bekvm.blogg.se

238000004891 communication Methods 0.000 claims description 4.238000004590 computer program Methods 0.000 claims description 8.230000001537 neural Effects 0.000 claims abstract description 142.Assignors: JETLEY, SAUMYA, MURRAY, NAILA, VIG, ELEONORA Publication of US20170308770A1 publication Critical patent/US20170308770A1/en Application granted granted Critical Publication of US9830529B2 publication Critical patent/US9830529B2/en Status Active legal-status Critical Current Anticipated expiration legal-status Critical Links Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.) Filing date Publication date Application filed by Xerox Corp filed Critical Xerox Corp Priority to US15/138,821 priority Critical patent/US9830529B2/en Assigned to XEROX CORPORATION reassignment XEROX CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Original Assignee Xerox Corp Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.) ( en Inventor Saumya Jetley Naila Murray Eleonora Vig Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.) Active Application number US15/138,821 Other versions US20170308770A1 Google Patents End-to-end saliency mapping via probability distribution predictionĭownload PDF Info Publication number US9830529B2 US9830529B2 US15/138,821 US201615138821A US9830529B2 US 9830529 B2 US9830529 B2 US 9830529B2 US 201615138821 A US201615138821 A US 201615138821A US 9830529 B2 US9830529 B2 US 9830529B2 Authority US United States Prior art keywords training image neural network saliency map Prior art date Legal status (The legal status is an assumption and is not a legal conclusion. Google Patents US9830529B2 - End-to-end saliency mapping via probability distribution prediction US9830529B2 - End-to-end saliency mapping via probability distribution prediction