Re-id via Discrepancy Matrix and Matrix Metric（IEEE Transactions on Cybernetics 2017）
Abstract 之前的研究工作主要集中通過行人的外觀特點構建一個魯棒性的向量描述，或者通過標籤向量來學習具有判別性的距離度量。本文提出一種新的模式，將特徵描述從特徵向量轉換到差異矩陣。特別地，爲了更好地識別一個人，它將距離度量從向量度量轉換爲矩陣度量，矩陣度量由類間差異投影 intradiscrepancy projection和類內差異投影部分 interdiscrepancy
相關文章
- 1. homography, essential and fundamental matrix
- 2. [Python] 01 - Number and Matrix
- 3. Survey and experimental study on metric learning methods
- 4. D. Walk on Matrix 位運算
- 5. 2019 IEEE Access之ReID: Person Re-Identification Between Visible and Thermal Camera Images Based on
- 6. Toeplitz matrix 與 Circulant matrix
- 7. matrix
- 8. Programmer Competency Matrix
- 9. Understanding the View Matrix
- 10. 深度學習中的Matrix Calculus (2)： Trace And Matrix Differential
- 更多相關文章...
- • W3C RDF and OWL 活動 - W3C 教程
- • XSL-FO table-and-caption 對象 - XSL-FO 教程
- • RxJava操作符（七）Conditional and Boolean
- • 算法總結-二分查找法
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. homography, essential and fundamental matrix
- 2. [Python] 01 - Number and Matrix
- 3. Survey and experimental study on metric learning methods
- 4. D. Walk on Matrix 位運算
- 5. 2019 IEEE Access之ReID: Person Re-Identification Between Visible and Thermal Camera Images Based on
- 6. Toeplitz matrix 與 Circulant matrix
- 7. matrix
- 8. Programmer Competency Matrix
- 9. Understanding the View Matrix
- 10. 深度學習中的Matrix Calculus (2)： Trace And Matrix Differential