Generalized Sparselet Models for Real-Time Multiclass Object Recognition

The problem of real-time multiclass object recognition is of great practical importance in object recognition. In this paper, we describe a framework that simultaneously utilizes shared representation, reconstruction sparsity, and parallelism to enable real-time multiclass object detection with defo...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 37(2015), 5 vom: 01. Mai, Seite 1001-12
1. Verfasser: Song, Hyun Oh (VerfasserIn)
Weitere Verfasser: Girshick, Ross, Zickler, Stefan, Geyer, Christopher, Felzenszwalb, Pedro, Darrell, Trevor
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2015
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't Research Support, U.S. Gov't, Non-P.H.S.
LEADER 01000caa a22002652 4500
001 NLM25259200X
003 DE-627
005 20250219030430.0
007 cr uuu---uuuuu
008 231224s2015 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2014.2353631  |2 doi 
028 5 2 |a pubmed25n0841.xml 
035 |a (DE-627)NLM25259200X 
035 |a (NLM)26353324 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Song, Hyun Oh  |e verfasserin  |4 aut 
245 1 0 |a Generalized Sparselet Models for Real-Time Multiclass Object Recognition 
264 1 |c 2015 
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 24.11.2015 
500 |a Date Revised 10.09.2015 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a The problem of real-time multiclass object recognition is of great practical importance in object recognition. In this paper, we describe a framework that simultaneously utilizes shared representation, reconstruction sparsity, and parallelism to enable real-time multiclass object detection with deformable part models at 5Hz on a laptop computer with almost no decrease in task performance. Our framework is trained in the standard structured output prediction formulation and is generically applicable for speeding up object recognition systems where the computational bottleneck is in multiclass, multi-convolutional inference. We experimentally demonstrate the efficiency and task performance of our method on PASCAL VOC, subset of ImageNet, Caltech101 and Caltech256 dataset 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
650 4 |a Research Support, U.S. Gov't, Non-P.H.S. 
700 1 |a Girshick, Ross  |e verfasserin  |4 aut 
700 1 |a Zickler, Stefan  |e verfasserin  |4 aut 
700 1 |a Geyer, Christopher  |e verfasserin  |4 aut 
700 1 |a Felzenszwalb, Pedro  |e verfasserin  |4 aut 
700 1 |a Darrell, Trevor  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 37(2015), 5 vom: 01. Mai, Seite 1001-12  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:37  |g year:2015  |g number:5  |g day:01  |g month:05  |g pages:1001-12 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2014.2353631  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 37  |j 2015  |e 5  |b 01  |c 05  |h 1001-12