Learning Features for Object Discovery: An Unsupervised Approach

碩士 === 國立清華大學 === 資訊工程學系 === 104 === The task of object discovery is to gure out common categories of objects in multiple images without prior knowledge of object categories. It is considered as very challenging computer vision problem. Given a set of images, we aim to identify and localize the comm...

Full description

Bibliographic Details
Main Authors:	Fang, Chun, 方鈞
Other Authors:	Chen, Hwann Tzong
Format:	Others
Language:	en_US
Published:	2016
Online Access:	http://ndltd.ncl.edu.tw/handle/16559322939509009527

id	ndltd-TW-104NTHU5392090
record_format	oai_dc
spelling	ndltd-TW-104NTHU53920902017-08-27T04:30:16Z http://ndltd.ncl.edu.tw/handle/16559322939509009527 Learning Features for Object Discovery: An Unsupervised Approach 用於物件搜尋之非監督式特徵學習法 Fang, Chun 方鈞碩士國立清華大學資訊工程學系 104 The task of object discovery is to gure out common categories of objects in multiple images without prior knowledge of object categories. It is considered as very challenging computer vision problem. Given a set of images, we aim to identify and localize the common objects. The common objects may vary in scales, poses, appearances, and with occlusions, and these variations make the task of object discovery more diffcult. Conventional solutions tackle the problem with the aid of human intervention. In this work, we present an unsupervised method to learn effective features for object discovery. Chen, Hwann Tzong 陳煥宗 2016 學位論文 ; thesis 32 en_US
collection	NDLTD
language	en_US
format	Others
sources	NDLTD
description	碩士 === 國立清華大學 === 資訊工程學系 === 104 === The task of object discovery is to gure out common categories of objects in multiple images without prior knowledge of object categories. It is considered as very challenging computer vision problem. Given a set of images, we aim to identify and localize the common objects. The common objects may vary in scales, poses, appearances, and with occlusions, and these variations make the task of object discovery more diffcult. Conventional solutions tackle the problem with the aid of human intervention. In this work, we present an unsupervised method to learn effective features for object discovery.
author2	Chen, Hwann Tzong
author_facet	Chen, Hwann Tzong Fang, Chun 方鈞
author	Fang, Chun 方鈞
spellingShingle	Fang, Chun 方鈞 Learning Features for Object Discovery: An Unsupervised Approach
author_sort	Fang, Chun
title	Learning Features for Object Discovery: An Unsupervised Approach
title_short	Learning Features for Object Discovery: An Unsupervised Approach
title_full	Learning Features for Object Discovery: An Unsupervised Approach
title_fullStr	Learning Features for Object Discovery: An Unsupervised Approach
title_full_unstemmed	Learning Features for Object Discovery: An Unsupervised Approach
title_sort	learning features for object discovery: an unsupervised approach
publishDate	2016
url	http://ndltd.ncl.edu.tw/handle/16559322939509009527
work_keys_str_mv	AT fangchun learningfeaturesforobjectdiscoveryanunsupervisedapproach AT fāngjūn learningfeaturesforobjectdiscoveryanunsupervisedapproach AT fangchun yòngyúwùjiànsōuxúnzhīfēijiāndūshìtèzhēngxuéxífǎ AT fāngjūn yòngyúwùjiànsōuxúnzhīfēijiāndūshìtèzhēngxuéxífǎ
_version_	1718519379899973632

Learning Features for Object Discovery: An Unsupervised Approach

Similar Items