Fourth Workshop on “Robust Subspace Learning and Applications in Computer Vision” at ICCV 2021

https://rsl-cv.univ-lr.fr/2021

Robust subspace learning/tracking/clustering either based on robust statistics estimation on reconstruction error and  on decomposition into low-rank/sparse plus additive matrices/tensors provide suitable frameworks for many computer vision applications like in video coding, key frame extraction, hyper-spectral video processing, dynamic MRI, motion saliency detection, background initialization and background/foreground separation. In this context, the previous three workshops RSL-CV hosted at ICCV 2015, ICCV 2017 and ICCV 2019 aimed to propose novel robust subspace clustering/learning/tracking approaches with adaptive and incremental algorithms  Even if progress has been made since the last workshops, there are still main challenges which concern the fundamental design of relaxed models and solvers which have to be with as few as possible iterations, and as efficient as possible. In addition, efforts should be concentrated on provable correct algorithms with convergence guarantees as well as robust subspace recovery algorithms. Furthermore, recent advances on low-rank and sparse embedding for dimensionality reduction, robust graph learning and robust deep autoencoders]offer promising increase of performance when applied to computer vision. Recent publications published in 2020 reinforced the interesting connection between deep learning and robust PCA.  Finally, even though 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 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 this workshop are thus three–fold: 1) designing robust methods for matrix and tensor subspace estimation in computer vision applications; 2) proposing new adaptive and incremental algorithms with convergence guarantees that reach the requirements of real-time applications (motion saliency, video coding and background/foreground separation); and 3) proposing robust algorithms to handle the key challenges in computer vision applications. Papers are solicited to address robust subspace methods to be applied in computer vision, including but not limited to the following:

Robust Subspace Learning (RPCA, RMF, RMC)

Robust Low Rank Factorization /Approximation/Recovery

Robust and Dynamic Tensor Decomposition

Robust Subspace Tracking/ Clustering

Decomposition intp low-rank/sparse plus additive matrices/tensors

Bayesian 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

Robust Deep Auto-Encoders

Sparse Subspace Learning/Distributed Subspace Learning

Timeline

Full Paper Submission Deadline: July 13, 2021 (for papers not submitted at ICCV), July 25, 2021 (for papers that are awaiting for ICCV decisions)

Decisions to Authors: July 31, 2021

Camera-ready Deadline:  August 17, 2021

Main  organizers

Thierry Bouwmans, Associate Professor, Laboratoire MIA, Univ. La Rochelle, France.

Soon Ki Jung, Professor, Kyungpook National University, Korea.

Panos Markopoulos^, Associate Professor, Rochester Institute of Technology, USA.

Paul Rodriguez^, Professor,  Pontificia Universidad Católica del Perú, Peru.

Mohamed Shehata, Associate Professor, Memorial University, Canada.

Rene Vidal^, Full Professor, Johns Hopkins University, USA.