Weakly supervised discovery of common visual structure in highly variable, cluttered images
is a key problem in recognition. We address this problem using deformable part-based …

In this paper, we investigate a novel reconfigurable part-based model, namely And-Or graph
model, to recognize object shapes in images. Our proposed model consists of four layers …

A tutorial explaining a machine vision model that emulates human performance when it recovers
natural 3D scenes from 2D images - ScienceDirect Skip to main contentSkip to article Elsevier logo …

Graph matching is a powerful tool for computer vision and machine learning. In this paper, a
novel approach to graph matching is developed based on the sequential Monte Carlo …

In this paper, we propose a novel framework for object detection and recognition in cluttered
images, given a single hand-drawn example as model. Compared with previous work, our …

This paper studies a novel discriminative part-based model to represent and recognize
object shapes with an “And-Or graph”. We define this model consisting of three layers: the …

Object detection using shape is interesting since it is well known that humans can recognize
an object simply from its shape. Thus, shape-based methods have great promise to handle a …

We consider a problem of finding maximum weight subgraphs (MWS) that satisfy hard
constraints in a weighted graph. The constraints specify the graph nodes that must belong to …

In this paper, we try to address the challenging problem of combining local shape features to
describe long and continuous shape characteristics. To this end, we firstly propose a novel …

We aim to solve the object recognition problem by a novel contour feature called
Deformable Edge Set (DES). The DES consists of several Deformable Edge Features (DEF) …