Abstract
Gait recognition, which aims at identifying individuals by their walking patterns, has recently drawn increasing research attention. However, gait recognition still suffers from the conflicts between the limited binary visual clues of the silhouette and numerous covariates with diverse scales, which brings challenges to the model’s adaptiveness. In this paper, we address this conflict by developing a novel MetaGait that learns to learn an omni sample adaptive representation. Towards this goal, MetaGait injects meta-knowledge, which could guide the model to perceive sample-specific properties, into the calibration network of the attention mechanism to improve the adaptiveness from the omni-scale, omni-dimension, and omni-process perspectives. Specifically, we leverage the meta-knowledge across the entire process, where Meta Triple Attention and Meta Temporal Pooling are presented respectively to adaptively capture omni-scale dependency from spatial/channel/temporal dimensions simultaneously and to adaptively aggregate temporal information through integrating the merits of three complementary temporal aggregation methods. Extensive experiments demonstrate the state-of-the-art performance of the proposed MetaGait. On CASIA-B, we achieve rank-1 accuracy of 98.7%, 96.0%, and 89.3% under three conditions, respectively. On OU-MVLP, we achieve rank-1 accuracy of 92.4%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Antoniou, A., Edwards, H., Storkey, A.: How to train your MAML. arXiv preprint arXiv:1810.09502 (2018)
Ariyanto, G., Nixon, M.S.: Model-based 3D gait biometrics. In: International Joint Conference on Biometrics, pp. 1–7 (2011)
Balazia, M., Plataniotis, K.N.: Human gait recognition from motion capture data in signature poses. IET Biom. 6, 129–137 (2017)
Bashir, K., Xiang, T., Gong, S.: Gait recognition using gait entropy image. In: IET International Conference on Imaging for Crime Detection and Prevention, pp. 1–6 (2009)
Bengio, E., Bacon, P.L., Pineau, J., Precup, D.: Conditional computation in neural networks for faster models. arXiv preprint arXiv:1511.06297 (2015)
Bodor, R., Drenner, A., Fehr, D., Masoud, O., Papanikolopoulos, N.: View-independent human motion classification using image-based reconstruction. Image Vis. Comput. 27(8), 1194–1206 (2009)
Bouchrika, I.: A survey of using biometrics for smart visual surveillance: gait recognition. In: Karampelas, P., Bourlai, T. (eds.) Surveillance in Action, pp. 3–23. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-68533-5_1
Boulgouris, N.V., Chi, Z.X.: Gait recognition based on human body components. In: IEEE International Conference on Image Processing, pp. 353–356 (2007)
Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2D pose estimation using part affinity fields. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291–7299 (2017)
Chao, H., He, Y., Zhang, J., Feng, J.: GaitSet: regarding gait as a set for cross-view gait recognition. In: AAAI (2019)
Chattopadhyay, P., Sural, S., Mukherjee, J.: Frontal gait recognition from incomplete sequences using RGB-D camera. IEEE Trans. Inf. Forensics Secur. 9(11), 1843–1856 (2014)
Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., Liu, Z.: Dynamic convolution: attention over convolution kernels. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11030–11039 (2020)
Cheng, H.P., et al.: Swiftnet: using graph propagation as meta-knowledge to search highly representative neural architectures. arXiv preprint arXiv:1906.08305 (2019)
Dai, J., et al.: Deformable convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 764–773 (2017)
Denil, M., Shakibi, B., Dinh, L., Ranzato, M., De Freitas, N.: Predicting parameters in deep learning. In: Advances in Neural Information Processing Systems (2013)
Devos, A., Chatel, S., Grossglauser, M.: Reproducing meta-learning with differentiable closed-form solvers. In: International Conference on Learning Representations (2019)
Dou, H., et al.: Versatilegait: a large-scale synthetic gait dataset with fine-grainedattributes and complicated scenarios. arXiv preprint arXiv:2101.01394 (2021)
