interfaces at Carnegie Mellon University, Pittsburgh, PA, USA in the group of Alex Waibel. In 1997 he obtained his PhD from INP Grenoble, France under the supervision of Prof. James L. Crowley in the field of computer vision. The title of his thesis was "Object Recognition using Multidimensional Receptive Field Histograms". Between 1997 and 2000 he was postdoctoral associate and Visiting Assistant Professor with the group of Prof. Alex Pentland at the Media Laboratory of the Massachusetts Institute of Technology, Cambridge, MA, USA. From 1999 until 2004 he was Assistant Professor at the Swiss Federal Institute of Technology in Zurich (ETH Zurich). Between 2004 and 2010 he was Full Professor at the computer science department of TU Darmstadt.
Cordelia Schmid holds a M.S. degree in Computer Science from the University of Karlsruhe and a Doctorate, also in Computer Science, from the Institut National Polytechnique de Grenoble (INPG). Her doctoral thesis on "Local Greyvalue Invariants for Image Matching and Retrieval" received the best thesis award from INPG in 1996. She received the Habilitation degree in 2001 for her thesis entitled "From Image Matching to Learning Visual Models". Dr. Schmid was a post-doctoral research assistant in the Robotics Research Group of Oxford University in 1996--1997. Since 1997 she has held a permanent research position at INRIA Rhone-Alpes, where she is a research director and directs an INRIA team. Dr. Schmid is the author of over a hundred technical publications. She has been an Associate Editor for IEEE PAMI (2001--2005) and for IJCV (2004--2012), editor-in-chief for IJCV (2013---), a program chair of IEEE CVPR 2005 and ECCV 2012 as well as a general chair of IEEE CVPR 2015. In 2006, 2014 and 2016, she was awarded the Longuet-Higgins prize for fundamental contributions in computer vision that have withstood the test of time. She is a fellow of IEEE. She was awarded an ERC advanced grant in 2013, the Humbolt research award in 2015 and the Inria & French Academy of Science Grand Prix in 2016. She was elected to the German National Academy of Sciences, Leopoldina, in 2017.
Important Dates
Paper submission deadline: July 6th, 2018
Acceptance notification: August 3rd, 2018
Camera-ready Paper deadline: August 24th, 2018 September 30th, 2018
Workshop date: September 14th, 2018
Submission
Authors should use the ECCV style files to prepare your submission. We welcome submissions for papers no more than 14 pages (excluding references). Regular papers will be lightly reviewed and should include the author names and affiliations (single-blind review).
The papers will be part of the conference proceedings with Springer. A camera-ready paper will need to be submitted by August 24thi September 30th. Note now most computer vision conferences have the policy that papers more than 4 pages (including references) will count as a full publication and cannot be resubmitted to another conference. The authors have the choice of limiting their papers to 4 pages themselves but cannot change the style files for that.
Submissions should be sent through the Microsoft CMT website .
Call for papers
Video understanding is one of the main open problems in computer vision: deep learning has resulted in dramatic progress in image understanding, but video still poses unresolved challenges. Video segmentation can address several of these challenges related to learning, representation, and computation, while at the same time leading to direct applications such as detection, tracking, and activity recognition.
After two very successful editions at ECCV'14 and ECCV'16, we would organize a Third Workshop on Video Segmentation at ECCV 2018, dedicated this time to the interface between deep learning and video segmentation and specifically to learning deep object, scene, and video representations. There has been significant progress in these topics over the last two years, powered by the development of better models, the availability of larger and more challenging datasets, and the increasing interest of the computer vision community.
This workshop would bring together researchers in the field, gather lessons learned, foster the exchange of new ideas, and envision novel research directions. The workshop is aimed at providing a space in which both influential researchers in the field and a large audience can interact freely and discuss a wide range of key topics in video segmentation.
Topics of interest include:
- The role of video segmentation in learning for recognition
- Using video segmentation to provide feedback for recognition and reconstruction models
- Deep learning based video segmentation techniques
- Comparisons of deep learning approaches in image and video segmentation
- Novel datasets for performance evaluation and/or empirical analyses of existing methods
- Supervised, semi-supervised and unsupervised methods, as well as techniques for interactive segmentation
- Video segmentation algorithms and their performance analysis, including novel optimization techniques
- Semantic video segmentation and semantic labeling
- Motion Segmentation
- Segmentation of videos with depth information, such as in RGB-D videos
- Other applications of video segmentation, incl. activity detection and recognition,
compression and representation