BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Unsupervised Multi-Task Feature Learning on Point Clouds - Hooman 
 Shayani -- Autodesk
DTSTART:20191128T130000Z
DTEND:20191128T143000Z
UID:TALK130096@talks.cam.ac.uk
CONTACT:James Fergusson
DESCRIPTION:We introduce an unsupervised multi-task model to jointly learn
  point and shape features on point clouds. We define three unsupervised ta
 sks including clustering\, reconstruction\, and self-supervised classifica
 tion to train a multi-scale graph-based encoder. We evaluate our model on 
 shape classification and segmentation benchmarks. The results suggest that
  it outperforms prior state-of-the-art unsupervised models: In the ModelNe
 t40 classification task\, it achieves an accuracy of 89.1% and in ShapeNet
  segmentation task\, it achieves an mIoU of 68.2 and accuracy of 88.6%. (b
 ased on: https://arxiv.org/pdf/1910.08207.pdf)
LOCATION:Kavli Large Meeting Room\, Kavli Building
END:VEVENT
END:VCALENDAR