.png){kind=icon}
返回
Regularized discriminant embedding for visual descriptor learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2014.07.029.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Visual descriptor learning seeks a projection to embed local descriptors (e.g., SIFT descriptors) into a new Euclidean space where pairs of matching descriptors (positive pairs) are better separated from pairs of non-matching descriptors (negative pairs). The original descriptors often confuse the positive pairs with the negative pairs, since local points labeled non-matching yield descriptors close together (irrelevant-near) or local points labeled matching yield descriptors far apart (relevant-far). This is because images differ in terms of viewpoint, resolution, noise, and illumination. In this paper, we formulate an embedding as a regularized discriminant analysis, which emphasizes relevant-far pairs and irrelevant-near pairs to better separate negative pairs from positive pairs. We then extend our method to nonlinear mapping by employing recent work on explicit kernel mapping. Experiments on object retrieval for landmark buildings in Oxford and Paris demonstrate the high performance of our method, compared to existing methods. (C) 2014 Elsevier B.V. All rights reserved.
Keyword:
Discriminant analysis
Kernel method
Local descriptor
Object retrieval
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
.png){kind=icon}
分享收藏Unsupervised Semantic Feature Discovery for Image Object Retrieval and Tag Refinement面向图像对象检索和标签细化的无监督语义特征发现
OAAI
OAAI分享收藏分享收藏分享收藏Involuntary oculomotor inhibition markers of saliency and deviance in response to auditory sequencesOAAI
OAAI分享收藏RANDOM SAMPLE CONSENSUS - A PARADIGM FOR MODEL-FITTING WITH APPLICATIONS TO IMAGE-ANALYSIS AND AUTOMATED CARTOGRAPHY随机样本共识-模型拟合的范例，可应用于图像分析和自动制图OAAI
OAAI分享收藏分享收藏
查看更多内容