ICCV International Workshop on Manifold Learning: from Euclid to Riemann, ICCV 2017

4 Juin 2017

---

Catégorie : Conférence internationale

---

ICCV International Workshop onManifold Learning: from Euclid to Riemann, ICCV 2017

Venice, Italy - 28 October 2017

In conjunction with ICCV 2017

Webpage: https://sites.google.com/site/maniflearn/

Contact: maniflearn@googlegroups.com

IMPORTANT DATES

• Paper Submission: June 15^th , 2017
• Author Notification: July 31th 2017
• Camera Ready: August 25^th , 2017
• Workshop: October 28^th, 2017

CALL FOR PAPERS

Manifold Learning (ML) has been the subject of intensive study over the past two decades in the computer vision and machine learning communities. Originally, manifold learning techniques aim to identify the underlying structure (usually low-dimensional) of data from a set of observations (in the form of high-dimensional vectors). The recent advances in deep learning make one wonder whether data-driven learning techniques can benefit from the theoretical findings from ML studies. This innocent looking question becomes more important if we note that deep learning techniques are notorious for being data-hungry and supervised (mostly). On the contrary, many ML techniques unravel data structures without much supervision. This workshop considers itself as the frontier to raise the question of how classical ML techniques can help deep learning and vice versa and targets studies and discussions that bridge the gap.

In this workshop, we will explore the latest development in machine learning techniques developed to work on/benefit from the non-linear manifolds. We will also target challenges and future directions related to the application of non-linear geometry, Riemannian manifolds in computer vision and machine learning. This workshop also acts as an opportunity for cross-disciplinary discussions and collaborations.

We encourage discussions on recent advances, ongoing developments, and novel applications of manifold learning, optimization, feature representations and deep learning techniques. We are soliciting original contributions that address a wide range of theoretical and practical issues including, but not limited to:

• Theoretical Advances related to manifold learning such as
• Dimensionality Reduction (e.g., Locally Linear Embedding, Laplacian Eigenmaps and etc.)
• Clustering (e.g., discriminative clustering)
• Kernel methods
• Hashing
• Feature learning
• Metric Learning
• Subspace Methods (e.g., Subspace clustering)
• Advanced Optimization Techniques (constrained and non-convex optimization techniques on non-linear manifolds)
• Mathematical Models for learning sequences
• Mathematical Models for learning Shapes
• Deep learning and non-linear manifolds
• Low-rank factorization methods
• Applications:
  • Biometrics
  • Image/video recognition
  • Action/activity recognition
  • Facial expressions recognition
  • Learning and scene understanding
  • Medical imaging
  • Robotics
  • Other related topics not listed above

INVITED SPEAKERS

• Prof. Pierre Absil (Department of Mathematical Engineering, University of Louvain, Belgium)
  Home Page: https://sites.uclouvain.be/absil/
  Talk Title: Fittingcomposite Bézier curves on manifolds and their applications in computer vision
  Abstract; https://sites.google.com/site/maniflearn/invited-speakers

• Prof. Cristian Sminchisescu (Mathematical Sciences, Lund University, Sweden)
  Home Page: http://www.maths.lth.se/matematiklth/personal/sminchis/index.html
  Talk Title: Deep Structured Models for Visual Recognition
  Abstract: https://sites.google.com/site/maniflearn/invited-speakers

• Dr. Minh Ha Quang (IIT Istituto Italiano di Tecnologia, Italy)
  Home Page:https://www.iit.it/people/minh-haquang
  Talk Title: Infinite-dimensional covariance operators and their applications in computer vision
  Abstract: https://sites.google.com/site/maniflearn/invited-speakers

• Dr. Pavan Turaga (Arizona State University, USA)
  Home Page:http://www.public.asu.edu/~pturaga/Welcome.html
  Talk Title: Geometric Methods in Modeling Dynamical Phenomenon: Applications in Video Analysis
  Abstract: https://sites.google.com/site/maniflearn/invited-speakers

• Prof. Mohamed Daoudi (IMT Lille Douai, CRIStAL UMR CNRS, France)
• Dr. Mehrtash Harandi (Data61-CSIRO and Australian National University, Australia)
• Prof. Vittorio Murino (IIT Istituto Italiano di Tecnologia, Italy)
• Prof. Richard Hartley (Australian National University and Data61-CSIRO, Australia

All submissions will be handled electronically via the conference’s CMT Website (https://cmt3.research.microsoft.com/MANIFLEARN2017). Submitted papers must be no longer than 8 pages following the official ICCV guideline http://iccv2017.thecvf.com/submission/main_conference/author_guidelines.ManifLearn reviewing will be double-blind. Each submission will be reviewed by at least three reviewers for originality, significance, clarity, soundness, relevance and technical contents. Papers that are not blind, or do not use the template, or have more than 8 pages (excluding references) will be rejected without review.