Efficient Local Feature Encoding for Human Action Recognition with Approximate Sparse Coding
Efficient Local Feature Encoding for Human Action Recognition with Approximate Sparse Coding
复制标题
DOI：
10.1587/transinf.2015edp7333
复制
发表时间：
2016-04
期刊：
影响因子：
--
通讯作者：
Yu Wang;Jien Kato
中科院分区：
文献类型：
--
作者：
Yu Wang;Jien Kato
局部时空特征在人类动作识别任务中很流行。在实践中，它们通常与特征编码方法结合使用，这有助于获得可用于学习和识别的视频级向量表示。在本文中，我们提出了一种有效的局部特征编码方法，称为近似稀疏编码（ASC）。 ASC 在离线学习阶段使用稀疏编码（SC）计算大量原型局部特征描述符的稀疏代码，并在编码阶段使用近似最近邻（ANN）搜索为每个待编码的局部特征查找最近的原型的预先计算的稀疏代码。它具有 SC 的低维性和 ANN 的高速度，这都是局部特征编码方法所需的属性。 ASC 在 KTH 数据集和 HMDB51 数据集上被过度评估。我们确认它能够有效地将大量本地视频特征编码为有区别的低维表示。关键词: 近似稀疏编码, 稀疏编码, 近似最近邻, 局部特征编码, 动作识别
Local spatio-temporal features are popular in the human action recognition task. In practice, they are usually coupled with a feature encoding approach, which helps to obtain the video-level vector representations that can be used in learning and recognition. In this paper, we present an efficient local feature encoding approach, which is called Approximate Sparse Coding (ASC). ASC computes the sparse codes for a large collection of prototype local feature descriptors in the off-line learning phase using Sparse Coding (SC) and look up the nearest prototype’s precomputed sparse code for each to-be-encoded local feature in the encoding phase using Approximate Nearest Neighbour (ANN) search. It shares the low dimensionality of SC and the high speed of ANN, which are both desired properties for a local feature encoding approach. ASC has been excessively evaluated on the KTH dataset and the HMDB51 dataset. We confirmed that it is able to encode large quantity of local video features into discriminative low dimensional representations efficiently. key words: approximate sparse coding, sparse coding, approximate nearest neighbour, local feature encoding, action recognition