Exploiting Web Images for Dataset Construction: A Domain Robust Approach
نویسندگان
چکیده
منابع مشابه
Exploiting weakly-labeled Web images to improve object classification: a domain adaptation approach
Most current image categorization methods require large collections of manually annotated training examples to learn accurate visual recognition models. The time-consuming human labeling effort effectively limits these approaches to recognition problems involving a small number of different object classes. In order to address this shortcoming, in recent years several authors have proposed to le...
متن کاملA New Approach for Real Time Motion Estimation Using Robust Statistics and Mpeg Domain Applied to Mosaic Images Construction
Dominant motion estimation in video sequence is a task that must be often be solved in Computer Vision problems but involves a high computational cost due to the overwhelming amount of data to be treated when working in image domain. In this paper we introduce a novel technique to perform motion analysis in video sequences taking advantage of the motion information of MPEG streams and its struc...
متن کاملCorrections to "Exploiting Web Images for Semantic Video Indexing Via Robust Sample-Specific Loss"
Manuscript received December 04, 2014; accepted December 04, 2014. Date of current version January 15, 2015. Y. Yang is with School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China. Z.-J. Zha is with Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, China. Y. Gao is with Tsinghua National Laboratory for Inf...
متن کاملExploiting Web Images for Semantic Video Indexing Via Robust Sample-Specific Loss
Semantic video indexing, also known as video annotation or video concept detection in literatures, has been attracting significant attention in recent years. Due to deficiency of labeled training videos, most of the existing approaches can hardly achieve satisfactory performance. In this paper, we propose a novel semantic video indexing approach, which exploits the abundant usertagged Web image...
متن کاملa new approach to credibility premium for zero-inflated poisson models for panel data
هدف اصلی از این تحقیق به دست آوردن و مقایسه حق بیمه باورمندی در مدل های شمارشی گزارش نشده برای داده های طولی می باشد. در این تحقیق حق بیمه های پبش گویی بر اساس توابع ضرر مربع خطا و نمایی محاسبه شده و با هم مقایسه می شود. تمایل به گرفتن پاداش و جایزه یکی از دلایل مهم برای گزارش ندادن تصادفات می باشد و افراد برای استفاده از تخفیف اغلب از گزارش تصادفات با هزینه پائین خودداری می کنند، در این تحقیق ...
15 صفحه اولذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Multimedia
سال: 2017
ISSN: 1520-9210,1941-0077
DOI: 10.1109/tmm.2017.2684626