Embedding Deep Metric for Person Re-identiﬁcation: A Study Against Large Variations

doi:doi:10.57702/ie18gd07

Embedding Deep Metric for Person Re-identiﬁcation: A Study Against Large Variations

Person re-identiﬁcation is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is distributed as highly-curved manifolds in the feature space, despite the current convolutional neural networks (CNN)’s capability of feature extraction.

BibTex:

@dataset{Hailin_Shi_and_Yang_Yang_and_Xiangyu_Zhu_and_Shengcai_Liao_and_Zhen_Lei_and_Weishi_Zheng_and_Stan_Z_Li_2024,
    abstract = {Person re-identiﬁcation is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is distributed as highly-curved manifolds in the feature space, despite the current convolutional neural networks (CNN)’s capability of feature extraction.},
    author = {Hailin Shi and Yang Yang and Xiangyu Zhu and Shengcai Liao and Zhen Lei and Weishi Zheng and Stan Z. Li},
    doi = {10.57702/ie18gd07},
    institution = {No Organization},
    keyword = {'CNN', 'deep learning', 'person re-identiﬁcation'},
    month = {dec},
    publisher = {TIB},
    title = {Embedding Deep Metric for Person Re-identiﬁcation: A Study Against Large Variations},
    url = {https://service.tib.eu/ldmservice/dataset/embedding-deep-metric-for-person-re-identi-cation--a-study-against-large-variations},
    year = {2024}
}