ECCV'16 Workshop on:
Brave new ideas for motion representations in videos
Together with the European Conference on Computer Vision (ECCV) 2016, Amsterdam.
Big thank to everyone who attended the very successful workshop.
Description of the workshop and its relevance
In the late years Deep Learning has been a great force of change on most computer vision tasks. In video analysis problems, however, such as action recognition and detection, motion analysis and tracking, shallow architectures remain surprisingly competitive. What is the reason for this conundrum? Larger datasets are part of the solution. The recently proposed Sports1M helped recently in the realistic training of large motion networks. Still, the breakthrough has not yet arrived.
Assuming that the recently proposed video datasets are large enough for training deep networks for video, another likely culprit for the standstill in video analysis is the capacity of the existing deep models. More specifically, the existing deep networks for video analysis might not be sophisticated enough to address the complexity of motion information. This makes sense, as videos introduce an exponential complexity as compared to static images. Unfortunately, state-of-the-art motion representation models are extensions of existing image representations rather than motion dedicated ones. Brave, new and motion-specific representations are likely to be needed for a breakthrough in video analysis.
Calling papers for brave new ideas
Attempting to publish a wild, but intriguing idea can be daunting, resulting in slow progress. On one hand a controversial new idea might be rejected by top-tier conferences, without the right experimental justification. On the other hand, researchers may not want to reveal a smart idea too soon in the fear of not receiving the right credit. To make amends with these two factors, the workshop will admit maximum 4-page papers describing novel, previously unseen ideas without necessarily requiring exhaustive quantitative justifications. Moreover, to make sure proper accreditation is given in the future, the workshop will have an open-review process, where all submitted papers should first be uploaded to arXiv.
Expert speakers
To kickstart the discussion we have confirmed speakers from different fields that relate to the understanding and modelling of motion and sequence data: Computer Vision (Ivan Laptev), Machine Learning (Max Welling), Neuro-Science (Aman Saleem).
Topics
The workshop focuses on motion representations related, but not limited, to the following topics:
- Influence of motion in object recognition, object affordance, scene understanding.
- Object and optical flow
- Motion prediction, causal reasoning and forecasting
- Event and action recognition
- Spatio-temporal action localization
- Modeling human motion in videos and video streams
- Motion segmentation and saliency
- Tracking of objects in space and time
- Unsupervised action, actom discovery using ego motion
- Applications of motion understanding and video dynamics in sports, healthcare, autonomous driving, driver assistance and robotics
