{"_id":"owmizbS77usQJpC4W","bibbaseid":"toro-baier-ruz-soto-howageneralpurposecommonsenseontologycanimproveperformanceoflearningbasedimageretrieval-2017","authorIDs":["32ZR23o2BFySHbtQK","3ear6KFZSRqbj6YeT","4Pq6KLaQ8jKGXHZWH","54578d9a2abc8e9f370004f0","5e126ca5a4cabfdf01000053","5e158f76f1f31adf01000118","5e16174bf67f7dde010003ad","5e1f631ae8f5ddde010000eb","5e1f7182e8f5ddde010001ff","5e26da3642065ede01000066","5e3acefaf2a00cdf010001c8","5e62c3aecb259cde010000f9","5e65830c6e5f4cf3010000e7","5e666dfc46e828de010002c9","6cMBYieMJhf6Nd58M","6w6sGsxYSK2Quk6yZ","7xDcntrrtC62vkWM5","ARw5ReidxxZii9TTZ","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","vMiJzqEKCsBxBEa3v","vQE6iTPpjxpuLip2Z","wQDRsDjhgpMJDGxWX","wbNg79jvDpzX9zHLK","wk86BgRiooBjy323E","zCbPxKnQGgDHiHMWn","zf9HENjsAzdWLMDAu"],"author_short":["Toro, R.","Baier, J.","Ruz, C.","Soto, A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["R."],"propositions":[],"lastnames":["Toro"],"suffixes":[]},{"firstnames":["J."],"propositions":[],"lastnames":["Baier"],"suffixes":[]},{"firstnames":["C."],"propositions":[],"lastnames":["Ruz"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Soto"],"suffixes":[]}],"title":"How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval","booktitle":"IJCAI","year":"2017","abstract":"The knowledge representation community has built general-purpose ontologies which contain large amounts of commonsense knowledge over relevant aspects of the world, including useful visual information, e.g.: \"a ball is used by a football player\", \"a tennis player is located at a tennis court\". Current state-of-the-art approaches for visual recognition do not exploit these rule-based knowledge sources. Instead, they learn recognition models directly from training examples. In this paper, we study how general-purpose ontologies—specifically, MIT's ConceptNet ontology—can improve the performance of state-of-the-art vision systems. As a testbed, we tackle the problem of sentence-based image retrieval. Our retrieval approach incorporates knowledge from ConceptNet on top of a large pool of object detectors derived from a deep learning technique. In our experiments, we show that ConceptNet can improve performance on a common benchmark dataset. Key to our performance is the use of the ESPGAME dataset to select visually relevant relations from ConceptNet. Consequently, a main conclusion of this work is that general-purpose commonsense ontologies improve performance on visual reasoning tasks when properly filtered to select meaningful visual relations. ","url":"https://arxiv.org/abs/1705.08844","bibtex":"@inproceedings{Toro:EtAl:2017,\n Author = {R. Toro and J. Baier and C. Ruz and A. Soto},\n Title = {How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval},\n booktitle = {{IJCAI}},\n year = {2017},\n abstract = {The knowledge representation community has built general-purpose ontologies which contain large amounts of commonsense knowledge over relevant aspects of the world, including useful visual information, e.g.: \"a ball is used by a football player\", \"a tennis player is located at a tennis court\". Current state-of-the-art approaches for visual recognition do not exploit these rule-based knowledge sources. Instead, they learn recognition models directly from training examples. In this paper, we study how general-purpose ontologies---specifically, MIT's ConceptNet ontology---can improve the performance of state-of-the-art vision systems. As a testbed, we tackle the problem of sentence-based image retrieval. Our retrieval approach incorporates knowledge from ConceptNet on top of a large pool of object detectors derived from a deep learning technique. In our experiments, we show that ConceptNet can improve performance on a common benchmark dataset. Key to our performance is the use of the ESPGAME dataset to select visually relevant relations from ConceptNet. Consequently, a main conclusion of this work is that general-purpose commonsense ontologies improve performance on visual reasoning tasks when properly filtered to select meaningful visual relations.\n},\nurl={https://arxiv.org/abs/1705.08844},\n}\n\n\n","author_short":["Toro, R.","Baier, J.","Ruz, C.","Soto, A."],"key":"Toro:EtAl:2017","id":"Toro:EtAl:2017","bibbaseid":"toro-baier-ruz-soto-howageneralpurposecommonsenseontologycanimproveperformanceoflearningbasedimageretrieval-2017","role":"author","urls":{"Paper":"https://arxiv.org/abs/1705.08844"},"metadata":{"authorlinks":{"soto, a":"https://asoto.ing.puc.cl/publications/"}},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"https://asoto.ing.puc.cl/AlvaroPapers.bib","creationDate":"2019-07-23T03:49:04.556Z","downloads":0,"keywords":[],"search_terms":["general","purpose","commonsense","ontology","improve","performance","learning","based","image","retrieval","toro","baier","ruz","soto"],"title":"How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval","year":2017,"dataSources":["3YPRCmmijLqF4qHXd","m8qFBfFbjk9qWjcmJ","QjT2DEZoWmQYxjHXS"]}