Du, Y., Wang, W., Wang, L.: Hierarchical recurrent neural network for skeleton based action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1110–1118 (2015)
Eigen, D., Ranzato, M., Sutskever, I.: Learning factored representations in a deep mixture of experts. arXiv preprint arXiv:1312.4314 (2013)
Fan, C., et al.: Gaitpart: temporal part-based model for gait recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)
Finn, C., Rajeswaran, A., Kakade, S., Levine, S.: Online meta-learning. In: International Conference on Machine Learning, pp. 1920–1930 (2019)
Gao, H., Zhu, X., Lin, S., Dai, J.: Deformable kernels: adapting effective receptive fields for object deformation. In: International Conference on Learning Representations (2019)
Goffredo, M., Bouchrika, I., Carter, J.N., Nixon, M.S.: Self-calibrating view-invariant gait biometrics. IEEE Trans. Cybern. 40(4), 997–1008 (2009)
Zhao, G., Liu, G., Li, H., Pietikainen, M.: 3D gait recognition using multiple cameras. In: International Conference on Automatic Face Gesture Recognition, pp. 529–534 (2006)
Han, J., Bhanu, B.: Individual recognition using gait energy image. IEEE Trans. Pattern Anal. Mach. Intell. 28(2), 316–322 (2006)
Harley, A.W., Derpanis, K.G., Kokkinos, I.: Segmentation-aware convolutional networks using local attention masks. In: International Conference on Computer Vision, pp. 5038–5047 (2017)
He, B., Yang, X., Wu, Z., Chen, H., Lim, S.N., Shrivastava, A.: GTA: global temporal attention for video action understanding. arXiv preprint arXiv:2012.08510 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)
Hospedales, T., Antoniou, A., Micaelli, P., Storkey, A.: Meta-learning in neural networks: a survey. arXiv preprint arXiv:2004.05439 (2020)
Hou, S., Cao, C., Liu, X., Huang, Y.: Gait lateral network: learning discriminative and compact representations for gait recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 382–398. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_22
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Huang, X., et al.: Context-sensitive temporal feature learning for gait recognition. In: International Conference on Computer Vision, pp. 12909–12918, October 2021
Huang, Y., Zhang, J., Zhao, H., Zhang, L.: Attention-based network for cross-view gait recognition. In: Advances in Neural Information Processing Systems, pp. 489–498 (2018)
Huang, Y., et al.: Curricularface: adaptive curriculum learning loss for deep face recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)
Huang, Z., et al.: 3D local convolutional neural networks for gait recognition. In: International Conference on Computer Vision, pp. 14920–14929, October 2021
Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79–87 (1991)
Kastaniotis, D., Theodorakopoulos, I., Fotopoulos, S.: Pose-based gait recognition with local gradient descriptors and hierarchically aggregated residuals. J. Electron. Imaging 25(6), 063019 (2016)
Kusakunniran, W., Wu, Q., Zhang, J., Li, H., Wang, L.: Recognizing gaits across views through correlated motion co-clustering. IEEE Trans. Image Process. 23(2), 696–709 (2014)
Kusakunniran, W., Wu, Q., Zhang, J., Ma, Y., Li, H.: A new view-invariant feature for cross-view gait recognition. IEEE Trans. Inf. Forensics Secur. 8(10), 1642–1653 (2013)
Li, S., Liu, W., Ma, H.: Attentive spatial-temporal summary networks for feature learning in irregular gait recognition. IEEE Trans. Multimedia 21(9), 2361–2375 (2019)
Liao, R., Yu, S., An, W., Huang, Y.: A model-based gait recognition method with body pose and human prior knowledge. Pattern Recog. 98, 107069 (2020)
Lin, B., Zhang, S., Bao, F.: Gait recognition with multiple-temporal-scale 3D convolutional neural network. In: ACM International Conference on Multimedia, pp. 3054–3062 (2020)
Lin, B., Zhang, S., Yu, X.: Gait recognition via effective global-local feature representation and local temporal aggregation. In: International Conference on Computer Vision, pp. 14648–14656, October 2021
