Skip to main content
SpringerLink
Log in

Multi-task person re-identification via attribute and part-based learning

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Person re-identification(re-ID) is a challenging task due to the dramatic visual appearance changes from pose, viewpoint, illumination, occlusion, low resolution, and background clutter, etc. Mid-level person attributes are robust to the above mentioned variations and are often exploited as efficient supplement information to promote the performance of person re-ID task. In this paper, we propose a multi-branch network that jointly learns discriminative appearance and complementary attribute representations from both global and local features and mid-level semantic attributes with the supervision of identification loss and verification loss in a unified deep learning model. On the one hand, we design global network, local network, and attribute network to extract global features, local features, and attribute features respectively. On the other hand, we fuse identification loss and verification loss to optimize our model by a multi-task learning strategy. Extensive experiments are conducted on Market1501 and DukeMTMC-reID with attribute annotations to verify the efficiency of our method and competitive performance compared with state-of-the-art algorithms. Specifically, our model achieves 94.45% Rank-1, 92.11% mAP on the Market-1501 dataset and 89.95% Rank-1, 86.49% mAP on the DukeMTMC-reID dataset.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

References

  1. Ahmed E, Jones M, Marks TK (2015) An improved deep learning architecture for person re-identification. 2015 IEEE conference on computer vision and pattern recognition (CVPR), Boston, USA, pp 3908–3916

  2. Bansal M, Kumar M, Kumar M (2021) 2D object recognition: a comparative analysis of SIFT, SURF and ORB feature descriptors. Multimed Tools Appl 80(12):18839–18857

    Article  Google Scholar 

  3. Chih-Yang Lin ZTAX, Akhyar F (2020) Sequential dual attention network for rain streak removal in a single image. IEEE Transactions on Image Processing

  4. Deng J, Dong W, Socher R et al (2009) ImageNet: a large-scale hierarchical image database. 2009 IEEE conference on computer vision and pattern recognition (CVPR), Miami, USA, pp 248–255

  5. Dikmen M, Akbas E, Huang TS et al (2010) Pedestrian Recognition with a Learned Metric. 2010 Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand 6495:501–512

  6. Ding SY, Lin L, Wang GR et al (2015) Deep feature learning with relative distance comparison for person re-identification. Pattern Recogn 48(10):2993–3003

    Article  Google Scholar 

  7. Farenzena M, Bazzani L, Perina A et al (2010) Person re-identification by symmetry-driven accumulation of local features. 2010 IEEE conference on computer vision and pattern recognition (CVPR), San Francisco, USA, pp 2360–2367

  8. Fu Y, Wei YC, Zhou YQ et al (2019) Horizontal pyramid matching for Person Re-Identification. AAAI Conference on Artificial Intelligence, Honolulu, Hawaii, USA, pp 8295–8302

  9. He KM, Zhang XY, Ren SQ et al (2016) Deep residual learning for image recognition. 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, USA, pp 770–778

  10. Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737

  11. Jinghao Luo YLCG (2019) Learning what and where from attributes to improve person re-identification. In 2019 IEEE International Conference on Image Processing (ICIP)

  12. Koestinger M, Hirzer M, Wohlhart P et al (2012) Large scale metric learning from equivalence constraints. 2012 IEEE conference on computer vision and pattern Recognition (CVPR), Rhode Island, USA, pp 2288–2295

  13. Kumar A, Kumar M, Kaur A (2021) Face detection in still images under occlusion and non-uniform illumination. Multimed Tools Appl 80(10):14565–14590

    Article  Google Scholar 

  14. Li Z, Chang SY, Liang F et al (2013) Learning locally-adaptive decision functions for person verification. 2013 IEEE conference on computer vision and pattern Recognition (CVPR), Portland, USA, pp 3610–3617

  15. Li DW, Chen XT, Zhang Z et al (2017) Learning deep context-aware features over body and latent parts for person re-identification. 2017 IEEE conference on computer vision and pattern Recognition (CVPR), Honolulu, Hawaii, USA, pp 7398–7407

  16. Li S, Yu H, Hu R (2020) Attributes-aided part detection and refinement for person re-identification. Pattern Recogn 97:107016

    Article  Google Scholar 

  17. Li W, Zhu XT, Gong SG (2017) Person re-identification by deep joint learning of multi-loss classification’. 2017 26th international joint conference on artificial intelligence (IJCAI), Melbourne, Australia, pp 2194–2200

