Qi Guo

1 month ago | nature.com | Yongxia Li |Jianguang Zhang |Jiajia Guo |Qi Guo |Weihao Qin |Xianbin Wen

Existing unsupervised Re-ID methods often rely on pseudo-labels generated by clustering algorithms. However, the effectiveness of these methods is highly dependent on the quality of the learned features. As a result, improving the quality of the extracted features will highly enhance the performance of the model. In this paper, an attention-based hybrid contrastive learning method (AHCL) is proposed by incorporating a novel attention mechanism, which combines spatial attention and channel attention to enable the model to learn more effective features. Additionally, a hybrid contrastive learning approach is introduced, which utilizes a memory dictionary to store features and extracts both cluster-level and instance-level features for contrastive learning. For cluster-level contrastive loss, it ensures that the network is updated in a more stable way by comparing the sample with the cluster center. Meanwhile, it can extract more discriminative information by comparing the sample with hard samples in instance-level contrastive loss. Thus, the performance of the model would be improved by using the combination of this two loss. The experimental results on three widely-used large-scale Re-ID datasets and experimental settings demonstrate that the proposed AHCL outperforms the compared existing methods and significantly enhances the accuracy of unsupervised person Re-identification.

Nov 19, 2024 | pubs.rsc.org | Ying Zhang |Ming Cheng |Qi Guo |Yabing Shang

Direct electrochemical N2 oxidation to nitrate on supportive Pt/CeO2 Here, we present the development of an efficient Pt/CeO2 catalyst for electrocatalytic N₂ oxidation to nitrate.

Oct 29, 2024 | onlinelibrary.wiley.com | Yanan Zhang |Jing Wang |Rui Li |Qi Guo

Conflict of Interest The authors declare no conflict of interest. Supporting Information Filename Description smll202406850-sup-0001-SuppMat.pdf13.9 MB Supporting Information References 1, , , , , , , , , , Nature 2021, 595, 361. 2, , , , , Mater. Today 2020, 32, 178. 3, , , Nat. Catal. 2019, 2, 578. 4, , , Science 2016, 354, 1378. 5, , Nat. Catal. 2019, 2, 558. 6, , , , Nat. Nanotechnol. 2016, 11, 1020. 7, , J. Phys. Chem. Lett. 2016, 7, 1127.

Aug 20, 2024 | physoc.onlinelibrary.wiley.com | Kun Zhang |Xin Li |Qi Guo |Wei Ding

1 INTRODUCTION Cardiovascular disease (CVD) is an increasingly serious problem as an autonomous predictor of mortality in patients undergoing maintenance hemodialysis (MHD) (Cozzolino et al., 2018; Tong et al., 2016). The US Renal Data System 2021 revealed that the prevalence of CVD in patients receiving MHD was 77.3%, with over half of known deaths being related to CVD (Johansen et al., 2022).

Aug 10, 2024 | onlinelibrary.wiley.com | Yanan Zhang |Rui Li |Xu Wang |Qi Guo

Conflict of Interest The authors declare no conflict of interest. Supporting Information Filename Description adfm202410379-sup-0001-SuppMat.pdf31.4 MB Supporting Information References 1, , , , , , , , , , Nat. Rev. Methods Prim. 2022, 2, 84. 2, , , , , , Adv. Mater. 2021, 33, 2007100. 3, , Chinese J. Catal. 2018, 39, 390. 4, , , , , , , , , Nat. Commun. 2018, 9, 2551. 5, , , Nat. Rev. Chem. 2017, 1, 0003. 6, , , , , , , , , , Nat. Commun. 2023, 14, 1949. 7, , , , Coordin.