Long-Term Cloth-Changing Person Re-identification

@article{Qian2020LongTermCP,
  title={Long-Term Cloth-Changing Person Re-identification},
  author={Xuelin Qian and Wenxuan Wang and Li Zhang and Fangrui Zhu and Yanwei Fu and Tao Xiang and Yugang Jiang and X. Xue},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.12633}
}
Person re-identification (Re-ID) aims to match a target person across camera views at different locations and times. Existing Re-ID studies focus on the short-term cloth-consistent setting, under which a person re-appears in different camera views with the same outfit. A discriminative feature representation learned by existing deep Re-ID models is thus dominated by the visual appearance of clothing. In this work, we focus on a much more difficult yet practical setting where person matching is… Expand
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. Expand
Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition
TLDR
A depth guided Adaptive Meta-Fusion Network for few-shot video recognition which is termed as AMeFu-Net, which is trained in the meta-learning way and demonstrates the effectiveness of the model on several action recognition benchmarks. Expand
The P-DESTRE: A Fully Annotated Dataset for Pedestrian Detection, Tracking, and Short/Long-Term Re-Identification From Aerial Devices
TLDR
The P-DESTRE dataset is announced, the first of its kind to provide video/UAV-based data for pedestrian long-term re-identification research, with ID annotations consistent across data collected in different days, and the most problematic data degradation factors and co-variates for UAV- based automated data analysis are identified. Expand
Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization
TLDR
This paper introduces Gait recognition as an auxiliary task to drive the Image ReID model to learn clothagnostic representations by leveraging personal unique and cloth-independent gait information, and adopts a two-stream architecture that consists of a image ReID-Stream and an auxiliary gait recognition stream (Gait-Stream). Expand
Fine-Grained Shape-Appearance Mutual Learning for Cloth-Changing Person Re-Identification
TLDR
A Fine-grained Shape-Appearance Mutual learning framework (FSAM), a two-stream framework that learns finegrained discriminative body shape knowledge in a shape stream and transfers it to an appearance stream to complement the cloth-unrelated knowledge in the appearance features, is proposed. Expand
Learning 3D Shape Feature for Texture-Insensitive Person Re-Identification
TLDR
This paper proposes a novel ReID learning framework that directly extracts a texture-insensitive 3D shape embedding from a 2D image by adding 3D body reconstruction as an auxiliary task and regularization, called 3D Shape Learning (3DSL). Expand
Adversarial Feature Disentanglement for Long-Term Person Re-identification
  • Wanlu Xu, Hong Liu, Wei Shi, Ziling Miao, Zhisheng Lu, Feihu Chen
  • Computer Science
  • IJCAI
  • 2021
TLDR
An adversarial feature disentanglement network (AFD-Net) which contains intra-class reconstruction and inter-class adversary to disentangle the identity-related and identity-unrelated (clothing) features. Expand
DeepChange: A Long-Term Person Re-Identification Benchmark
TLDR
A large, realistic long-term person reidentification benchmark consisting of 178K bounding boxes from 1.1K person identities, collected and constructed over 12 months, and provides insightful observations and analysis with more realistic performance metrics. Expand
Large-Scale Spatio-Temporal Person Re-identification: Algorithm and Benchmark
TLDR
This work contributes a novel Large-scale Spatio-Temporal (LaST) person re- ID dataset, including 10,860 identities with more than 224k images, and proposes an easy-to-implement baseline that works well on such challenging re-ID setting. Expand
Long-term Person Re-identification: A Benchmark
TLDR
This work contributes timely a large, realistic long-term person re-identification benchmark consisting of 171K bounding boxes from 1.1K person identities, collected and constructed over a course of 12 months. Expand
...
1
2
...

References

SHOWING 1-10 OF 61 REFERENCES
Celebrities-ReID: A Benchmark for Clothes Variation in Long-Term Person Re-Identification
TLDR
A benchmark approach to the dataset where a two-step fine-tuning strategy on human body parts is introduced to tackle the challenge of clothes variation achieves competitive performance on a widely used person re-ID dataset Market1501, which proves the reliability of the proposed benchmark approach. Expand
Person Re-Identification by Contour Sketch Under Moderate Clothing Change
  • Q. Yang, Ancong Wu, W. Zheng
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2021
TLDR
This work performs cross-clothes person re-id based on a contour sketch of person image to take advantage of the shape of the human body instead of color information for extracting features that are robust to moderate clothing change, and develops a multistream network for aggregating multi-granularity features to better identify a person. Expand
Beyond Scalar Neuron: Adopting Vector-Neuron Capsules for Long-Term Person Re-Identification
TLDR
Experimental results show that the ReIDCaps network can outperform existing state-of-the-art methods by a large margin in the long-term scenario and Soft Embedding Attention and Feature Sparse Representation mechanisms are adopted in the network for performance boosting. Expand
Color-Sensitive Person Re-Identification
TLDR
A novel Color-Sensitive Re-ID to take full advantage of color information and a novel Color Translation GAN (CTGAN) to learn mappings between different clothing colors and preserve identity consistency among the same person with the clothing color is proposed. Expand
Learning a Discriminative Null Space for Person Re-identification
  • Li Zhang, T. Xiang, S. Gong
  • Computer Science, Mathematics
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
TLDR
This work proposes to overcome the SSS problem in re-id distance metric learning by matching people in a discriminative null space of the training data, which has a fixed dimension, a closed-form solution and is very efficient to compute. Expand
Leader-Based Multi-Scale Attention Deep Architecture for Person Re-Identification
TLDR
A deep re-id network (MuDeep) that is composed of two novel types of layers – a multi-scale deep learning layer, and a leader-based attention learning layer that outperforms the state-of-the-art on a number of benchmarks and has a better generalization ability under a domain generalization setting. Expand
Person Transfer GAN to Bridge Domain Gap for Person Re-identification
TLDR
A Person Transfer Generative Adversarial Network (PTGAN) is proposed to relieve the expensive costs of annotating new training samples and comprehensive experiments show that the domain gap could be substantially narrowed-down by the PTGAN. Expand
Harmonious Attention Network for Person Re-identification
  • Wei Li, Xiatian Zhu, S. Gong
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
TLDR
A novel Harmonious Attention CNN (HA-CNN) model is formulated for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images. Expand
Joint Discriminative and Generative Learning for Person Re-Identification
TLDR
This paper proposes a joint learning framework that couples re-id learning and data generation end-to-end and renders significant improvement over the baseline without using generated data, leading to the state-of-the-art performance on several benchmark datasets. Expand
End-to-End Deep Kronecker-Product Matching for Person Re-identification
TLDR
A novel Kronecker Product Matching module to match feature maps of different persons in an end-to-end trainable deep neural network that outperforms state-of-the-art methods on the Market-1501, CUHK03, and DukeMTMC datasets, which demonstrates the effectiveness and generalization ability of the proposed approach. Expand
...
1
2
3
4
5
...