(Hyper)-Graphs Inference via Convex Relaxations and Move Making Algorithms: Contributions and Applications in artificial vision

Pawan Kumar 1 Nikos Komodakis 2, 3 Nikos Paragios 4, 5
2 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
Abstract : Computational visual perception seeks to reproduce human vision through the combination of visual sensors, artificial intelligence and computing. To this end, computer vision tasks are often reformulated as mathematical inference problems where the objective is to determine the set of parameters corresponding to the lowest potential of a task-specific objective function. Graphical models have been the most popular formulation in the field over the past two decades where the problem is viewed as an discrete assignment labeling one. Modularity, scalability and portability are the main strength of these methods which once combined with efficient inference algorithms they could lead to state of the art results. In this tutorial we focus on the inference component of the problem and in particular we discuss in a systematic manner the most commonly used optimization principles in the context of graphical models. Our study concerns inference over low rank models (interactions between variables are constrained to pairs) as well as as higher order ones (arbitrary set of variables determine hyper-cliques on which constraints are introduced) and seeks a concise, self-contained presentation of prior art as well as the presentation of the current state of the art methods in the field.
Complete list of metadatas

Cited literature [66 references]  Display  Hide  Download

https://hal.inria.fr/hal-01223027
Contributor : Paragios Nikos <>
Submitted on : Sunday, November 1, 2015 - 5:46:22 PM
Last modification on : Thursday, February 7, 2019 - 5:29:19 PM
Long-term archiving on : Friday, April 28, 2017 - 4:59:59 AM

File

TR-8798.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01223027, version 1

Relations

Citation

Pawan Kumar, Nikos Komodakis, Nikos Paragios. (Hyper)-Graphs Inference via Convex Relaxations and Move Making Algorithms: Contributions and Applications in artificial vision. [Research Report] RR-8798, Inria. 2015, pp.65. ⟨hal-01223027⟩

Share

Metrics

Record views

561

Files downloads

651