Detector Ensemble. Dai, S., Yang, M., Wu, Y., & Katsaggelos, A. In 2007 IEEE Conference on Computer Vision and Pattern Recognition, pages 1–8, jun, 2007. IEEE. Paper doi abstract bibtex Component-based detection methods have demonstrated their promise by integrating a set of part-detectors to deal with large appearance variations of the target. However, an essential and critical issue, i.e., how to handle the imperfectness of part-detectors in the integration, is not well addressed in the literature. This paper proposes a detector ensemble model that consists of a set of substructure-detectors, each of which is composed of several part-detectors. Two important issues are studied both in theory and in practice, (1) finding an optimal detector ensemble, and (2) detecting targets based on an ensemble. Based on some theoretical analysis, a new model selection strategy is proposed to learn an optimal detector ensemble that has a minimum number of false positives and satisfies the design requirement on the capacity of tolerating missing parts. In addition, this paper also links ensemble-based detection to the inference in Markov random field, and shows that the target detection can be done by a max-product belief propagation algorithm. © 2007 IEEE.
@inproceedings{Shengyang2007,
abstract = {Component-based detection methods have demonstrated their promise by integrating a set of part-detectors to deal with large appearance variations of the target. However, an essential and critical issue, i.e., how to handle the imperfectness of part-detectors in the integration, is not well addressed in the literature. This paper proposes a detector ensemble model that consists of a set of substructure-detectors, each of which is composed of several part-detectors. Two important issues are studied both in theory and in practice, (1) finding an optimal detector ensemble, and (2) detecting targets based on an ensemble. Based on some theoretical analysis, a new model selection strategy is proposed to learn an optimal detector ensemble that has a minimum number of false positives and satisfies the design requirement on the capacity of tolerating missing parts. In addition, this paper also links ensemble-based detection to the inference in Markov random field, and shows that the target detection can be done by a max-product belief propagation algorithm. {\textcopyright} 2007 IEEE.},
author = {Dai, Shengyang and Yang, Ming and Wu, Ying and Katsaggelos, Aggelos},
booktitle = {2007 IEEE Conference on Computer Vision and Pattern Recognition},
doi = {10.1109/CVPR.2007.383274},
isbn = {1-4244-1179-3},
issn = {10636919},
month = {jun},
pages = {1--8},
publisher = {IEEE},
title = {{Detector Ensemble}},
url = {http://ieeexplore.ieee.org/document/4270299/},
year = {2007}
}
Downloads: 0
{"_id":"gv6v8kewXCh6zH3Ax","bibbaseid":"dai-yang-wu-katsaggelos-detectorensemble-2007","author_short":["Dai, S.","Yang, M.","Wu, Y.","Katsaggelos, A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","abstract":"Component-based detection methods have demonstrated their promise by integrating a set of part-detectors to deal with large appearance variations of the target. However, an essential and critical issue, i.e., how to handle the imperfectness of part-detectors in the integration, is not well addressed in the literature. This paper proposes a detector ensemble model that consists of a set of substructure-detectors, each of which is composed of several part-detectors. Two important issues are studied both in theory and in practice, (1) finding an optimal detector ensemble, and (2) detecting targets based on an ensemble. Based on some theoretical analysis, a new model selection strategy is proposed to learn an optimal detector ensemble that has a minimum number of false positives and satisfies the design requirement on the capacity of tolerating missing parts. In addition, this paper also links ensemble-based detection to the inference in Markov random field, and shows that the target detection can be done by a max-product belief propagation algorithm. © 2007 IEEE.","author":[{"propositions":[],"lastnames":["Dai"],"firstnames":["Shengyang"],"suffixes":[]},{"propositions":[],"lastnames":["Yang"],"firstnames":["Ming"],"suffixes":[]},{"propositions":[],"lastnames":["Wu"],"firstnames":["Ying"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos"],"suffixes":[]}],"booktitle":"2007 IEEE Conference on Computer Vision and Pattern Recognition","doi":"10.1109/CVPR.2007.383274","isbn":"1-4244-1179-3","issn":"10636919","month":"jun","pages":"1–8","publisher":"IEEE","title":"Detector Ensemble","url":"http://ieeexplore.ieee.org/document/4270299/","year":"2007","bibtex":"@inproceedings{Shengyang2007,\nabstract = {Component-based detection methods have demonstrated their promise by integrating a set of part-detectors to deal with large appearance variations of the target. However, an essential and critical issue, i.e., how to handle the imperfectness of part-detectors in the integration, is not well addressed in the literature. This paper proposes a detector ensemble model that consists of a set of substructure-detectors, each of which is composed of several part-detectors. Two important issues are studied both in theory and in practice, (1) finding an optimal detector ensemble, and (2) detecting targets based on an ensemble. Based on some theoretical analysis, a new model selection strategy is proposed to learn an optimal detector ensemble that has a minimum number of false positives and satisfies the design requirement on the capacity of tolerating missing parts. In addition, this paper also links ensemble-based detection to the inference in Markov random field, and shows that the target detection can be done by a max-product belief propagation algorithm. {\\textcopyright} 2007 IEEE.},\nauthor = {Dai, Shengyang and Yang, Ming and Wu, Ying and Katsaggelos, Aggelos},\nbooktitle = {2007 IEEE Conference on Computer Vision and Pattern Recognition},\ndoi = {10.1109/CVPR.2007.383274},\nisbn = {1-4244-1179-3},\nissn = {10636919},\nmonth = {jun},\npages = {1--8},\npublisher = {IEEE},\ntitle = {{Detector Ensemble}},\nurl = {http://ieeexplore.ieee.org/document/4270299/},\nyear = {2007}\n}\n","author_short":["Dai, S.","Yang, M.","Wu, Y.","Katsaggelos, A."],"key":"Shengyang2007","id":"Shengyang2007","bibbaseid":"dai-yang-wu-katsaggelos-detectorensemble-2007","role":"author","urls":{"Paper":"http://ieeexplore.ieee.org/document/4270299/"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","ya2CyA73rpZseyrZ8","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":[],"search_terms":["detector","ensemble","dai","yang","wu","katsaggelos"],"title":"Detector Ensemble","year":2007}