CoChat
Sign Up
Cited by 25Video Surveillance and Tracking MethodsAdvanced Image and Video Retrieval TechniquesAdvanced Neural Network Applications

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

Salience-Guided Iterative Asymmetric Mutual Hashing for Fast Person Re-Identification

Zhao, Cairong, Tu, Yuanpeng, Lai, Zhihui, Shen, Fumin, Shen, Heng Tao, Miao, Duoqian·2021·IEEE Transactions on Image Processing
DOI 10.1109/tip.2021.3109508
Open this paper in CoChat — free account

Abstract

Person Re-identification (ReID) aims to retrieve the pedestrian with the same identity across different views. Existing studies mainly focus on improving accuracy, while ignoring their efficiency. Recently, several hash based methods have been proposed. Despite their improvement in efficiency, there still exists an unacceptable gap in accuracy between these methods and real-valued ones. Besides, few attempts have been made to simultaneously explicitly reduce redundancy and improve discrimination of hash codes, especially for short ones. Integrating Mutual learning may be a possible solution to reach this goal. However, it fails to utilize the complementary effect of teacher and student models. Additionally, it will degrade the performance of teacher models by treating two models equally. To address these issues, we propose a salience-guided iterative asymmetric mutual hashing (SIAMH) to achieve high-quality hash code generation and fast feature extraction. Specifically, a salience-guided self-distillation branch (SSB) is proposed to enable SIAMH to generate hash codes based on salience regions, thus explicitly reducing the redundancy between codes. Moreover, a novel iterative asymmetric mutual training strategy (IAMT) is proposed to alleviate drawbacks of common mutual learning, which can continuously refine the discriminative regions for SSB and extract regularized dark knowledge for two models as well. Extensive experiment results on five widely used datasets demonstrate th…

Overview

Integrity signals

Registry

Crossref · 10.1109/tip.2021.3109508

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Existing attempts to integrate physics into video generation either add physics losses directly at the pixel level, which is noisy and computationally heavy, or tightly couple a generative model to a specific simulator, limiting flexibility and domain coverage.

    “Existing attempts either (i) add physics losses directly at the pixel level, which is noisy and computationally heavy [51,53,54,57], or (ii) tightly couple a generative model to a specific simulator, limiting flexibility and domain coverage.”

    From PhyStruct-Video: Structured Physics State Spaces for Physically Consistent Video Generation (2025) · cites this paper as [57]