  18. Li W, Zhu XT, Gong SG (2018) Harmonious attention network for person re-identification. 2018 IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City, USA, pp 2285–2294

  19. Liao SC, Hu Y, Zhu XY et al (2015) Person re-identification by local maximal occurrence representation and metric learning. 2015 IEEE conference on computer vision and pattern Recognition (CVPR), Boston, USA, pp 2197–2206

  20. Lin YT, Zheng L, Zheng ZD et al (2018) Improving person re-identification by attribute and identity learning. Pattern Recogn 95:151–161

    Article  Google Scholar 

  21. Lisanti G, Masi I, Bagdanov AD, Bimbo AD (2015) Person Re-Identification by iterative Re-weighted sparse ranking. IEEE Trans Pattern Anal Mach Intell 37(8):1629–1642

    Article  Google Scholar 

  22. Liu S, Hao XL, Zhang RH et al (2020) Adversarial erasing attention for person re-identification in camera networks under complex environments. IEEE Access 8:56469–56479

    Article  Google Scholar 

  23. Liu JW, Zha ZJ, Xie HT et al (2018) CA3Net: contextual-attentional attribute-appearance network for person re-identification. 2018 ACM multimedia conference on multimedia conference, Seoul, Republic of Korea, pp 737–745

  24. Luo H, Gu YZ, Liao XY et al (2019) Bag of tricks and a strong baseline for deep person re-identification. 2019 IEEE conference on computer vision and pattern recognition workshops (CVPRW), Long Beach, USA, pp 1487–1495

  25. Luo H, Jiang W, Zhang X, Fan X, Qian J, Zhang C (2019) AlignedReID++: dynamically matching local information for person re-identification. Pattern Recogn 94:53–61

    Article  Google Scholar 

  26. Ristani E, Solera F, Zou RS et al (2016) Performance measures and a data set for multi-target, multi-camera tracking. 2016 European conference on computer vision workshops (ECCVW), Amsterdam, Netherlands, vol 9914, pp 17–35

  27. Sarfraz MS, Schumann A, Eberle A et al (2018) A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking’ 2018 IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City, USA, pp 420–429

  28. Schumann A, Stiefelhagen R (2017) Person re-identification by deep learning attribute-complementary information. 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW), Honolulu, Hawaii, USA, pp 1435–1443

  29. Shi ZY, Hospedales TM, Xiang T (2015) Transferring a semantic representation for person re-identification and search. 2015 IEEE conference on computer vision and pattern Recognition (CVPR), Boston, USA, pp 4184–4193

  30. Su C, Li JN, Zhang SL et al (2017) Pose-driven deep convolutional model for person re-identification. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, pp 3980–3989

  31. Su C, Yang F, Zhang SL et al (2018) Multi-task Learning with low rank Attribute embedding for Multi-camera Person Re-Identification. IEEE Trans Pattern Anal Mach Intell 40(5):1167–1181

    Article  Google Scholar 

  32. Su C, Zhang SL, Xing JL et al (2016) Deep attributes driven multi-camera person re-identification. 2016 European conference on computer vision (ECCV), Amsterdam, Netherlands, pp 475–491

  33. Sun YF, Zheng L, Deng WJ et al (2017) SVDNet for pedestrian retrieval. 2017 IEEE international conference on computer vision (ICCV), Venice, Italy, pp 3820–3828

  34. Sun YF, Zheng L, Yang Y et al (2018) Beyond part models: person retrieval with refined part pooling (and a strong convolutional baseline). 2018 European conference on computer vision (ECCV), Munich, Germany, pp 501–518

  35. Tay C, Roy S, Yap K (2019) AANet: attribute attention network for person re-identifications. 2019 IEEE conference on computer vision and pattern recognition (CVPR), Long Beach, CA, USA, pp 7127–7136

  36. Tay CP, Roy S, Yap KH (2020) AANet: attribute attention network for person re-identifications[J]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

  37. Tian H, Zhang X, Lan L, Luo Z (2019) Person re-identification via adaptive verification loss. Neurocomputing 359:93–101

    Article  Google Scholar 

  38. Varior RR, Shuai B, Lu JW et al (2016) A siamese long short-term memory architecture for human re-identification. 2016 European conference on computer vision (ECCV), Amsterdam, Netherlands, pp 135–153

  39. Wang Z, Jiang JJ, Wu Y et al (2020) Learning sparse and identity-preserved hidden attributes for Person Re-Identification. IEEE Trans Image Process 29:2013–2025

