Pose-Guided Feature Alignment for Occluded Person Re-Identification

By Jiaxu Miao, Yu Wu, Ping Liu, Yuhang Ding, Yi Yang. IEEE International Conference on Computer Vision, 2019

606 citations recorded by the source corpus.

Persons are often occluded by various obstacles in person retrieval scenarios. Previous person re-identification (re-id) methods, either overlook this issue or resolve it based on an extreme assumption. To alleviate the occlusion problem, we propose to detect the occluded regions, and explicitly exclude those regions during feature generation and matching. In this paper, we introduce a novel method named Pose-Guided Feature Alignment (PGFA), exploiting pose landmarks to disentangle the useful information from the occlusion noise. During the feature constructing stage, our method utilizes human landmarks to generate attention maps. The generated attention maps indicate if a specific body part is occluded and guide our model to attend to the non-occluded regions. During matching, we explicitly partition the global feature into parts and use the pose landmarks to indicate which partial features belonging to the target person. Only the visible regions are utilized for the retrieval. Besides, we construct a large-scale dataset for the Occluded Person Re-ID problem, namely Occluded-DukeMTMC, which is by far the largest dataset for the Occlusion Person Re-ID. Extensive experiments are conducted on our constructed occluded re-id dataset, two partial re-id datasets, and two commonly used holistic re-id datasets. Our method largely outperforms existing person re-id methods on three occlusion datasets, while remains top performance on two holistic datasets.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/0e6beea0b90b7072c96fd6acd6c7186bd8aeadd1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Diverse Knowledge Distillation for End-to-End Person Search (2020, background): “In person Re-ID community, a major research line is to deal with the misalignment problem caused by occlusions, partial bodies or wrongly detected boxes (Sun et al. 2019; Guo et al. 2019; Sun et al. 2018; Zhao et al. 2020; Miao et al. 2019).”
TransReID: Transformer-based Object Re-Identification (2021, methodology): “We evaluate our proposed method on four person ReID datasets, Market-1501 [45], DukeMTMC-reID [29], MSMT17 [38], Occluded-Duke [26], and two vehicle ReID datasets, VeRi-776 [21] and VehicleID [20].”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, background): “The Pose-Guided Feature Alignment (PGFA) [226] exploits the pose landmarks to mine discriminative part information from occlusion noise.”
Identity-Guided Human Semantic Parsing for Person Re-Identification (2020, background): “Occluded-DukeMTMC [29], which contains 15618 training images, 17661 gallery images, and 2210 occluded query images, is by far the largest and the only occluded person re-ID datasets that contains training set.”
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels (2022, methodology): “We evaluate our method on four person re-identification datasets, including MSMT17 (Wei et al. 2018), Market-1501 (Zheng et al. 2015), DukeMTMC-reID (Ristani et al. 2016), Occluded-Duke (Miao et al. 2019), and two vehicle ReID datasets, VeRi-776 (Liu et al. 2016b) and VehicleID (Liu et al. 2016a).”
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification (2020, methodology): “PFGA [26] uses key-points information and only gets a 82.6% Rank-1 score on DukeMTMC-reID dataset.”
Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer (2021, methodology): “8% mAP on the [37] 67.7 81.9 65.5 74.8 PGFA [30] 68.0 80.0 69.1 80.9 AFPB [61] 78.5 - - - PVPM [5] 78.3 87.7 - - FPR [13] 81.0 - 68.1 - HOReID [40] 85 Occluded-Duke dataset.”