Skip to main navigation Skip to search Skip to main content

Recognition and visual learning of articulated shape by accumulative Hopfield matching

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

Abstract

In this paper, we describe a system that can recognize and learn visual model of an articulated object automatically given different views of the object, provided that the local structure is unchanged. The system is based on the Hopfield style network to find the feature correspondences between different views of an articulated object. With this proposed matching system, we can finally learn the relationship between articulated parts of the object with the poses detected. Experiments on real images show the effectiveness of the proposed system.
Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages2153-2158
Volume3
Publication statusPublished - 2001
Externally publishedYes
EventInternational Joint Conference on Neural Networks (IJCNN'01) - Washington, DC, United States
Duration: 15 Jul 200119 Jul 2001

Publication series

Name
Volume3

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN'01)
PlaceUnited States
CityWashington, DC
Period15/07/0119/07/01

Fingerprint

Dive into the research topics of 'Recognition and visual learning of articulated shape by accumulative Hopfield matching'. Together they form a unique fingerprint.

Cite this