Adaptive hierarchical contexts for object recognition with conditional mixture of trees. Peralta, B., Espinace, P., & Soto, A. In BMVC, 2012. Paper abstract bibtex 4 downloads Robust category-level object recognition is currently a major goal for the computer vision community. Intra-class and pose variations, as well as, background clutter and partial occlusions are some of the main difficulties to achieve this goal. Contextual in- formation, in the form of object co-occurrences and spatial constraints, has been suc- cessfully applied to improve object recognition performance, however, previous work considers only fixed contextual relations that do not depend of the type of scene under inspection. In this work, we present a method that learns adaptive conditional relation- ships that depend on the type of scene being analyzed. In particular, we propose a model based on a conditional mixture of trees that is able to capture contextual relationships among objects using global information about a scene. Our experiments show that the adaptive specialization of contextual relationships improves object recognition accuracy outperforming previous state-of-the-art approaches.
@InProceedings{ peralta:etal:2012,
author = {B. Peralta and P. Espinace and A. Soto},
title = {Adaptive hierarchical contexts for object recognition with
conditional mixture of trees},
booktitle = {{BMVC}},
year = {2012},
abstract = {Robust category-level object recognition is currently a
major goal for the computer vision community. Intra-class
and pose variations, as well as, background clutter and
partial occlusions are some of the main difficulties to
achieve this goal. Contextual in- formation, in the form of
object co-occurrences and spatial constraints, has been
suc- cessfully applied to improve object recognition
performance, however, previous work considers only fixed
contextual relations that do not depend of the type of
scene under inspection. In this work, we present a method
that learns adaptive conditional relation- ships that
depend on the type of scene being analyzed. In particular,
we propose a model based on a conditional mixture of trees
that is able to capture contextual relationships among
objects using global information about a scene. Our
experiments show that the adaptive specialization of
contextual relationships improves object recognition
accuracy outperforming previous state-of-the-art
approaches. },
url = {FinalBMVC-12.pdf}
}
Downloads: 4
{"_id":{"_str":"53427a470e946d920a0018e0"},"__v":1,"authorIDs":["32ZR23o2BFySHbtQK","3ear6KFZSRqbj6YeT","4Pq6KLaQ8jKGXHZWH","54578d9a2abc8e9f370004f0","5e126ca5a4cabfdf01000053","5e158f76f1f31adf01000118","5e16174bf67f7dde010003ad","5e1f631ae8f5ddde010000eb","5e1f7182e8f5ddde010001ff","5e26da3642065ede01000066","5e3acefaf2a00cdf010001c8","5e62c3aecb259cde010000f9","5e65830c6e5f4cf3010000e7","5e666dfc46e828de010002c9","6cMBYieMJhf6Nd58M","6w6sGsxYSK2Quk6yZ","7xDcntrrtC62vkWM5","ARw5ReidxxZii9TTZ","BjzM7QpRCG7uCF7Zf","DQ4JRTTWkvKXtCNCp","GbYBJvxugXMriQwbi","HhRoRmBvwWfD4oLyK","JFk6x26H6LZMoht2n","JvArGGu5qM6EvSCvB","LpqQBhFH3PxepH9KY","MT4TkSGzAp69M3dGt","QFECgvB5v2i4j2Qzs","RKv56Kes3h6FwEa55","Rb9TkQ3KkhGAaNyXq","RdND8NxcJDsyZdkcK","SpKJ5YujbHKZnHc4v","TSRdcx4bbYKqcGbDg","W8ogS2GJa6sQKy26c","WTi3X2fT8dzBN5d8b","WfZbctNQYDBaiYW6n","XZny8xuqwfoxzhBCB","Xk2Q5qedS5MFHvjEW","bbARiTJLYS79ZMFbk","cBxsyeZ37EucQeBYK","cFyFQps7W3Sa2Wope","dGRBfr8zhMmbwK6eP","eRLgwkrEk7T7Lmzmf","fMYSCX8RMZap548vv","g6iKCQCFnJgKYYHaP","h2hTcQYuf2PB3oF8t","h83jBvZYJPJGutQrs","jAtuJBcGhng4Lq2Nd","pMoo2gotJcdDPwfrw","q5Zunk5Y2ruhw5vyq","rzNGhqxkbt2MvGY29","uC8ATA8AfngWpYLBq","uoJ7BKv28Q6TtPmPp","vMiJzqEKCsBxBEa3v","vQE6iTPpjxpuLip2Z","wQDRsDjhgpMJDGxWX","wbNg79jvDpzX9zHLK","wk86BgRiooBjy323E","zCbPxKnQGgDHiHMWn","zf9HENjsAzdWLMDAu"],"author_short":["Peralta, B.","Espinace, P.","Soto, A."],"bibbaseid":"peralta-espinace-soto-adaptivehierarchicalcontextsforobjectrecognitionwithconditionalmixtureoftrees-2012","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["B."],"propositions":[],"lastnames":["Peralta"],"suffixes":[]},{"firstnames":["P."],"propositions":[],"lastnames":["Espinace"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Soto"],"suffixes":[]}],"title":"Adaptive