logo

SCIENCE CHINA Information Sciences, Volume 64 , Issue 7 : 179104(2021) https://doi.org/10.1007/s11432-020-3004-7

A spatial structural similarity triplet loss for auxiliary vehicle re-identification

More info
  • ReceivedMay 6, 2020
  • AcceptedJul 24, 2020
  • PublishedDec 7, 2020

Abstract

There is no abstract available for this article.


Acknowledgment

This work was supported in part by National Natural Science Foundation of China (Grant Nos. 61976098, 61871434), in part by National Key RD Program of China (Grant No. 2018YFB0803700), in part by Natural Science Foundation of Fujian Province (Grant No. 2018J01090), in part by Key Science and Technology Project of Xiamen City (Grant No. 3502ZCQ20191005), in part by Science and Technology Bureau of Quanzhou (Grant No. 2018C115R), and in part by China Scholarship Council.


Supplement

Appendixes A and B.


References

[1] Chen H, Lagadec B, Bremond F. Partition and reunion: a two-branch neural network for vehicle re-identification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, 2019. 184--192. Google Scholar

[2] Liu C H, Huynh D Q, Reynolds M. Urban area vehicle re-identification with self-attention stair feature fusion and temporal Bayesian re-ranking. In: Proceedings of International Joint Conference on Neural Networks, Budapest, 2019. Google Scholar

[3] Liu X B, Zhang S L, Huang Q M, et al. Ram: a region-aware deep model for vehicle re-identification. In: Proceedings of IEEE International Conference on Multimedia and Expo, Seattle, 2018. Google Scholar

[4] Zhu J, Zeng H, Huang J. Vehicle Re-Identification Using Quadruple Directional Deep Learning Features. IEEE Trans Intell Transp Syst, 2020, 21: 410-420 CrossRef Google Scholar

[5] Zhu J, Zeng H, Jin X. Joint horizontal and vertical deep learning feature for vehicle re-identification. Sci China Inf Sci, 2019, 62: 199101 CrossRef Google Scholar

[6] Wang Z, Bovik A C, Sheikh H R. Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Trans Image Process, 2004, 13: 600-612 CrossRef ADS Google Scholar

[7] Pan X G, Luo P, Shi J P, et al. Two at once: enhancing learning and generalization capacities via ibn-net. In: Proceedings of European Conference on Computer Vision, Munich, 2018. 464--479. Google Scholar

[8] Liu X C, Liu W, Mei T, et al. A deep learning-based approach to progressive vehicle re-identification for urban surveillance. In: Proceedings of European Conference on Computer Vision, Amsterdam, 2016. 869--884. Google Scholar

[9] Liu H Y, Tian Y H, Wang Y W, et al. Deep relative distance learning: Tell the difference between similar vehicles. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 2016. 2167--2175. Google Scholar

  • Figure 1

    (Color online) The framework of the spatial structural similarity triplet loss auxiliary deep network (S$^3$ANet) for vehicle re-identification. Here, SGAP represents a spatial global average pooling layer; FC-BN-DT represents the composite of fully connected, batch normalization, and dropout layers.