Local region partition for person re-identification

Multimedia Tools and Applications - Due to the different posture and view angle, the image will appear some objects that do not exist in another image of the same person captured by another camera....     

Low illumination person re-identification

Multimedia Tools and Applications - Low illumination is a common problem for recognition and tracking. Low illumination video-based person re identification (re-id) is an important application in...     

A part-based attention network for person re-identification

Multimedia Tools and Applications - Person re-identification (re-id) is the task of recognizing images of the same pedestrian captured by different cameras with non-overlapping views. Person re-id...     

On-the-fly feature importance mining for person re-identification

State-of-the-art person re-identification methods seek robust person matching through combining various feature types. Often, these features are implicitly assigned with generic weights, which are assumed to be universally and equally good for all individuals, independent of people's different appearances. In this study, we show that certain features play more important role than others under different viewing conditions. To explore this characteristic, we propose a novel unsupervised approach to bottom-up feature importance mining on-the-fly specific to each re-identification probe target image, so features extracted from different individuals are weighted adaptively driven by their salient and inherent appearance attributes. Extensive experiments on three public datasets give insights on how feature importance can vary depending on both the viewing condition and specific person's appearance, and demonstrate that unsupervised bottom-up feature importance mining specific to each probe image can facilitate more accurate re-identification especially when it is combined with generic universal weights obtained using existing distance metric learning methods.     

Learning discriminative features for semi-supervised person re-identification

Multimedia Tools and Applications - We focus on the one-example person re-identification (Re-ID) task, where each identity has only one labeled example along with many unlabeled examples. Since...     

Deep multi-instance learning for end-to-end person re-identification

Multimedia Tools and Applications - In this paper, we introduce a deep multi-instance learning framework to boost the instance-level person re-identification performance. Motivated by the...     

Combined salience based person re-identification

Human eye perceives an object as the entity with global information and local information. Human salience is distinctive local information in matching pedestrians across disjoint camera views, and matching on overall foreground guarantees reliable and robust identification. In this paper, we propose a strategy for the matching of mean salience to identify pedestrians. Also, we consider that person re-identification based on the local single directional matching suffers from the variations of pose, illumination and overlapping, and propose a global bi-directional matching to solve the challenging problems of person re-identification. Furthermore, our matching of mean salience is tightly combined with the global bi-directional matching. Patch matching is utilized to handle the misalignment problem in pedestrian images. We test our feature and matching approaches in person re-identification scenario. Experimental results demonstrate that the mean salience and the global bi-directional matching have promising discriminative capability in comparison with other ones.     

Multi-level feature learning with attention for person re-identification

Person re-identification (re-ID) aims to match a specific person in a large gallery with different cameras and locations. Previous part-based methods mainly focus on part-level features with uniform partition, which increases learning ability for discriminative feature but not efficient or robust to scenarios with large variances. To address this problem, in this paper, we propose a novel feature fusion strategy based on traditional convolutional neural network. Then, a multi-branch deeper feature fusion network architecture is designed to perform discriminative learning for three semantically aligned region. Based on it, a novel self-attention mechanism is employed to softly assign corresponding weights to the semantic aligned feature during back-propagation. Comprehensive experiments have been conducted on several large-scale benchmark datasets, which demonstrates that proposed approach yields consistent and competitive re-ID accuracy compared with current single-domain re-ID methods.

     

Deep learning with particle filter for person re-identification

Person re-identification, having attracted much attention in the multimedia community, is still challenged by the accuracy and the robustness, as the images for the verification contain such variations as light, pose, noise and ambiguity etc. Such practical challenges require relatively robust and accurate feature learning technologies. We introduced a novel deep neural network with PF-BP(Particle Filter-Back Propagation) to achieve relatively global and robust performances of person re-identification. The local optima in the deep networks themselves are still the main difficulty in the learning, in despite of several advanced approaches. A novel neural network learning, or PF-BP, was first proposed to solve the local optima problem in the non-convex objective function of the deep networks. When considering final deep network to learn using BP, the overall neural network with the particle filter will behave as the PF-BP neural network. Also, a max-min value searching was proposed by considering two assumptions about shapes of the non-convex objective function to learn on. Finally, a salience learning based on the deep neural network with PF-BP was proposed to achieve an advanced person re-identification. We test our neural network learning with particle filter aimed to the non-convex optimization problem, and then evaluate the performances of the proposed system in a person re-identification scenario. Experimental results demonstrate that the corresponding performances of the proposed deep network have promising discriminative capability in comparison with other ones.