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 58

  1. luo, 2019, Bag of tricks and a strong baseline for deep person re-identification, Proc IEEE/CVF Conf Comput Vis Pattern Recognit Workshops (CVPRW), 1487
  2. li, 2019, Deep multi-index hashing for person re-identification, arXiv 1905 10980
  3. 10.1016/j.patcog.2019.05.036 · DOI
  4. 10.1109/TIP.2015.2467315 · DOI
  5. 10.1109/TIP.2017.2683063 · DOI
  6. lin, 2019, Group re-identification with multi-grained matching and integration, arXiv 1905 07108
  7. yuan, 2019, Revisit knowledge distillation: A teacher-free framework, arXiv 1909 11723
  8. 10.1109/CVPR.2018.00454 · DOI
  9. hinton, 2015, Distilling the knowledge in a neural network, ArXiv 1503 02531
  10. su, 2018, Greedy hash: Towards fast optimization for accurate hash coding in CNN, Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst (NeurIPS), 806
  11. 10.1109/ICCV.2017.598 · DOI · Paper page
  12. chen, 2020, Online knowledge distillation with diverse peers, Proc 34th AAAI Conf Artif Intell (AAAI), 3430
  13. zheng, 2016, Learning cross-view binary identities for fast person re-identification, Proc Intern Joint Conf Artificial Intel (IJCAI), 2399
  14. 10.1609/aaai.v33i01.33013771 · DOI
  15. 10.1109/CVPR.2017.358 · DOI
  16. 10.1007/978-3-030-01270-0_12 · DOI
  17. 10.1109/ICIP.2018.8451107 · DOI
  18. xu, 2018, Deep neural network compression with single and multiple level quantization, Proc 32nd AAAI Conf Artif Intell, 4335
  19. 10.1109/TPAMI.2018.2882816 · DOI
  20. 10.1109/TIP.2017.2695101 · DOI
  21. 10.1109/CVPR.2017.566 · DOI
  22. 10.1007/978-3-030-58598-3_17 · DOI
  23. 10.1109/ICME.2019.00126 · DOI
  24. 10.1109/ICCV.2017.405 · DOI
  25. 10.1109/CVPR.2014.27 · DOI
  26. 10.1109/TPAMI.2012.193 · DOI
  27. liu, 2012, Supervised hashing with kernels, Proc IEEE Conf Comput Vis Pattern Recognit, 2074
  28. 10.1016/j.neucom.2018.04.013 · DOI
  29. 10.1109/CVPR42600.2020.00642 · DOI
  30. he, 2020, FastReID: A pytorch toolbox for general instance re-identification, arXiv 2006 02631
  31. shu, 2021, Large-scale spatio-temporal person re-identification: Algorithm and benchmark, arXiv 2105 15076
  32. 10.1109/CVPR.2018.00016 · DOI · Paper page
  33. 10.1145/3394171.3413979 · DOI
  34. kang, 2016, Column sampling based discrete supervised hashing, Proc 13th AAAI Conf Artif Intell, 1230
  35. 10.1007/978-3-030-01240-3_40 · DOI
  36. 10.1109/CVPR.2015.7298598 · DOI
  37. 10.1145/997817.997857 · DOI
  38. zhao, 2015, Deep semantic ranking based hashing for multi-label image retrieval, Proc IEEE Conf Comput Vis Pattern Recognit (CVPR), 1556
  39. 10.1109/CVPR.2018.00134 · DOI
  40. 10.1109/TIP.2015.2405340 · DOI
  41. 10.1109/TPAMI.2018.2833865 · DOI
  42. 10.1109/CVPR.2015.7298947 · DOI · Paper page
  43. 10.1007/978-3-030-01225-0_30 · DOI
  44. 10.1109/CVPR.2018.00243 · DOI
  45. 10.1609/aaai.v33i01.33018295 · DOI
  46. 10.1109/ICCV.2019.00386 · DOI
  47. 10.1109/ICCV.2019.00844 · DOI
  48. zhang, 2017, Alignedreid: Surpassing human-level performance in person re-identification, arXiv 1711 08184
  49. 10.1109/ICCV.2015.133 · DOI
  50. 10.1145/3240508.3240539 · DOI
  51. 10.1109/ICCV.2019.00380 · DOI
  52. 10.1109/CVPR42600.2020.00336 · DOI
  53. 10.1109/CVPR.2019.00954 · DOI
  54. 10.1109/CVPR.2019.00224 · DOI
  55. 10.1109/CVPR.2018.00117 · DOI
  56. zheng, 2016, Person re-identification: Past, present and future, arXiv 1610 02984
  57. zhang, 2020, Relation-aware global attention for person re-identification, Proc IEEE/CVF Conf Comput Vis Pattern Recognit (CVPR), 3183
  58. 10.1109/CVPR.2019.00048 · DOI

Cited by

Sorted by citations

Metadata

Authors
Zhao, C., Tu, Y., Lai, Z., Shen, F., Shen, H. T., & Miao, D.
Affiliations
  • Tongji University (CN)
  • Shenzhen University (CN)
  • University of Electronic Science and Technology of China (CN)
ORCID
Venue
IEEE Transactions on Image Processing
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2021
Volume
30
Pages
7776-7789
ISSN
  • 1057-7149 (ISSN-L)
  • 1941-0042
DOI
10.1109/tip.2021.3109508
OpenAlex
W3197756237
Cited by
25
References
2
Citations by year
2025: 1 · 2024: 6 · 2023: 7 · 2022: 9 · 2021: 2
FWCI
2.16
Type
journal article
Language
en
Open access
closed
Licence
Locations
  • IEEE Transactions on Image Processing (publishedVersion)
  • PubMed (publishedVersion)
Funders
  • National Natural Science Foundation of China (62076184, 61673299, 61976160, 61573255)
  • Open Research Fund of Key Laboratory of Advanced Theory and Application in Statistics and Data Science (East China Normal University), Ministry of Education
  • Shanghai Innovation Action Project of Science and Technology (20511100700)
  • Fundamental Research Funds for the Central Universities
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
person re-identification, hashing, mutual learning, dark knowledge, fast feature extraction, teacher-student models
MeSH terms
Pedestrians, Algorithms, Humans

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review