Person Re-Identification by Semantic Region Representation and Topology Constraint

@article{Lei2019PersonRB,
  title={Person Re-Identification by Semantic Region Representation and Topology Constraint},
  author={Jianjun Lei and Lijie Niu and H. Fu and Bo Peng and Qingming Huang and Chunping Hou},
  journal={IEEE Transactions on Circuits and Systems for Video Technology},
  year={2019},
  volume={29},
  pages={2453-2466}
}
Person re-identification is a popular research topic which aims at matching the specific person in a multi-camera network automatically. Feature representation and metric learning are two important issues for person re-identification. In this paper, we propose a novel person re-identification method, which consists of a reliable representation called semantic region representation (SRR), and an effective metric learning with mapping space topology constraint (MSTC). The SRR integrates semantic… 

Semantic-Aware Occlusion-Robust Network for Occluded Person Re-Identification

TLDR
A novel semanticaware occlusion-robust network (SORN) is proposed that effectively exploits the intrinsic relationship between the tasks of person Re-ID and semantic segmentation for occluded person reidentification.

Jointly Learning Commonality and Specificity Dictionaries for Person Re-Identification

TLDR
A framework for learning a pair of commonality and specificity dictionaries is developed, while introducing a distance constraint to force the particularities of the same person over the specificity dictionary to have the same coding coefficients and the coding coefficients of different pedestrians to have weak correlation.

A benchmark for clothes variation in person re‐identification

TLDR
A new benchmark data set for person re‐identification with clothes variation is introduced that contains 107 persons with 9,738 images, captured in 15 indoor/outdoor scenes from September 2019 to December 2019, varying according to viewpoints, lighting, resolutions, human pose, seasons, backgrounds, and clothes especially.

Attribute-Identity Embedding and Self-Supervised Learning for Scalable Person Re-Identification

TLDR
This work develops an attribute-identity joint prediction dictionary learning model for simultaneously learning a latent attribute space, a semantic attribute dictionary and an identifier, and proposes a prediction-training cycle self-supervised learning to tune the model variables to make them more adaptive in the target domain.

Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval

TLDR
A novel semi-heterogeneous three-way joint embedding network (Semi3-Net) is proposed, which integrates three branches (a sketch branch, a natural image branch, and an edgemap branch) to learn more discriminative cross-domain feature representations for the SBIR task.

Learning to Acquire the Quality of Human Pose Estimation

TLDR
End-to-end human pose quality learning is proposed, which adds a quality prediction block alongside pose regression that learns the object keypoint similarity (OKS) between the estimated pose and its corresponding ground truth by sharing the pose features with heatmap regression.

ANL: Anti-Noise Learning for Cross-Domain Person Re-Identification

TLDR
The experiments demonstrate that the proposed ANL framework can effectively reduce the domain conflicts and alleviate the influence of noisy samples, as well as superior performance compared with the state-of-the-art methods.

Hierarchical Dynamic Programming Module for Human Pose Refinement

TLDR
This paper proposes a simple yet effective module to refine the estimated pose by exploiting the temporal coherency among the heatmaps of adjacent frames, which can be easily inserted into image-based networks as a plug-in.

CNN-Based Macropixel-Level Up-Sampling for Plenoptic Image Coding

TLDR
A convolutional neural network (CNN)-based macropixel-level up-sampling method for plenoptic image coding that achieves considerable bitrate reduction compared with the HEVC/H.265 format SCC extension profile.

Angle-Closure Detection in Anterior Segment OCT Based on Multilevel Deep Network

TLDR
An automated system based on deep learning is presented for angle-closure detection in AS-OCT images, which is shown to surpass previous detection methods and other deep learning systems on two clinical AS- OCT datasets.

References

SHOWING 1-10 OF 80 REFERENCES

Point to Set Similarity Based Deep Feature Learning for Person Re-Identification

TLDR
A novel person Re-ID method based on P2S similarity comparison that can jointly minimize the intra- class distance and maximize the inter-class distance, while back-propagating the gradient to optimize parameters of the deep model.

Person re-identification by Local Maximal Occurrence representation and metric learning

TLDR
This paper proposes an effective feature representation called Local Maximal Occurrence (LOMO), and a subspace and metric learning method called Cross-view Quadratic Discriminant Analysis (XQDA), and presents a practical computation method for XQDA.

Sample-Specific SVM Learning for Person Re-identification

TLDR
A Least Square Semi-Coupled Dictionary Learning algorithm is proposed to learn a pair of dictionaries and a mapping function efficiently and performs favorably against the state-of-the-art approaches, especially on the rank-1 recognition rate.

Similarity Learning with Spatial Constraints for Person Re-identification

TLDR
This work learns a novel similarity function, which consists of multiple sub-similarity measurements with each taking in charge of a subregion, and takes advantage of the recently proposed polynomial feature map to describe the matching within each subregion and inject all the feature maps into a unified framework.

Deeply-Learned Part-Aligned Representations for Person Re-identification

TLDR
This paper proposes a simple yet effective human part-aligned representation for handling the body part misalignment problem, and shows state-of-the-art results over standard datasets, Market-1501,CUHK03, CUHK01 and VIPeR.

Learning Correspondence Structures for Person Re-Identification

TLDR
This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification by introducing a boosting-based approach to learn a correspondence structure, which indicates the patchwise matching probabilities between images from a target camera pair and introduces a global constraint-based matching process.

Discriminant Context Information Analysis for Post-Ranking Person Re-Identification

TLDR
This work proposes to achieve an unsupervised post-ranking framework for person re-identification by introducing an analysis of the similar appearances of the first ranks which remarkably improves the first rank results and outperforms the state-of-the-art approaches.

Person Reidentification Using Attribute-Restricted Projection Metric Learning

TLDR
The main idea of the method is to learn a low-dimensional metric space, in which the features extracted from different observations of the same person are pulled, and the features extracts from observations of different persons but in the neighborhood of original feature space are pushed.

Person Re-Identification by Saliency Learning

TLDR
This work proposes a novel perspective for person re-identification based on learning person saliency and matching saliency distribution and proposes two alternative methods, i.e., K-Nearest Neighbors and One-class SVM, to estimate a saliency score for each image patch, through which distinctive features stand out without using identity labels in the training procedure.
...