This year BMVC will feature two high quality tutorials delivered consecuiively on the afternoon of Monday, September 3. Tutorial
admission is free to BMVC attendees, however please indicate your intention to attend during regisation to assist in the management of numbers.
Tutorial: Large-scale and larger-scale image search.
Dr Herve Jegou
INRIA Rennes, France
The first part of this tutorial, dedicated to large-scale image retrieval, will first introduce the typical use-cases and the datasets used for evaluation of image search when considering an unsupervised framework. We will present different classes of techniques considering different trade-offs with respect to efficiency and search quality. Starting with the most costly but precise patch-based matching and spatial verification techniques, we will present the bag-of-words model, its matching interpretation and several improvements, including re-ranking techniques based on spatial verification and query expansion. Finally, the most scalable techniques based on aggregation/coding techniques and compressed-domain search will be detailed.
Tutorial: MAP inference in Discrete Models.
Dr Pushmeet Kohli
Microsoft Research, UK
Many problems in Computer Vision are formulated in form of a random filed of discrete variables. Examples range from low-level vision such as image segmentation, optical flow and stereo reconstruction, to high-level vision such as object recognition. The goal is typically to infer the most probable values of the random variables, known as Maximum a Posteriori (MAP) estimation. This has been widely studied in several areas of Computer Science (e.g. Computer Vision, Machine Learning, Theory), and the resulting algorithms have greatly helped in obtaining accurate and reliable solutions to many problems. These algorithms are extremely efficient and can find the globally (or strong locally) optimal solutions for an important class of models in polynomial time. Hence, they have led to a significant increase in the use of random field models in computer vision and information engineering in general. This tutorial is aimed at researchers who wish to use and understand these algorithms for solving new problems in computer vision and information engineering. No prior knowledge of probabilistic models or discrete optimization will be assumed. The tutorial will answer the following questions: (a) How to formalize and solve some known vision problems using MAP inference of a random field? (b) What are the different genres of MAP inference algorithms? (c) How do they work? (d) What are the recent developments and open questions in this field?
Further information on scheduling and location will appear on the conference programme.