Brave new ideas for motion representations in videos II, CVPR 2017

CVPR 2017, Honolulu, Hawaii – 21st July 2017

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.

Visit here forĀ full details of the workshop

Author - Robotic Vision

Robotic Vision

The ARC Centre of Excellence for Robotic Vision is leading the world in transformational research tackling the critical and complex challenge of applying computer vision to robotics. We believe that the ability to see, to visually understand the complex world around us and respond to it, is critical for the next generation of robots that will perform useful work in agriculture, environmental monitoring, healthcare, infrastructure inspection, construction and manufacturing. We believe that robotic vision is the key to unleashing the full potential of robots and fundamentally changing the way we live and work. Link

Category: Conferences/Workshops
Posted 31 May 2017


Australian Centre for Robotic Vision
2 George Street Brisbane, 4001
+61 7 3138 7549