International Workshop RSL-CV 2017, October 28, 2017, Venice, Italy

Second International Workshop on “Robust Subspace Learning and Applications in Computer Vision”
in conjunction with
Extended Deadline July 25, 2017

Robust subspace learning/tracking/clustering by decomposition into low-rank/sparse plus additive matrices/tensors provides a suitable framework for many computer vision applications such as video co ding, key frame extraction, hyper-spectral video processing, dynamic MRI, motion saliency detection, backgroundinitialization and background/foreground separation. In this context, the first workshop RSL-CV 2015 hosted at ICCV 2015 aimed to propose novel robust subspace clustering/learning/tracking approaches, and adaptive and incremental algorithms in the continuity of the fundamental publication of Candes et al., which induced more than 500 papers in the field.

Even if progress were made, there are still main challenges which concern the fundamental design of efficientrelaxed models and solvers which have to be with iterations as few as possible, and as efficient as possible. Furthermore, even if many efforts have been made to develop methods that perform well visually with reduced computational cost, no algorithm has emerged that is able to simultaneously address all of the key challenges that accompany real-world videos taken by static or moving cameras like illumination changes, dynamic backgrounds, bootstrapping that generate corrupted and missing data.

The goals of RSL-CV 2017 are three-fold: 1) proposing robust subspace clustering/learning/tracking for computer vision applications, 2) proposing new adaptive and incremental algorithms for robust subspace clustering/learning/ tracking to reach the requirements of real-time applications such as motion saliency, video coding and background/foreground separation, and 3) proposing robust algorithms to tackle key challenges in computer vision applications such as dynamic backgrounds and illumination changes for background/foreground separation.

Papers are solicited to address robust subspace clu stering/learning/tracking based on matrix/tensor decomposition, to be applied in computer vision, including but not limited to the followings:

  • Robust Subspace Learning: RPCA, RMF, RMC
  • Robust Low Rank Factorization
  • Approximation/Recovery
  • Robust Subspace Tracking
  • Robust Subspace Clustering
  • Decomposition in low-rank/sparse plus additive
  • matrices/tensors
  • Bayesian RPCA, Fuzzy RPCA
  • Compressive Sensing
  • Dictionary Learning
  • Structured Sparsity, Dynamic Group Sparsity
  • Solvers (ALM, ADM, etc...),
  • Closed form solutions
  • Efficient SVD algorithms
  • Multilevel RPCA
  • Incremental RPCA
  • Real time implementation on GPU
  • Embedded implementation
  • Deep Learning
We encourage authors to evaluate their approach on at least one of the reference datasets for each application (Please see the Computer Vision Datasets).

Other resources are available here.

The printable Call for Papers  for RSL-CV 2017 can be downloaded here.