Diffusion-on-Manifold Aggregation of Local Features for Shape-based 3D Model Retrieval
Diffusion-on-Manifold Aggregation of Local Features for Shape-based 3D Model Retrieval
复制标题
DOI：
10.1145/2671188.2749380
复制
发表时间：
2015-06
期刊：
影响因子：
--
通讯作者：
T. Furuya;Ryutarou Ohbuchi
中科院分区：
文献类型：
--
作者：
T. Furuya;Ryutarou Ohbuchi
聚集一组局部特征已经成为表示诸如2D图像和3D模型等多媒体数据的最常用方法之一。Bag-of-Feature(BF)聚集[2]的成功促使了BF的几个扩展，即VLAD[12]、Fisher向量(FV)编码[22]和超级向量(SV)编码[34]。它们都是通过聚类一组大量的局部特征来学习少量的码字或具有代表性的局部特征。通过考虑码字周围的特征的分布来编码从媒体数据(例如，图像)提取的局部特征集；BF使用频率，VLAD和FV使用位移向量，并且SV使用两者的组合。在这样做时，这些编码算法假设关于码字的特征空间的线性。因此，即使特征集形成非线性流形，其非线性也将被忽略，潜在地降低聚集特征的质量。本文提出了一种新的特征聚合算法，称为流形上扩散算法(DM)，它试图通过扩散距离来考虑由局部特征集形成的非线性流形的结构。在三维形状检索方面，我们还提出了一种面向定向点集的局部三维形状特征。使用基于形状的3D模型检索场景进行的实验表明，DM聚集比现有的聚集算法VLAD、FV和SV等具有更好的检索精度。
Aggregating a set of local features has become one of the most common approaches for representing a multi-media data such as 2D image and 3D model. The success of Bag-of-Features (BF) aggregation [2] prompted several extensions to BF, that are, VLAD [12], Fisher Vector (FV) coding [22] and Super Vector (SV) coding [34]. They all learn small number of codewords, or representative local features, by clustering a set of large number of local features. The set of local features extracted from a media data (e.g., an image) is encoded by considering distribution of features around the codewords; BF uses frequency, VLAD and FV uses displacement vector, and SV uses a combination of both. In doing so, these encoding algorithms assume linearity of feature space about a codeword. Consequently, even if the set of features form a non-linear manifold, its non-linearity would be ignored, potentially degrading quality of aggregated features. In this paper, we propose a novel feature aggregation algorithm called Diffusion-on-Manifold (DM) that tries to take into account, via diffusion distance, structure of non-linear manifold formed by the set of local features. In view of 3D shape retrieval, we also propose a local 3D shape feature defined for oriented point set. Experiments using shape-based 3D model retrieval scenario show that the DM aggregation results in better retrieval accuracy than the existing aggregation algorithms we've compared against, that are, VLAD, FV, and SV, etc..