Generative regularization with latent topics for discriminative object recognition
Popular part-based approaches to recognition are currently limited to few localized parts, which only poorly represent the fine-scale details and large variability of object categories. Extending to hundreds of specific part detectors helps to capture peculiar characteristics but due to their specif...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
[2015]
|
| In: |
Pattern recognition
Year: 2015, Jahrgang: 48, Heft: 12, Pages: 3871-3880 |
| DOI: | 10.1016/j.patcog.2015.06.013 |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1016/j.patcog.2015.06.013 Verlag, lizenzpflichtig, Volltext: http://www.sciencedirect.com/science/article/pii/S0031320315002356 
|
| Verfasserangaben: | Jose C. Rubio, Angela Eigenstetter, Björn Ommer |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1713927713 | ||
| 003 | DE-627 | ||
| 005 | 20220818143731.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 200708s2015 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.patcog.2015.06.013 |2 doi | |
| 035 | |a (DE-627)1713927713 | ||
| 035 | |a (DE-599)KXP1713927713 | ||
| 035 | |a (OCoLC)1341344808 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 27 |2 sdnb | ||
| 100 | 1 | |a Rubio, Jose C. |e VerfasserIn |0 (DE-588)1052420338 |0 (DE-627)788467247 |0 (DE-576)408129239 |4 aut | |
| 245 | 1 | 0 | |a Generative regularization with latent topics for discriminative object recognition |c Jose C. Rubio, Angela Eigenstetter, Björn Ommer |
| 264 | 1 | |c [2015] | |
| 300 | |b Illustrationen | ||
| 300 | |a 10 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Available online 2 July 2015 | ||
| 500 | |a Gesehen am 08.07.2020 | ||
| 520 | |a Popular part-based approaches to recognition are currently limited to few localized parts, which only poorly represent the fine-scale details and large variability of object categories. Extending to hundreds of specific part detectors helps to capture peculiar characteristics but due to their specificity, for each object instance different parts will be helpful and others will yield noisy responses that actually impair classification. While training the part-based model, we thus need to learn which parts are relevant for which training instances. To automatically discover these latent topics of parts and instances we employ generative non-negative matrix factorization and seek topics with low reconstruction error. To assure recognition performance this generative approach is embedded within a discriminative latent max-margin procedure that separates classes while optimizing the latent topics. Consequently, generative reconstruction is regularizing discriminative classification, while the latter ensures that topics actually help in recognition. Experiments on PASCAL VOC demonstrate the recognition performance of our model as well as the construction of meaningful topics. | ||
| 650 | 4 | |a Latent SVM | |
| 650 | 4 | |a Mixture models | |
| 650 | 4 | |a Non-Negative Matrix Factorization | |
| 650 | 4 | |a Part-based models | |
| 650 | 4 | |a Visual object recognition | |
| 700 | 1 | |a Eigenstetter, Angela |e VerfasserIn |0 (DE-588)1074025326 |0 (DE-627)830173145 |0 (DE-576)43553503X |4 aut | |
| 700 | 1 | |a Ommer, Björn |d 1981- |e VerfasserIn |0 (DE-588)1034893106 |0 (DE-627)746457510 |0 (DE-576)382507916 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Pattern recognition |d Amsterdam : Elsevier, 1968 |g 48(2015), 12, Seite 3871-3880 |h Online-Ressource |w (DE-627)265784131 |w (DE-600)1466343-0 |w (DE-576)101177364 |7 nnas |a Generative regularization with latent topics for discriminative object recognition |
| 773 | 1 | 8 | |g volume:48 |g year:2015 |g number:12 |g pages:3871-3880 |g extent:10 |a Generative regularization with latent topics for discriminative object recognition |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.patcog.2015.06.013 |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
| 856 | 4 | 0 | |u http://www.sciencedirect.com/science/article/pii/S0031320315002356 |x Verlag |z lizenzpflichtig |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20200708 | ||
| 993 | |a Article | ||
| 994 | |a 2015 | ||
| 998 | |g 1034893106 |a Ommer, Björn |m 1034893106:Ommer, Björn |d 700000 |d 708070 |e 700000PO1034893106 |e 708070PO1034893106 |k 0/700000/ |k 1/700000/708070/ |p 3 |y j | ||
| 998 | |g 1074025326 |a Eigenstetter, Angela |m 1074025326:Eigenstetter, Angela |p 2 | ||
| 998 | |g 1052420338 |a Rubio, Jose C. |m 1052420338:Rubio, Jose C. |p 1 |x j | ||
| 999 | |a KXP-PPN1713927713 |e 3711417248 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"title":[{"title":"Generative regularization with latent topics for discriminative object recognition","title_sort":"Generative regularization with latent topics for discriminative object recognition"}],"person":[{"display":"Rubio, Jose C.","roleDisplay":"VerfasserIn","role":"aut","family":"Rubio","given":"Jose C."},{"given":"Angela","family":"Eigenstetter","role":"aut","roleDisplay":"VerfasserIn","display":"Eigenstetter, Angela"},{"given":"Björn","family":"Ommer","role":"aut","roleDisplay":"VerfasserIn","display":"Ommer, Björn"}],"recId":"1713927713","language":["eng"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"note":["Available online 2 July 2015","Gesehen am 08.07.2020"],"id":{"doi":["10.1016/j.patcog.2015.06.013"],"eki":["1713927713"]},"origin":[{"dateIssuedDisp":"[2015]","dateIssuedKey":"2015"}],"name":{"displayForm":["Jose C. Rubio, Angela Eigenstetter, Björn Ommer"]},"relHost":[{"origin":[{"dateIssuedDisp":"1968-","dateIssuedKey":"1968","publisher":"Elsevier","publisherPlace":"Amsterdam"}],"id":{"eki":["265784131"],"zdb":["1466343-0"]},"physDesc":[{"extent":"Online-Ressource"}],"title":[{"title_sort":"Pattern recognition","subtitle":"the journal of the Pattern Recognition Society","title":"Pattern recognition"}],"type":{"bibl":"periodical","media":"Online-Ressource"},"note":["Gesehen am 31.05.23"],"disp":"Generative regularization with latent topics for discriminative object recognitionPattern recognition","recId":"265784131","corporate":[{"role":"isb","roleDisplay":"Herausgebendes Organ","display":"Pattern Recognition Society"}],"language":["eng"],"pubHistory":["1.1968/69 - 48.2015; Vol. 49.2016 -"],"part":{"pages":"3871-3880","issue":"12","year":"2015","extent":"10","volume":"48","text":"48(2015), 12, Seite 3871-3880"}}],"physDesc":[{"noteIll":"Illustrationen","extent":"10 S."}]} | ||
| SRT | |a RUBIOJOSECGENERATIVE2015 | ||