國立虎尾科技大學 |

Learning Conditional Models for Visual Perception.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Learning Conditional Models for Visual Perception./
Author:	Veit, Andreas.
Description:	1 online resource (125 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9780438026872

Learning Conditional Models for Visual Perception.
Veit, Andreas.

Learning Conditional Models for Visual Perception. - 1 online resource (125 pages)

Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.

Thesis (Ph.D.)--Cornell University, 2018.

Includes bibliographical references

In recent years, the field of computer vision has seen a series of major advances, made possible by rapid development in algorithms, data collection and computing infrastructure. As a result, vision systems have started to be broadly adopted in everyday applications. Progress has been particularly promising in image recognition, where algorithms now often match human performance. Nevertheless, vision systems still largely fall behind humans in their ability to understand the complexities of the visual world and its apparent contradictions. For example, an image can carry different meanings to different people in different contexts. However, being often limited to a single point of view, vision systems tend to focus on the meaning that dominates in the training data.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780438026872Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Learning Conditional Models for Visual Perception.
LDR:03369ntm a2200325K 4500 001 914859
005 20180724121431.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780438026872
035 $a (MiAaPQ)AAI10815847
035 $a (MiAaPQ)cornellgrad:10825
035 $a AAI10815847
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Veit, Andreas. $3 1188241
245 1 0 $a Learning Conditional Models for Visual Perception.
264 0 $c 2018
300 $a 1 online resource (125 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
500 $a Adviser: Serge J. Belongie.
502 $a Thesis (Ph.D.)--Cornell University, 2018.
504 $a Includes bibliographical references
520 $a In recent years, the field of computer vision has seen a series of major advances, made possible by rapid development in algorithms, data collection and computing infrastructure. As a result, vision systems have started to be broadly adopted in everyday applications. Progress has been particularly promising in image recognition, where algorithms now often match human performance. Nevertheless, vision systems still largely fall behind humans in their ability to understand the complexities of the visual world and its apparent contradictions. For example, an image can carry different meanings to different people in different contexts. However, being often limited to a single point of view, vision systems tend to focus on the meaning that dominates in the training data.
520 $a In this dissertation, we address this limitation by building conditional vision models that can learn from multiple points of view and adapt their results to account for different conditions. First, we address the related tasks of image tagging and tag based image retrieval. In particular, we build a system that can take into account the fact that people may associate different meaning with certain images and tags. Thus, the system can personalize outputs for ambiguous tags such as #rock, which could refer either to a music genre, a geological object or even outdoor climbing. Further, we focus on the task of image based similarity search. Specifically, we design a system that can understand multiple notions of similarity. For example, when searching for related items to an input images of a shoe, users might be interested in shoes of similar color, style, or for the same kind of activity. By capturing the multitude of aspects in terms of which objects can be compared, our system can find the right set of related items. Lastly, we explore how the underlying convolutional networks themselves can be made aware of the context in which they are used. In a study, we first discover a new understanding of the roles that individual layers take on in modern convolutional networks. Then, we leverage our insights and design a network that can adaptively define its own topology conditioned on the input image to increase both accuracy and efficiency.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Cornell University. $b Computer Science. $3 1179602
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10815847 $z click for full text (PQDT)