Existing person re-identification methods usually directly calculate the similarities of person pictures regardless of their viewpoints. However, matching persons under different viewpoints is difficult since it is intrinsically hard to directly learn a representation which is geometrically invariant to large viewpoint variations. In this paper, we explicitly take viewpoint information into account and propose a novel Deep Residual Equivariant Mapping and Fine-grained Features (DREMFF) approach for viewpoint-robust person re-identification. Specifically, DREMFF hypothesizes that there exists inherent mapping between different viewpoints of a person, and consequently, the global representation discrepancy of a person under different viewpoints will be bridged through equivariant mapping by adaptively adding residuals to original representation according corresponding angle deviation. What's more, based on attention mechanism, DREMFF extracts fine-grained features for each image from multiple salient regions as well as different scales. These captured information is capable of providing assistant decision-making at lower granularities. The mapped global features and the learned fine-grained features work collaboratively to enable viewpoint-robust person re-identification. Experiments on three challenging benchmarks consistently demonstrate the effectiveness of the proposed approach.

Dictionary learning (DL) is an effective feature learning technique, and has led to interesting results in many classification tasks. Recently, by combining DL with multiple kernel learning (which is a crucial and effective technique for combining different feature representation information), a few multi-kernel DL methods have been presented to solve the multiple feature representations based classification problem. However, how to improve the representation capability and discriminability of multi-kernel dictionary has not been well studied. In this paper, we propose a novel multi-kernel DL approach, named multi-kernel low-rank dictionary pair learning (MKLDPL). Specifically, MKLDPL jointly learns a kernel synthesis dictionary and a kernel analysis dictionary by exploiting the class label information. The learned synthesis and analysis dictionaries work together to implement the coding and reconstruction of samples in the kernel space. To enhance the discriminability of the learned multi-kernel dictionaries, MKLDPL imposes the low-rank regularization on the analysis dictionary, which can make samples from the same class have similar representations. We apply MKLDPL for multiple features based image classification task. Experimental results demonstrate the effectiveness of the proposed approach.

When a company lacks local data in hand, engineers can build an effort model for the effort estimation of a new project by utilizing the training data shared by other companies. However, one of the most important obstacles for data sharing is the privacy concerns of software development organizations. In software engineering, most of existing privacy-preserving works mainly focus on the defect prediction, or debugging and testing, yet the privacy-preserving data sharing problem has not been well studied in effort estimation. In this paper, we aim to provide data owners with an effective approach of privatizing their data before release. We firstly design an Interval Covering based Subclass Division (ICSD) strategy. ICSD can divide the target data into several subclasses by digging a new attribute (i.e., class label) from the effort data. And the obtained class label is beneficial to maintaining the distribution of the target data after obfuscation. Then, we propose a manifold learning based bi-directional data obfuscation (MLBDO) algorithm, which uses two nearest neighbors, which are selected respectively from the previous and next subclasses by utilizing the manifold learning based nearest neighbor selector, as the disturbances to obfuscate the target sample. We call the entire approach as ICSD&MLBDO. Experimental results on seven public effort datasets show that: 1) ICSD&MLBDO can guarantee the privacy and maintain the utility of obfuscated data. 2) ICSD&MLBDO can achieve better privacy and utility than the compared privacy-preserving methods.