    Article  Google Scholar 

  40. Wang GS, Yuan YF, Chen X et al (2018) Learning discriminative features with multiple granularities for person re-identification. 2018 ACM multimedia conference on multimedia conference, Seoul, Republic of Korea, pp 274–282

  41. Wei LH, Zhang SL, Yao HT et al (2017) GLAD: global-local-alignment descriptor for pedestrian retrieval. 2017 ACM international conference on multimedia, New York, USA, pp 420–428

  42. Xiao T, Li HS, Ouyang WL et al (2016) Learning deep feature representations with domain guided dropout for person re-identification. 2016 IEEE conference on computer vision and pattern Recognition (CVPR), Las Vegas, USA, pp 1249–1258

  43. Xie Z, Niu J, Yi L, Lu G (2021) Regularization and attention feature distillation base on light CNN for hyperspectral face recognition[J]. Multimed Tools Appl 1–17

  44. Xie B, Wu XF, Zhang SF et al Learning diverse features with part-level resolution for person re-identification. arXiv preprint arXiv:2001.07442

  45. Xiong F, Gou MR, Camps OI et al (2014) Person re-identification using kernel-based metric learning methods. 2014 European Conference on Computer Vision (ECCV), Zurich, Switzerland 8695:1–16

  46. Yang WX, Yan Y, Chen S (2019) Adaptive deep metric embeddings for person re-identification under occlusions. Neurocomputing 340:125–132

    Article  Google Scholar 

  47. Yeh C, Huang C, Kang L (2020) Multi-Scale Deep Residual Learning-Based single Image haze removal via Image decomposition. IEEE Trans Image Process 29:3153–3167

    Article  Google Scholar 

  48. Zhai Y, Guo X, Lu Y et al (2019) In defense of the classification loss for person re-identification. 2019 IEEE conference on computer vision and pattern recognition workshops (CVPRW), Long Beach, CA, USA, pp 1526–1535

  49. Zhang Y, Gu XS, Tang J et al (2019) Part-Based Attribute-aware Network for Person Re-Identification. IEEE Access 7:53585–53595

    Article  Google Scholar 

  50. Zheng L, Bie Z, Sun YF et al (2016) MARS: a video benchmark for large-scale person re-identification. 2016 European conference on computer vision (ECCV), Amsterdam, Netherlands, pp 868–884

  51. Zheng WS, Gong SG, Xiang T (2013) Reidentification by relative distance comparison. IEEE Trans Pattern Anal Mach Intell 35(3):653–668

    Article  Google Scholar 

  52. Zheng L, Shen L, Tian L et al (2015) Scalable person re-identification: a benchmark. 2015 IEEE international conference on computer vision (ICCV), Santiago, Chile, pp 1116–1124

  53. Zheng L, Yang Y, Hauptmann AG (2016) Person re-identification: past, present and future. arXiv preprint arXiv:1610.02984

  54. Zheng ZD, Zheng L, Yang Y (2017) Unlabeled samples generated by GAN improve the person re-dentification baseline in vitro. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, pp 3774–3782

  55. Zheng ZD, Zheng L, Yang Y (2019) Pedestrian alignment network for large-scale person re-identification. IEEE Transactions on Circuits and Systems for Video Technology, pp 3037–3045

  56. Zhu H, Ma M, Ma W, Jiao L, Hong S, Shen J, Hou B (2021) A spatial-channel progressive fusion ResNet for remote sensing classification. Inf Fusion 70:72–87

    Article  Google Scholar 

Download references

Acknowledgements

This paper is supported by the National Key Research and Development Program of China (2018YFB1306900) and National Natural Science Foundation of China (NO. U1813222).

Author information

Authors and Affiliations

  1. School of Artificial Intelligence, Hebei University of Technology, Tianjin, 300401, People’s Republic of China

    Yuqing Peng, Wei Li, Yingjun Li, Yixin Pei & Yongfang Guo

  2. Hebei Province Key Laboratory of Big Data Calculation, Tianjin, 300401, People’s Republic of China

    Yuqing Peng, Wei Li, Yingjun Li & Yixin Pei

Authors
  1. Yuqing Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wei Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yingjun Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yixin Pei
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yongfang Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yongfang Guo.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Peng, Y., Li, W., Li, Y. et al. Multi-task person re-identification via attribute and part-based learning. Multimed Tools Appl 81, 11221–11237 (2022). https://doi.org/10.1007/s11042-022-12124-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12124-7

Keywords

Search

Navigation