DIVERSITY REGULARIZED METRIC LEARNING FOR PERSON RE-IDENTIFICATION（ICIP2016）
基於多元正則化度量學習的行人再識別 ABSTRACT 度量學習是行人再識別的有效方法。 它利用潛在因素找到適合測量距離的合適空間。 通常，少數因素不足以匹配行人，而大量因素導致高計算成本。 在本文中，爲了平衡這種操作，提出了一種新的多元正則化距離度量學習方法。 對於特徵表示，從源圖像中提取局部判別特徵，並且提出鄰接最大約束以處理未對準的問題。 然後利用多樣正則化容器通過使潛在因子不相關來學習度量，
相關文章
- 1. 1707.Deep Learning for Person Reidentification Using Support Vector Machines 論文筆記
- 2. Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-ide
- 3. Stepwise Metric Promotion for Unsupervised Video Person Re-identification
- 4. Efficient PSD Constrained Asymmetric Metric Learning for Person Re-identification(MLAPG)
- 5. Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification閱讀筆記
- 6. 論文筆記《Deep Cosine Metric Learning for Person Re-Identification》
- 7. Person Re-identification by Local Maximal Occurrence Representation and Metric Learning（LOMO+XQDA）
- 8. Survey and experimental study on metric learning methods
- 9. Large-scale Distance Metric Learning with Uncertainty
- 10. Few-shot Learning with Meta Metric Learners
- 更多相關文章...
- • Kotlin 繼承 - Kotlin 教程
- • XSD 僅含元素 - XML Schema 教程
- • Java 8 Stream 教程
- • Java Agent入門實戰（一）-Instrumentation介紹與使用
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. 1707.Deep Learning for Person Reidentification Using Support Vector Machines 論文筆記
- 2. Bit-Scalable Deep Hashing with Regularized Similarity Learning for Image Retrieval and Person Re-ide
- 3. Stepwise Metric Promotion for Unsupervised Video Person Re-identification
- 4. Efficient PSD Constrained Asymmetric Metric Learning for Person Re-identification(MLAPG)
- 5. Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification閱讀筆記
- 6. 論文筆記《Deep Cosine Metric Learning for Person Re-Identification》
- 7. Person Re-identification by Local Maximal Occurrence Representation and Metric Learning（LOMO+XQDA）
- 8. Survey and experimental study on metric learning methods
- 9. Large-scale Distance Metric Learning with Uncertainty
- 10. Few-shot Learning with Meta Metric Learners