Hierarchical Statistical Learning of Generic Parts of Object Structure

Fidler, Sanja; Berginc, Gregor; Leonardis, Aleš

doi:10.1109/cvpr.2006.134

Cited by 35 publications

(30 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This line of architecture is also consistent with the findings on biological systems [44,9]. A number of authors have further emphasized these computational considerations [13,23,2,47,26], suggesting that matching should be performed at multiple hierarchical stages, in order to gradually and coherently limit the otherwise computationally prohibitive search space [13,53,8,3,33,2,23,17,47,19]. While hierarchies presented a natural way to represent objects in the early vision works [13,24,32,11], surprisingly, they have not become an integral part of the modern vision approaches.…”

Section: Introductionsupporting

confidence: 70%

Learning Hierarchical Compositional Representations of Object Structure

Fidler¹,

Boben²,

Leonardis³

2009

Object Categorization

View full text Add to dashboard Cite

Section: Introductionsupporting

confidence: 70%

Learning Hierarchical Compositional Representations of Object Structure

Fidler¹,

Boben²,

Leonardis³

2009

Object Categorization

View full text Add to dashboard Cite

“…It can be interpreted this way 2 : the node b with probability m i generates composition at a random position c i . There can be an arbitrary number of such structural components, but the reasonable number is ca 2-8 [13].…”

Section: Probabilistic Frameworkmentioning

confidence: 99%

A Simple Stochastic Algorithm for Structural Features Learning

Mačák

2015

Computer Vision - ACCV 2014 Workshops

View full text Add to dashboard Cite

Abstract. A conceptually very simple unsupervised algorithm for learning structure in the form of a hierarchical probabilistic model is described in this paper. The proposed probabilistic model can easily work with any type of image primitives such as edge segments, non-max-suppressed filter set responses, texels, distinct image regions, SIFT features, etc., and is even capable of modelling non-rigid and/or visually variable objects. The model has recursive form and consists of sets of simple and gradually growing sub-models that are shared and learned individually in layers. The proposed probabilistic framework enables to exactly compute the probability of presence of a certain model, regardless on which layer it actually is. All these learned models constitute a rich set of independent structure elements of variable complexity that can be used as features in various recognition tasks.

show abstract

“…In general, these methods are computationally demanding and prior knowledge of the object category is required. There are related work in modeling textons [25] and learning generic parts from multiple object categories for object recognition [20,5,23]. In data mining domain, there are also related work in discovering spatial collocation patterns [9] and interpreting mined frequent patterns [24,14].…”

Section: Related Workmentioning

confidence: 99%