dc.contributor.author | Alamri, F | |
dc.contributor.author | Pugeault, N | |
dc.date.accessioned | 2019-06-07T14:18:42Z | |
dc.date.issued | 2019-09-30 | |
dc.description.abstract | Contextual information, such as the co-occurrence of objects and the spatial and relative size among objects provides deep and complex information about scenes. It also can play an important role in improving object detection. In this work, we present two contextual models (rescoring and re-labeling models) that leverage contextual information (16 contextual relationships are applied in this paper) to enhance the state-of-the-art RCNN-based object detection (Faster RCNN). We experimentally demonstrate that our models lead to enhancement in detection performance using the most common dataset used in this field (MSCOCO). | en_GB |
dc.identifier.citation | 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), 19-22 August 2019, Oslo, Norway | en_GB |
dc.identifier.doi | 10.1109/DEVLRN.2019.8850686 | |
dc.identifier.uri | http://hdl.handle.net/10871/37406 | |
dc.language.iso | en | en_GB |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_GB |
dc.rights | © 2019 IEEE. Personal use of this material is permitted. Permis-sion from IEEE must be obtained for all other uses, in any currentor future media, including reprinting/republishing this material foradvertising or promotional purposes, creating new collective works, forresale or redistribution to servers or lists, or reuse of any copyrightedcomponent of this work in other works | en_GB |
dc.subject | Neural Network | en_GB |
dc.subject | object detection | en_GB |
dc.subject | contextual information | en_GB |
dc.subject | rescoring | en_GB |
dc.title | Contextual relabelling of detected objects | en_GB |
dc.type | Conference paper | en_GB |
dc.date.available | 2019-06-07T14:18:42Z | |
dc.description | This is the author accepted manuscript. The final version is available from IEEE via the DOI in this record | en_GB |
dc.rights.uri | http://www.rioxx.net/licenses/all-rights-reserved | en_GB |
dcterms.dateAccepted | 2019-05-07 | |
rioxxterms.version | AM | en_GB |
rioxxterms.licenseref.startdate | 2019-05-07 | |
rioxxterms.type | Conference Paper/Proceeding/Abstract | en_GB |
refterms.dateFCD | 2019-06-07T13:43:39Z | |
refterms.versionFCD | AM | |
refterms.dateFOA | 2019-11-04T14:00:20Z | |
refterms.panel | B | en_GB |