Show simple item record

dc.contributor.authorZhang, Zimingen_US
dc.contributor.authorLiu, Yunen_US
dc.contributor.authorChen, Xien_US
dc.contributor.authorZhu, Yanjunen_US
dc.contributor.authorCheng, Ming-Mingen_US
dc.contributor.authorSaligrama, Venkateshen_US
dc.contributor.authorTorr, Philip H.S.en_US
dc.date.accessioned2018-06-19T18:09:09Z
dc.date.available2018-06-19T18:09:09Z
dc.date.issued2018-05-01
dc.identifierhttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000428901200015&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=6e74115fe3da270499c3d65c9b17d654
dc.identifier.citationZiming Zhang, Yun Liu, Xi Chen, Yanjun Zhu, Ming-Ming Cheng, Venkatesh Saligrama, Philip HS Torr. 2018. "Sequential Optimization for Efficient High-Quality Object Proposal Generation." IEEE Transactions On Pattern Analysis And Machine Intelligence, Volume 40, Issue 5, pp. 1209 - 1223 (15). https://doi.org/10.1109/TPAMI.2017.2707492
dc.identifier.issn0162-8828
dc.identifier.issn1939-3539
dc.identifier.urihttps://hdl.handle.net/2144/29424
dc.description.abstractWe are motivated by the need for a generic object proposal generation algorithm which achieves good balance between object detection recall, proposal localization quality and computational efficiency. We propose a novel object proposal algorithm, BING ++, which inherits the virtue of good computational efficiency of BING [1] but significantly improves its proposal localization quality. At high level we formulate the problem of object proposal generation from a novel probabilistic perspective, based on which our BING++ manages to improve the localization quality by employing edges and segments to estimate object boundaries and update the proposals sequentially. We propose learning the parameters efficiently by searching for approximate solutions in a quantized parameter space for complexity reduction. We demonstrate the generalization of BING++ with the same fixed parameters across different object classes and datasets. Empirically our BING++ can run at half speed of BING on CPU, but significantly improve the localization quality by 18.5 and 16.7 percent on both VOC2007 and Microhsoft COCO datasets, respectively. Compared with other state-of-the-art approaches, BING++ can achieve comparable performance, but run significantly faster.en_US
dc.format.extentp. 1209 - 1223en_US
dc.languageEnglish
dc.publisherIEEEen_US
dc.relation.ispartofIEEE Transactions On Pattern Analysis And Machine Intelligence
dc.subjectScience & technologyen_US
dc.subjectTechnologyen_US
dc.subjectComputer science, artificial intelligenceen_US
dc.subjectEngineering, electrical & electronicen_US
dc.subjectComputer scienceen_US
dc.subjectEngineeringen_US
dc.subjectEfficient high-quality object proposalen_US
dc.subjectObject detectionen_US
dc.subjectSequential minimizationen_US
dc.subjectSVMSen_US
dc.subjectArtificial intelligence and image processingen_US
dc.subjectInformation systemsen_US
dc.subjectElectrical and electronic engineeringen_US
dc.titleSequential optimization for efficient high-quality object proposal generationen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/TPAMI.2017.2707492
pubs.elements-sourceweb-of-scienceen_US
pubs.notesEmbargo: Not knownen_US
pubs.organisational-groupBoston Universityen_US
pubs.organisational-groupBoston University, College of Engineeringen_US
pubs.organisational-groupBoston University, College of Engineering, Department of Electrical & Computer Engineeringen_US
pubs.publication-statusPublisheden_US


This item appears in the following Collection(s)

Show simple item record