Göm meny

Reading Group in Computer and Robot Vision

  • The purpose of this reading group is to provide an overview of the rapidly evolving computer vision literature. We meet once a week to discuss an article that all participants should read before the seminar.
  • All participants are welcome to suggest, and present articles of their choosing. The theme for articles should be computer and robot vision, with emphasis on new, high-impact conference papers (e.g. from ICCV, CVPR, RSS, or ECCV). To make best use of time, you may consider choosing an article that relates to your work, that you presumably would read anyway. If the article is well written that is also a plus.
  • You have the option to attend the seminars as part of a PhD course. You will get one 1hp for each time you present a paper, and participate in another three seminars. If you want to go for the PhD course option, let me know in advance by sending me an email with you personal number, so I can register your attendance.
    / Per-Erik

  • Meeting room: Visionen, Lilla Konf.rummet, Campus Valla, Building B.

  • Time: Wednesdays at 10.00-11.00.

  • E-mail list: Upcoming articles are announced on the mailing list vision-seminars.

Upcoming articles

Article suggestions

  • Have a look at e.g. the following proceedings: CVPR'17, ECCV'16, ICCV'15, SIGGRAPH'16, RSS'2016, ACCV'16. Some old, unused suggestions are listed below.
  • L. Oth et al. Rolling Shutter Camera Calibration, CVPR13 , [External PDF] SD130816
  • C. Kuster et al., Gaze Correction for Home Video Conferencing, SIGGRAPH Asia 2012 , [External link] SD130904
  • H.S. Wong et al., Dynamic and Hierarchical Multi-Structure Geometric Model Fitting , ICCV11 , [External link] SD131115
  • W. Förstner, On the Theoretical Accuracy of Multi Image Matching , Restoration and Triangulation, [External link] SD131004
  • M. Elad and A. Feuer, Super Resolution Reconstruction of Image Sequences, TPAMI99 [External link] SD131004
  • C. Vondrick et al., Inverting and Visualizing Features for Object Detection, ArXiv [ External Link] SD131008
  • N. Kholgade et al., 3D Object Manipulation in a Single Photograph using Stock 3D Models, SIGGRAPH14 [External link] SD140808
  • J. Kopf, M. Cohen, R. Szeliski, First-person Hyperlapse Videos, SIGGRAPH14 [External link] SD140812
  • C. Chen et al. R-CNN for Small Object Detection, MERL technical report [PDF] SD170531

Paper log spring 2017

  • March 23: Per-Erik presents: Show, Attend and Tell: Neural Image Caption Generation with Visual Attention, ICML15 [PDF] [GitHub page]
  • March 30: Martin presents: V. Mnih et al. Asynchronous Methods for Deep Reinforcement Learning, ICML16 [PDF] [video 1] [video 2] [video 3].
  • April 6: Gustav presents: J. Andreas et al. Neural Module Networks, CVPR16 [PDF] [homepage]
  • April 27: Mikael Persson. J. Engel, V. Koltun, D. Cremers, Direct Sparse Odometry, arXiv, 2016 [PDF][webpage]
  • May 4: Abdelrahman Eldesokey. F. Luan et al., Deep Photo Style Transfer, ArXiv [ArXiv] [GitHub]
  • May 11: Andreas Robinson. T. Zhou et al. Unsupervised Learning of Depth and Ego-Motion from Video, CVPR17 [PDF] [webpage]
  • June 8: Joakim Johnander presents: Eddy Llg et al., FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks, CVPR'17 [PDF] [author homepage]

Paper log autumn 2017

  • August 30: Joakim Johnander presents: S. Valipour et al. Recurrent Fully Convolutional Networks for Video Segmentation, WACV17. [PDF] [project page]
  • September 6: Mikael Persson presents: A. Shrivastava et al. Learning from Simulated and Unsupervised Images through Adversarial Training, CVPR17 [ArXiV] reimplementation [Git] [Apple ML blog post] [Meetup discussion of paper]

Old paper logs

Senast uppdaterad: 2017-09-06