     

A Siamese inception architecture network for person re-identification

Person re-identification is an extremely challenging problem as person’s appearance often undergoes dramatic changes due to the large variations of viewpoints, illuminations, poses, image resolutions, and cluttered backgrounds. How to extract discriminative features is one of the most critical ways to address these challenges. In this paper, we mainly focus on learning high-level features and combine the low-level, mid-level, and high-level features together to re-identify a person across different cameras. Firstly, we design a Siamese inception architecture network to automatically learn effective semantic features for person re-identification in different camera views. Furthermore, we combine multi-level features in null space with the null Foley–Sammon transform metric learning approach. In this null space, images of the same person are projected to a single point, which minimizes the intra-class scatter to the extreme and maximizes the relative inter-class separation simultaneously. Finally, comprehensive evaluations demonstrate that our approach achieves better performance on four person re-identification benchmark datasets, including Market-1501, CUHK03, PRID2011, and VIPeR.     

Random linear interpolation data augmentation for person re-identification

Person Re-Identification (person re-ID) is an image retrieval task which identifies the same person in different camera views. Generally, a good person re-ID model requires a large dataset containing over 100000 images to reduce the risk of over-fitting. Most current handcrafted person re-ID datasets, however, are insufficient for training a learning model with high generalization ability. In addition, the lacking of images with various levels of occlusion is still remaining in most existing datasets. Motivated by these two problems, this paper proposes a new data augmentation method called Random Linear Interpolation that can enlarge the sizes of person re-ID datasets and improve the generalization ability of the learning model. The key enabler of our approach is generating fused images by interpolating pairs of original images. In other words, the innovation of the proposed approach is considering data augmentation between two random samples. Plenty of experimental results demonstrates that the proposed method is effective to improve baseline models. On Market1501 and DukeMTMC-reID datasets, our approach can achieve 92.71% and 82.19% rank-1 accuracy, respectively.

     

Gait-based person re-identification under covariate factors

Pattern Analysis and Applications - Gait is recognized as an effective behavioral biometric trait. Gait pattern information can be captured and perceived from a distance thanks to its noninvasive...     

Self-attention mechanism in person re-identification models

In recent years, person re-identification based on video has become a hot topic in the field of person re-identification. The self-attention mechanism can improve the ability of deep neural networks in computer vision tasks such as image classification, image segmentation and natural language processing tasks. In order to verify whether the self-attention can improve the performance or not in person re-identification tasks, this paper applies two self-attention mechanisms, non-local attention and recurrent criss-cross attention to person re-identification model, and experiments are conducted on Market-1501, DukeMTMC-reID and MSMT17 person re-identification datasets. The results show that the self-attention mechanism can improve the accuracy of the person re-identification model. The accuracy is higher when the self-attention module is inserted into the convolutional layers of the re-identification network.

     

PLA: progressive learning algorithm for efficient person re-identification

Multimedia Tools and Applications - Inthis paper, we study the problem of Person Re-Identification (ReID) for large-scale applications in the real-world scenarios. Recently most research efforts on...     

Relation network based on multi-granular hypergraphs for person re-identification

Applied Intelligence - In recent years, person re-identification (re-ID) has become a widespread research topic that focuses on retrieving target pedestrians from a set of images, typically taken...     

Sparse coding with cross-view invariant dictionaries for person re-identification

The task of matching observations of the same person in disjoint views captured by non-overlapping cameras is known as the person re-identification problem. It is challenging owing to low-quality images, inter-object occlusions, and variations in illumination, viewpoints and poses. Unlike previous approaches that learn Mahalanobis-like distance metrics, we propose a novel approach based on dictionary learning that takes the advances of sparse coding of discriminatingly and cross-view invariantly encoding features representing different people. Firstly, we propose a robust and discriminative feature extraction method of different feature levels. The feature representations are projected to a lower computation common subspace. Secondly, we learn a single cross-view invariant dictionary for each feature level for different camera views and a fusion strategy is utilized to generate the final matching results. Experimental statistics show the superior performance of our approach by comparing with state-of-the-art methods on two publicly available benchmark datasets VIPeR and PRID 2011.     

Leaning compact and representative features for cross-modality person re-identification

World Wide Web - This paper pays close attention to the cross-modality visible-infrared person re-identification (VI Re-ID) task, which aims to match pedestrian samples between visible and infrared...