Dhff: Robust Multi-Scale Person Search by Dynamic Hierarchical Feature Fusion

Lu, Yan; Hong, Zheran; Liu, Bin; Li, Weihai; Yu, Nenghai

doi:10.1109/icip.2019.8803580

Cited by 6 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IDE+ATT-part [7] proposed a self-matching speed learning method based on attention-guided to balance different occlusion levels. DHFF [40] treats the shallow network as an attention network, which achieved mAP 90.2% and top-1 91.7% on the CUHK-SYSU dataset, and mAP 41.1% and top-1 70.15% on the PRW dataset. QEEPS [4]…”

Section: Comparison With Other Attention Modelsmentioning

confidence: 99%

ABOS: An Attention-Based One-Stage Framework for Person Search

Chen

Han

Cui

et al. 2022

Preprint

View full text Add to dashboard Cite

Person search is of great significance to public safety research, such as crime surveillance, video surveillance and security. Person search is a method of locating and identifying the queried person from a complete set of images. The main cause of false recall and missed detection in person search is the presence of person occlusion in the images. In order to improve the accuracy of person search when the person to be queried is occluded, this paper proposes an attention-based one-stage framework for person search (ABOS) using an anchor-free model as a baseline. The method uses the channel attention module to express different forms of occlusion and take full advantage of the spatial attention module to highlight the target region of the occluded pedestrians. These attention modules integrate deep and shallow features to guide the network to pay attention to the visible area of the occluded target and extract the semantic information of the pedestrians. Experimental results on CUHK-SYSU and PRW datasets show that the proposed person search method based on attention mechanism in this paper has better performance than existing methods, achieving 93.7% of mAP on CUHK-SYSU dataset and 46.4% of mAP on PRW dataset, respectively

show abstract

Section: Comparison With Other Attention Modelsmentioning

confidence: 99%

ABOS: An Attention-Based One-Stage Framework for Person Search

Chen

Han

Cui

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…IDE+ATT-part [9] proposed a self-matching speed learning method based on attention guided to balance different occlusion levels. DHFF [45] treats the shallow network as an attention network, which achieved mAP 90.2% and top-1 91.7% on the CUHK-SYSU dataset, and mAP 41.1% and top-1 70.1% on the PRW dataset. QEEPS [4] proposed an improved QSSE-Net based on Squeeze-and-Excitation attention network, which achieved mAP 88.9% and top-1 89.1% on the CUHK-SYSU dataset, and mAP 37.1% and top-1 76.7% on the PRW dataset.…”

Section: Comparison With Other Attention Modelsmentioning

confidence: 99%

ABOS: an attention-based one-stage framework for person search

Chen

Han

Cui

et al. 2022

J Wireless Com Network

View full text Add to dashboard Cite

Person search is of great significance to public safety research, such as crime surveillance, video surveillance and security. Person search is a method of locating and identifying the queried person from a complete set of images. The main cause of false recall and missed detection in person search is the presence of person occlusion in the images. In order to improve the accuracy of person search when the person to be queried is occluded, this paper proposes an attention-based one-stage framework for person search (ABOS) using an anchor-free model as a baseline. The method uses the channel attention module to express different forms of occlusion and take full advantage of the spatial attention module to highlight the target region of the occluded pedestrians. These attention modules integrate deep and shallow features to guide the network to pay attention to the visible area of the occluded target and extract the semantic information of the pedestrians. Experimental results on CUHK-SYSU and PRW datasets show that the proposed person search method based on attention mechanism in this paper has better performance than existing methods, achieving 93.7$$\%$$ % of mAP on CUHK-SYSU dataset and 46.4$$\%$$ % of mAP on PRW dataset, respectively.

show abstract

“…Query-guided End-to-End Person Search network (QEEPS) [16] is proposed to leverage the query image extensively for person search. Lu et al proposed DHFF [17] to handle the challenge of multi-scale matching faced by person search. Motivated by the above discussions, this paper presents an end-to-end architecture for person search.…”

Section: Introductionmentioning

confidence: 99%

Stable and Effective One-Step Method for Person Search

Xiang

Wang

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Person search, which requires both pedestrian detection and person re-identification, is a challenging computer vision task applied to real-world scenarios. The challenges faced by detection and re-identification, such as occlusion, poor illumination, confusing background, are still urgent for person search. In addition, one-step methods for person search need to deal with the divergence between two tasks. In this work, we propose an end-to-end model containing the feature extractor, the region proposal network, and the multi-task learning module. In order to process divergence between detection and re-identification, we introduce switchable normalization and gradient centralization to improve the stability of the model. To solve the imbalance problem of hard examples, we introduce focal loss as a classification loss in the multi-task learning module. The experimental results on two benchmarks, i.e., CUHK-SYSU and PRW, well demonstrate that our method outperforms the state-of-the-art one-step methods.

show abstract

Dhff: Robust Multi-Scale Person Search by Dynamic Hierarchical Feature Fusion

Cited by 6 publications

References 15 publications

ABOS: An Attention-Based One-Stage Framework for Person Search

ABOS: An Attention-Based One-Stage Framework for Person Search

ABOS: an attention-based one-stage framework for person search

Stable and Effective One-Step Method for Person Search

Contact Info

Product

Resources

About