<div dir="ltr"><a href="https://sites.google.com/site/bigvision2014cvpr/" target="_blank" style="font-family:arial,sans-serif;font-size:12.800000190734863px">https://sites.google.com/site/bigvision2014cvpr/</a><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">The goal of this workshop is providing a venue for researchers interested in large-scale vision to present new work, exchange ideas, and build connections. The workshop will feature keynotes and invited talks from prominent researchers as well as a poster session that fosters in depth discussion.</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">We invite submissions of extended abstracts related to the following topics in the context of big data and large-scale vision:</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">Indexing algorithms and data structures</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">Weakly supervised or unsupervised learning</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">Never ending / continuous learning</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">Metric learning</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">Visual models and feature representations</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">Transfer learning and domain adaptation</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">Systems and infrastructure</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">Visual data mining and knowledge discovery</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">Dataset issues (e.g. dataset collection and dataset biases)</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">Efficient learning and inference techniques</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">Optimization techniques</span><br style="font-family:arial,sans-serif;font-size:12.800000190734863px">
<br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><br style="font-family:arial,sans-serif;font-size:12.800000190734863px"><span style="font-family:arial,sans-serif;font-size:12.800000190734863px">The abstracts should be no more than 2 pages in CVPR 2014 format. Accepted abstracts will be presented as posters or oral talks. The workshop is not intended as a venue for publication and no proceedings will be produced. All submissions will undergo double-blind reviews. In the case of previous published work, the review will be single-blind.</span><br>
<div><span style="font-family:arial,sans-serif;font-size:12.800000190734863px"><br></span></div></div>