Abstract
Pedestrian attributes recognition draw significant interest in the field of intelligent video surveillance. Despite that the convolutional neural networks are remarkable in learning discriminative features from images, the learning of comprehensive features of pedestrians for fine-grained tasks remains an challenging problem. In this paper, we proposed a novel multi-level skip connections and squeeze-and-excitation convolutional neural network (MSE-Net), which is composed of multi-level skip connections (MLSC) and Squeeze-and-Excitation blocks (SE-Blocks). Additionally, the proposed MSE-Net brings unique advantages: (1) Multi-level skip connections (MLSC) obtain more meaningful fine-grained information from both the low-level and high-level features and can maintain gradient flow in the network. For fine-grained attributes, such as glasses and accessories, MLSC retains fine-grained information and local information from shallow layers; (2) Squeeze-and-Excitation blocks (SE-blocks) strengthen the sensitivity of the network to information, compress the features, and perceive global receptive field. It can select important feature channels, and then weights the previous features by multiplication and then recalibrates the original features in the channel dimension. Intensive experimental results have been provided to prove that the proposed network outperforms the state-of-the-art methods on RAP dataset, and the robustness against predicting positive and negative samples in each attribute.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, A., Liu, L., Wang, K., Liu, S., Yan, S.: Clothing attributes assisted person reidentification. IEEE Trans. Circuits Syst. Video Technol. 25(5), 869–878 (2015)
Peng, P., Tian, Y., Xiang, T., Wang, Y., Huang, T.: Joint learning of semantic and latent attributes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 336–353. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_21
Reid, D.A., Nixon, M.S., Stevenage, S.V.: Soft biometrics; human identification using comparative descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1216 (2014)
Su, C., Zhang, S., Xing, J., Gao, W., Tian, Q.: Multi-type attributes driven multi-camera person re-identification. Pattern Recogn. 75, 77–89 (2017)
Sun, Y., Zheng, L., Deng, W., Wang, S.: Svdnet for pedestrian retrieval. In: IEEE International Conference on Computer Vision, pp. 3820–3828 (2017)
Hall, D., Perona, P.: Fine-grained classification of pedestrians in video: benchmark and state of the art. In: Computer Vision and Pattern Recognition (2015)
Zhu, J., Liao, S., Lei, Z., Li, S.Z.: Multi-label convolutional neural network based pedestrian attribute classification. Image Vis. Comput. 58(C), 224–229 (2017)
Zhou, Y., et al.: Weakly-supervised learning of mid-level features for pedestrian attribute recognition and localization. In: BMVC (2017)
Lin, Y.: Weighted sparse image classification based on low rank representation. Comput. Mater. Continua 56(1), 91–105 (2018)
Fang, W., Zhang, F., Sheng, V.S., Ding, Y.: A method for improving CNN-based image recognition using dcgan. Comput. Mater. Continua 57, 167–178 (2018)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Layne, R., Hospedales, T.M., Gong, S.: Towards person identification and re-identification with attributes. In: Fusiello, A., Murino, V., Cucchiara, R. (eds.) ECCV 2012. LNCS, vol. 7583, pp. 402–412. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33863-2_40
Layne, R., Hospedales, T.M., Gong, S., Mary, Q.: Person re-identification by attributes. In: BMVC, p. 8 (2012)
Zhu, J., Liao, S., Lei, Z., Yi, D., Li, S.Z.: Pedestrian attribute classification in surveillance: database and evaluation. In: IEEE International Conference on Computer Vision Workshops, pp. 331–338 (2013)
Zhu, J., Liao, S., Lei, Z., Li, S.Z.: Multi-label convolutional neural network based pedestrian attribute classification. Image Vis. Comput. 58, 224–229 (2017)
Deng, Y., Luo, P., Chen, C.L., Tang, X.: Pedestrian attribute recognition at far distance. In: ACM International Conference on Multimedia. pp. 789–792 (2014)
Maji, S., Berg, A.C., Malik, J.: Classification using intersection kernel support vector machines is efficient. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8 (2008)
Sudowe, P., Spitzer, H., Leibe, B.: Person attribute recognition with a jointly-trained holistic CNN model. In: IEEE International Conference on Computer Vision Workshop, pp. 329–337 (2015)
Li, D., Chen, X., Huang, K.: Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 111–115 (2015)
Zhang, N., Paluri, M., Ranzato, M., Darrell, T., Bourdev, L.: Panda: pose aligned networks for deep attribute modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1637–1644 (2014)
Sharma, G., Jurie, F., Schmid, C.: Expanded parts model for human attribute and action recognition in still images. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp. 652–659 (2013)
Zhu, J., Liao, S., Yi, D., Lei, Z., Li, S.Z.: Multi-label CNN based pedestrian attribute learning for soft biometrics. In: International Conference on Biometrics, pp. 535–540 (2015)
Li, D., Zhang, Z., Chen, X., Ling, H., Huang, K.: A richly annotated dataset for pedestrian attribute recognition. arXiv preprint arXiv:1603.07054 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 pp. 448–456 (2015)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. arXiv preprint arXiv:1709.01507 (2017)
Gray, D., Tao, H.: Viewpoint invariant pedestrian recognition with an ensemble of localized features. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 262–275. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-88682-2_21
Prosser, B.J., Zheng, W.S., Gong, S., Xiang, T., Mary, Q.: Person re-identification by support vector ranking. In: BMVC, p. 6 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Lou, M., Yu, Z., Guo, F., Zheng, X. (2019). MSE-Net: Pedestrian Attribute Recognition Using MLSC and SE-Blocks. In: Sun, X., Pan, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2019. Lecture Notes in Computer Science(), vol 11632. Springer, Cham. https://doi.org/10.1007/978-3-030-24274-9_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-24274-9_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24273-2
Online ISBN: 978-3-030-24274-9
eBook Packages: Computer ScienceComputer Science (R0)