Structural Learning for Visual Inferences
Quannan Li · eScholarship (California Digital Library) · 2013
In this work, we investigate the structural information in typical problems in boththe machine learning and computer vision domains and propose effective yet efficient methods to tackle those problems. In particular, for structural labeling, we propose a fixed-point model which is able to learn/model long range structural contexts and is very efficient to train. For visual codebook learning, we propose arandomness and sparsity induced learning scheme which can fit to the local intrinsic structure of image patches. We also propose methods to tackle the problems of mid-level feature learning and object tracking where the structural information are helpful. For mid-level feature learning, we propose a fully automatic algorithm which harvests effective visual concepts from a large number of Internet images using text-based queries. For object tracking, we propose a disagreement-based approach which can be built on top of nearly any existing tracking systems by exploiting their disagreements. Our methods achieve state-of-the-art performance and high efficiency.