{"type":"ScholarlyArticle","title":"Object Recognition with Hidden Attributes","authors":[{"name":"Xiaoyang Wang","slug":"xiaoyang-wang","given":"Xiaoyang","family":"Wang","affiliation":""},{"name":"Qiang Ji","slug":"qiang-ji","given":"Qiang","family":"Ji","affiliation":""}],"abstract":"Attribute based object recognition performs object recognition using the semantic properties of the object. Unlike the existing approaches that treat attributes as a middle level representation and require to estimate the attributes during testing, we propose to incorporate the hidden attributes, which are the attributes used only during training to improve model learning and are not needed during testing. To achieve this goal, we develop two different approaches to incorporate hidden attributes. The first approach utilizes hidden attributes as additional information to improve the object classification model. The second approach further exploits the semantic relationships between the objects and the hidden attributes. Experiments on benchmark data sets demonstrate that both approaches can effectively improve the learning of the object classifiers over the baseline models that do not use attributes, and their combination reaches the best performance. Experiments also show that the proposed approaches outperform both state of the art methods that use attributes as middle level representation and the approaches that learn the classifiers with hidden information.","doi":null,"url":"https://ijcai.org/proceedings/2016/494","pdf":"https://ijcai.org/proceedings/2016/0494.pdf","markdown":"https://ijcai.org/proceedings/2016/494.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/494","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":494,"pages":{"first":3498,"last":3503},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}