Some slides from the workshop are available, click the respective links to download them.
The Program is available.
The submission site is now open.
Max Planck Institute for Intelligent Systems
University of Edinburgh
John Hopkins University
Adobe Systems Inc.
Irfan Essa/Matthias Grundmann
Georgia Institute of Technology/Google Research
Program 09:00-09:10 Welcome and opening
09:10-09:45 Invited Talk, Efficient hierarchical graph-based video segmentation
Irfan Essa (Georgia Institute of Technology/Google Research)
09:45-10:00 Short talk Video Object Segmentation by Non-Local Consensus Voting
Alon Faktor, Michal Irani (Weizmann Institute of Science)
10:00-10:35 Invited talk, Parametric Figure-Ground Proposals and Second Order Pooling Methods for Semantic Segmentation: RGB, RGB-D and Video
Cristian Sminchisescu (Lund University)
10:35-11:10 Coffee Break and Posters
11:10-11:45 Invited Talk, Interactive segmentation approaches for video production
Jue Wang (Adobe Systems)
11:45-12:00 Short talk, A video representation using temporal superpixels,
J. Chang, D. Wei, and J. W. Fisher (Massachussetts Institute of Technology);
12:00-12:15 Short talk, Video segmentation by tracing discontinuities in a trajectory embedding,
Katerina Fragkiadaki (University of California, Berkeley) and Jianbo Shi (University of Pennsylvannia)
12:15-12:30 Short Talk, Progressive multigrid eigensolvers for multiscale spectral segmentation,
Michael Maire (California Institute of Technology/TTI Chicago) and Stella X. Yu (University of California, Berkeley)
12:30-14:00 Lunch and Posters
14:00-14:35 Invited Talk, Video object segmentation helps learning object class models,
Vittorio Ferrari (University of Edinburgh)
14:35-14:50 Short Talk, temporally consistent superpixels
M. Reso, J. Jachalsky, R. Rosenhahn, J. Ostermann (Leibniz Universität Hannover)
14:50-15:05 Short talk,Online video seeds for temporal window objectness
M. Van Den Bergh, G. Roig, X. Boix, S. Manen, and L. V. Gool (ETH Zürich)
15:05-15:20 Short talk,Motion Words for Videos
E. Taralova, F. de la Torre, M. Hebert (Carnegie Mellon University)
15:20-15:55 Coffee Break and Posters
15:55-16:30 Invited Talk, Semantic (less) Motion and Video Segmentation,
René Vidal (Johns Hopkins University)
16:30-16:40 Surprise Talk from Michael Black
16:40-17:30 Panel Discussions
Paper submission deadline: July 3rd, 2014
Acceptance notification: July 28th, 2014
Workshop date: September 12th, 2014
Authors should use the ECCV style files to prepare your submission. We welcome submissions for:
Regular papers: not more than 10 pages plus references. Regular papers will be lightly reviewed by the workshop organizers and should include the author names (single-blind review) as accepted papers will be directly sent to Springer to be included on the USB stick for ECCV.
For regular papers, there will be two options:
(1) The papers can be part of the post-conference proceedings with Springer. It will be possible to correct and extend the paper after the workshop. Papers will count as a full publication and cannot be submitted to a later venue anymore.
(2) Authors can decide before the post-conference proceedings deadline not to include their paper in the official proceedings. Such papers remain unpublished work and can be submitted to other venues.
Extended abstracts: not more than 2 pages. Extended abstracts may contain papers that have been previously accepted and/or presented at other venues. They will not be part of the proceedings but will be presented as posters if accepted.
All submissions will be handled by the Microsoft CMT system.
Click here to go to the submission website
Call for papers
Interest in the video segmentation problem has grown dramatically in recent years, resulting in a significant recent
body of work along with advances in both methods and datasets. It is time to take stock of the video segmentation
problem and chart the future course of work in this field.
The goal of this workshop is to bring together a broad and representative group of video segmentation researchers
for a lively and impactful discussion on a wide range of topics: What is the difference between video segmentation and the well-studied problem of image
segmentation? What are the commonalities and differences among the many different definitions
of the video segmentation problem, and what terminology should we use to distinguish them? What is the best
way to measure performance and what are the best practices and tools for video annotation? What is the state of existing standard
datasets and how can they be improved? How should segmentations be represented and what are the consequences for
The workshop will consists of a combination of invited talks, poster presentations of submitted works and
panel discussions. Paper submissions should include author names and affiliations, and will be subject to single-blind review by the organizers, based on the quality of the work and its relevance to the
workshop topic. Authors of accepted papers will have the option to submit a full paper for inclusion in the workshop
post-proceedings (camera-ready papers submitted after the workshop) if they choose.
Topics of interest include:
- Video segmentation algorithms and their performance analysis, including novel optimization techniques
- Comparisons between image and video segmentation techniques
- Proposals of taxonomies and terminologies for video segmentation, including the discussion of annotations and
- Novel datasets for performance evaluation and/or empirical analyses of existing methods
- Semantic labeling in video segmentation
- Supervised and unsupervised methods, as well as techniques for interactive segmentation
- Motion Segmentation
- Segmentation of videos with depth information, such as in RGB-D videos
- Applications of video segmentation to topics such as event recognition, activity detection, and object recognition