PoseShop : human image database construction and personalized content synthesis

We present PoseShop--a pipeline to construct segmented human image database with minimal manual intervention. By downloading, analyzing, and filtering massive amounts of human images from the Internet, we achieve a database which contains 400 thousands human figures that are segmented out of their b...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on visualization and computer graphics. - 1996. - 19(2013), 5 vom: 15. Mai, Seite 824-37
1. Verfasser: Chen, Tao (VerfasserIn)
Weitere Verfasser: Tan, Ping, Ma, Li-Qian, Cheng, Ming-Ming, Shamir, Ariel, Hu, Shi-Min
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2013
Zugriff auf das übergeordnete Werk:IEEE transactions on visualization and computer graphics
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM218916655
003 DE-627
005 20231224041637.0
007 cr uuu---uuuuu
008 231224s2013 xx |||||o 00| ||eng c
028 5 2 |a pubmed24n0729.xml 
035 |a (DE-627)NLM218916655 
035 |a (NLM)22732681 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Chen, Tao  |e verfasserin  |4 aut 
245 1 0 |a PoseShop  |b human image database construction and personalized content synthesis 
264 1 |c 2013 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 18.11.2013 
500 |a Date Revised 04.06.2013 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a We present PoseShop--a pipeline to construct segmented human image database with minimal manual intervention. By downloading, analyzing, and filtering massive amounts of human images from the Internet, we achieve a database which contains 400 thousands human figures that are segmented out of their background. The human figures are organized based on action semantic, clothes attributes, and indexed by the shape of their poses. They can be queried using either silhouette sketch or a skeleton to find a given pose. We demonstrate applications for this database for multiframe personalized content synthesis in the form of comic-strips, where the main character is the user or his/her friends. We address the two challenges of such synthesis, namely personalization and consistency over a set of frames, by introducing head swapping and clothes swapping techniques. We also demonstrate an action correlation analysis application to show the usefulness of the database for vision application 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Tan, Ping  |e verfasserin  |4 aut 
700 1 |a Ma, Li-Qian  |e verfasserin  |4 aut 
700 1 |a Cheng, Ming-Ming  |e verfasserin  |4 aut 
700 1 |a Shamir, Ariel  |e verfasserin  |4 aut 
700 1 |a Hu, Shi-Min  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on visualization and computer graphics  |d 1996  |g 19(2013), 5 vom: 15. Mai, Seite 824-37  |w (DE-627)NLM098269445  |x 1941-0506  |7 nnns 
773 1 8 |g volume:19  |g year:2013  |g number:5  |g day:15  |g month:05  |g pages:824-37 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 19  |j 2013  |e 5  |b 15  |c 05  |h 824-37