@InProceedings{	  peralta:etal:2011,
  author	= {B. Peralta and A. Soto},
  title		= {Mixing Hierarchical Contexts for Object Recognition},
  booktitle	= {{CIARP}},
  year		= {2011},
  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 information in the form of
		  ob- ject co-ocurrences and spatial contraints has been
		  successfully applied to reduce the inherent uncertainty of
		  the visual world. Recently, Choi et al. [5] propose the use
		  of a tree-structured graphical model to capture contextual
		  relations among objects. Under this model there is only one
		  possible fixed contextual relation among subsets of
		  objects. In this work we extent Choi et al. approach by
		  using a mixture model to consider the case that contextual
		  relations among objects depend on scene type. Our
		  experiments highlight the advantages of our proposal,
		  showing that the adaptive specialization of contextual
		  relations improves object recogni- tion and object
		  detection performances. },
  url		= {http://saturno.ing.puc.cl/media/papers_alvaro/Peralta-2011.pdf}
}

{"_id":{"_str":"53427a470e946d920a0018e1"},"__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.","Soto, A."],"bibbaseid":"peralta-soto-mixinghierarchicalcontextsforobjectrecognition-2011","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["B."],"propositions":[],"lastnames":["Peralta"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Soto"],"suffixes":[]}],"title":"Mixing Hierarchical Contexts for Object Recognition","booktitle":"CIARP","year":"2011","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 information in the form of ob- ject co-ocurrences and spatial contraints has been successfully applied to reduce the inherent uncertainty of the visual world. Recently, Choi et al. [5] propose the use of a tree-structured graphical model to capture contextual relations among objects. Under this model there is only one possible fixed contextual relation among subsets of objects. In this work we extent Choi et al. approach by using a mixture model to consider the case that contextual relations among objects depend on scene type. Our experiments highlight the advantages of our proposal, showing that the adaptive specialization of contextual relations improves object recogni- tion and object detection performances. ","url":"http://saturno.ing.puc.cl/media/papers_alvaro/Peralta-2011.pdf","bibtex":"@InProceedings{\t peralta:etal:2011,\n author\t= {B. Peralta and A. Soto},\n title\t\t= {Mixing Hierarchical Contexts for Object Recognition},\n booktitle\t= {{CIARP}},\n year\t\t= {2011},\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 information in the form of\n\t\t ob- ject co-ocurrences and spatial contraints has been\n\t\t successfully applied to reduce the inherent uncertainty of\n\t\t the visual world. Recently, Choi et al. [5] propose the use\n\t\t of a tree-structured graphical model to capture contextual\n\t\t relations among objects. Under this model there is only one\n\t\t possible fixed contextual relation among subsets of\n\t\t objects. In this work we extent Choi et al. approach by\n\t\t using a mixture model to consider the case that contextual\n\t\t relations among objects depend on scene type. Our\n\t\t experiments highlight the advantages of our proposal,\n\t\t showing that the adaptive specialization of contextual\n\t\t relations improves object recogni- tion and object\n\t\t detection performances. },\n url\t\t= {http://saturno.ing.puc.cl/media/papers_alvaro/Peralta-2011.pdf}\n}\n\n","author_short":["Peralta, B.","Soto, A."],"key":"peralta:etal:2011","id":"peralta:etal:2011","bibbaseid":"peralta-soto-mixinghierarchicalcontextsforobjectrecognition-2011","role":"author","urls":{"Paper":"http://saturno.ing.puc.cl/media/papers_alvaro/Peralta-2011.pdf"},"metadata":{"authorlinks":{"soto, a":"https://asoto.ing.puc.cl/publications/"}},"downloads":3},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/ialab-puc/ialab.ing.puc.cl/master/pubs.bib","downloads":3,"keywords":[],"search_terms":["mixing","hierarchical","contexts","object","recognition","peralta","soto"],"title":"Mixing Hierarchical Contexts for Object Recognition","year":2011,"dataSources":["3YPRCmmijLqF4qHXd","sg6yZ29Z2xB5xP79R","sj4fjnZAPkEeYdZqL","m8qFBfFbjk9qWjcmJ","QjT2DEZoWmQYxjHXS"]}