hierarchical contexts for object recognition with conditional mixture of trees","booktitle":"BMVC","year":"2012","abstract":"Robust category-level object recognition is currently a major goal for the computer vision community. Intra-class and pose variations, as well as, background clutter and partial occlusions are some of the main difficulties to achieve this goal. Contextual in- formation, in the form of object co-occurrences and spatial constraints, has been suc- cessfully applied to improve object recognition performance, however, previous work considers only fixed contextual relations that do not depend of the type of scene under inspection. In this work, we present a method that learns adaptive conditional relation- ships that depend on the type of scene being analyzed. In particular, we propose a model based on a conditional mixture of trees that is able to capture contextual relationships among objects using global information about a scene. Our experiments show that the adaptive specialization of contextual relationships improves object recognition accuracy outperforming previous state-of-the-art approaches. ","url":"FinalBMVC-12.pdf","bibtex":"@InProceedings{\t peralta:etal:2012,\n author\t= {B. Peralta and P. Espinace and A. Soto},\n title\t\t= {Adaptive hierarchical contexts for object recognition with\n\t\t conditional mixture of trees},\n booktitle\t= {{BMVC}},\n year\t\t= {2012},\n abstract\t= {Robust category-level object recognition is currently a\n\t\t major goal for the computer vision community. Intra-class\n\t\t and pose variations, as well as, background clutter and\n\t\t partial occlusions are some of the main difficulties to\n\t\t achieve this goal. Contextual in- formation, in the form of\n\t\t object co-occurrences and spatial constraints, has been\n\t\t suc- cessfully applied to improve object recognition\n\t\t performance, however, previous work considers only fixed\n\t\t contextual relations that do not depend of the type of\n\t\t scene under inspection. In this work, we present a method\n\t\t that learns adaptive conditional relation- ships that\n\t\t depend on the type of scene being analyzed. In particular,\n\t\t we propose a model based on a conditional mixture of trees\n\t\t that is able to capture contextual relationships among\n\t\t objects using global information about a scene. Our\n\t\t experiments show that the adaptive specialization of\n\t\t contextual relationships improves object recognition\n\t\t accuracy outperforming previous state-of-the-art\n\t\t approaches. },\n url\t\t= {FinalBMVC-12.pdf}\n}\n\n","author_short":["Peralta, B.","Espinace, P.","Soto, A."],"key":"peralta:etal:2012","id":"peralta:etal:2012","bibbaseid":"peralta-espinace-soto-adaptivehierarchicalcontextsforobjectrecognitionwithconditionalmixtureoftrees-2012","role":"author","urls":{"Paper":"https://raw.githubusercontent.com/ialab-puc/ialab.ing.puc.cl/master/FinalBMVC-12.pdf"},"metadata":{"authorlinks":{"soto, a":"https://asoto.ing.puc.cl/publications/"}},"downloads":4},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/ialab-puc/ialab.ing.puc.cl/master/pubs.bib","downloads":4,"keywords":[],"search_terms":["adaptive","hierarchical","contexts","object","recognition","conditional","mixture","trees","peralta","espinace","soto"],"title":"Adaptive hierarchical contexts for object recognition with conditional mixture of trees","year":2012,"dataSources":["3YPRCmmijLqF4qHXd","sg6yZ29Z2xB5xP79R","sj4fjnZAPkEeYdZqL","m8qFBfFbjk9qWjcmJ","QjT2DEZoWmQYxjHXS"]}