Welcome to the CALVIN research group homepage. We are part of the IPAB institute of the University of Edinburgh.
We research several topics related to learning in computer vision.
Our current focus is on weakly supervised learning of object classes, semantic segmentation, and large-scale auto-annotation.
- One post-doc position on visual learning. Email Vittorio Ferrari with your CV and publication list to apply.
- One PhD positions on learning from video, co-supervised with Cordelia Schmid at INRIA Grenoble. See here for more details and how to apply.
- Vittorio Ferrari's invited talk at Google
- One paper accepted to CVPR 2013. The camera-ready version is available online.
- Results for our ECCV 2012 paper on segmentation propagation in ImageNet released.
- Sequences of hyphotheses generated by our NIPS 2012 technique on Pascal VOC 2010 released.
- One paper accepted as a spotlight oral to NIPS 2012. Searching for objects driven by context.
- One paper accepted to ACCV 2012. Appearance Sharing for Collective Human Pose Estimation
- Best Paper Award at ECCV 2012 for our paper Segmentation Propagation in ImageNet.
- Matthieu Guillaumin received Outstanding Reviewer awards at both BMVC 2012 and ECCV 2012.
- Results for our CVPR 2012 paper on knowledge transfer for object localization released.
- PAMI paper on modeling human-object interactions
- Synchronic activities stickmen dataset, appearing in Human Pose Co-Estimation and Applications (PAMI) now available online
- Source code for our Segmentation Transfer technique released (appearing in Figure-ground segmentation by transferring window masks, CVPR 2012)
- Two CVPR 2012 papers in the top list of a Google reporter
- Two papers accepted to ECCV 2012 (one oral)
- Vittorio Ferrari received an ERC Starting Grant.
- Vittorio Ferrari received an Outstanding Reviewer award at IEEE CVPR 2012.
- Youtube-Objects dataset, appearing on Learning Object Class Detectors from Weakly Annotated Video (CVPR12), is now available online