|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM268253609 |
| 003 |
DE-627 |
| 005 |
20250221044916.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231224s2017 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2016.2612825
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n0894.xml
|
| 035 |
|
|
|a (DE-627)NLM268253609
|
| 035 |
|
|
|a (NLM)28113970
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Jinhui Tang
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a LEGO-MM
|b LEarning Structured Model by Probabilistic loGic Ontology Tree for MultiMedia
|
| 264 |
|
1 |
|c 2017
|
| 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 Revised 20.11.2019
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Recent advances in multimedia ontology have resulted in a number of concept models, e.g., large-scale concept for multimedia and Mediamill 101, which are accessible and public to other researchers. However, most current research effort still focuses on building new concepts from scratch, very few work explores the appropriate method to construct new concepts upon the existing models already in the warehouse. To address this issue, we propose a new framework in this paper, termed LEarning Structured Model by Probabilistic loGic Ontology Tree for MultiM edia (LEGO 1 -MM), which can seamlessly integrate both the new target training examples and the existing primitive concept models to infer the more complex concept models. LEGO-MM treats the primitive concept models as the lego toy to potentially construct an unlimited vocabulary of new concepts. Specifically, we first formulate the logic operations to be the lego connectors to combine the existing concept models hierarchically in probabilistic logic ontology trees. Then, we incorporate new target training information simultaneously to efficiently disambiguate the underlying logic tree and correct the error propagation. Extensive experiments are conducted on a large vehicle domain data set from ImageNet. The results demonstrate that LEGO-MM has significantly superior performance over the existing state-of-the-art methods, which build new concept models from scratch
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Shiyu Chang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Guo-Jun Qi
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Qi Tian
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yong Rui
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Huang, Thomas S
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 26(2017), 1 vom: 15. Jan., Seite 196-207
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnas
|
| 773 |
1 |
8 |
|g volume:26
|g year:2017
|g number:1
|g day:15
|g month:01
|g pages:196-207
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2016.2612825
|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 26
|j 2017
|e 1
|b 15
|c 01
|h 196-207
|