Lin, J., Rao, Y., Lu, J., Zhou, J.: Runtime neural pruning. In: Advances in Neural Information Processing Systems (2017)
Lin, P., Sun, P., Cheng, G., Xie, S., Li, X., Shi, J.: Graph-guided architecture search for real-time semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2020
Ma, J., Zhao, Z., Yi, X., Chen, J., Hong, L., Chi, E.H.: Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In: SIGKDD, pp. 1930–1939 (2018)
Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)
Macoveciuc, I., Rando, C.J., Borrion, H.: Forensic gait analysis and recognition: standards of evidence admissibility. J. Forensic Sci. 64(5), 1294–1303 (2019)
Makihara, Y., Sagawa, R., Mukaigawa, Y., Echigo, T., Yagi, Y.: Gait recognition using a view transformation model in the frequency domain. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 151–163. Springer, Heidelberg (2006). https://doi.org/10.1007/11744078_12
Radenović, F., Tolias, G., Chum, O.: Fine-tuning CNN image retrieval with no human annotation. IEEE Trans. Pattern Anal. Mach. Intell. 41(7), 1655–1668 (2018)
Samangooei, S., Nixon, M.S.: Performing content-based retrieval of humans using gait biometrics. Multimed. Tools Appl. 49, 195–212 (2010)
Sepas-Moghaddam, A., Etemad, A.: Deep gait recognition: a survey. arXiv preprint arXiv:2102.09546 (2021)
Shan, S., Li, Y., Oliva, J.B.: Meta-neighborhoods. In: Advances in Neural Information Processing Systems, vol. 33, pp. 5047–5057 (2020)
Su, H., Jampani, V., Sun, D., Gallo, O., Learned-Miller, E., Kautz, J.: Pixel-adaptive convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11166–11175 (2019)
Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)
Takemura, N., Makihara, Y., Muramatsu, D., Echigo, T., Yagi, Y.: Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition. IPSJ Trans. Comput. Vis. Appl. 10(1), 1–14 (2018). https://doi.org/10.1186/s41074-018-0039-6
Veit, A., Belongie, S.: Convolutional networks with adaptive inference graphs. In: European Conference on Computer Vision, pp. 3–18 (2018)
Wang, D., Zhang, S.: Unsupervised person re-identification via multi-label classification. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)
Wang, L., Ning, H., Tan, T., Hu, W.: Fusion of static and dynamic body biometrics for gait recognition. IEEE TCSVT 14(2), 149–158 (2004)
Wang, X., Yu, F., Dou, Z.Y., Darrell, T., Gonzalez, J.E.: Skipnet: learning dynamic routing in convolutional networks. In: European Conference on Computer Vision, pp. 409–424 (2018)
Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: European Conference on Computer Vision, pp. 3–19 (2018)
Yang, B., Bender, G., Le, Q.V., Ngiam, J.: Condconv: conditionally parameterized convolutions for efficient inference. In: Advances in Neural Information Processing Systems (2019)
Yu, S., Tan, D., Tan, T.: A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In: International Conference on Pattern Recognition, pp. 441–444 (2006)
Zhang, F., Wah, B.W.: Supplementary meta-learning: towards a dynamic model for deep neural networks. In: International Conference on Computer Vision, pp. 4344–4353 (2017)
Zhang, Y., Huang, Y., Yu, S., Wang, L.: Cross-view gait recognition by discriminative feature learning. IEEE Trans. Image Process. 29, 1001–1015 (2019)
Acknowledgement
This work is supported in part by the National Natural Science Foundation of China under Grant U20A20222, National Key Research and Development Program of China under Grant 2020AAA0107400, Zhejiang Provincial Natural Science Foundation of China under Grant LR19F020004, NSFC (62002320, U19B2043) and the Key R &D Program of Zhejiang Province, China (2021C01119).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dou, H., Zhang, P., Su, W., Yu, Y., Li, X. (2022). MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13665. Springer, Cham. https://doi.org/10.1007/978-3-031-20065-6_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-20065-6_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20064-9
Online ISBN: 978-3-031-20065-6
eBook Packages: Computer ScienceComputer Science (R0)