کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6864378 | 1439540 | 2018 | 28 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Person re-identification post-rank optimization via hypergraph-based learning
ترجمه فارسی عنوان
بهینه سازی پس از رتبه بندی شخص از طریق یادگیری مبتنی بر هیپرگرا
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
هوش مصنوعی
چکیده انگلیسی
In computer vision, person re-identification has recently received significant attention from researchers and is becoming an emerging research domain with various challenges. Specifically, re-ranking or post-rank optimization is a significant challenge. Existing re-identification methods perform well in certain particular scenarios, but their performance at rank-1 remains a major concern. Such methods cannot model the complex and higher-order relationship among the images. To address such issues, we present a hypergraph-based learning scheme that not only improves the rank-1 accuracy but also models the complex and higher-order relationships among the images. After obtaining the rank list using a baseline method, we apply a new refinement algorithm on it to classify ranks accordingly. Furthermore, to discover the relationship among samples, we utilize the hypergraphs for re-rank learning. A soft assignment technique is used to perform weight learning of hyperedges. The proposed method achieves better ranking performance; consequently, the re-identification is improved. An extensive experimental analysis on challenging and publicly available datasets reveals that the proposed re-ranking scheme performs better than the existing methods.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neurocomputing - Volume 287, 26 April 2018, Pages 143-153
Journal: Neurocomputing - Volume 287, 26 April 2018, Pages 143-153
نویسندگان
Saeed-Ur Rehman, Zonghai Chen, Mudassar Raza, Peng Wang, Qibin Zhang,