pith. machine review for the scientific record. sign in

arxiv: 2604.15979 · v1 · submitted 2026-04-17 · 💻 cs.CV

Recognition: unknown

MMGait: Towards Multi-Modal Gait Recognition

Aoqi Li, Chenye Wang, Qingyuan Cai, Saihui Hou, Yongzhen Huang

Pith reviewed 2026-05-10 08:59 UTC · model grok-4.3

classification 💻 cs.CV
keywords gait recognitionmulti-modal benchmarkcross-modal retrievalshared embeddingbiometric identificationsensor fusionOmniGait
0
0 comments X

The pith

MMGait introduces a benchmark with data from five sensors to support unified multi-modal gait recognition.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper creates MMGait, a dataset of gait sequences from 725 subjects captured by RGB, depth, infrared, LiDAR, and radar sensors to yield twelve modalities spanning geometric, photometric, and motion information. This setup lets researchers test gait recognition when using one sensor type, matching across different sensors, or fusing several together. The authors also release OmniGait, a baseline model that maps inputs from any modality into one shared space so a single network can handle the three recognition styles.

Core claim

The central claim is that the MMGait benchmark, containing 334,060 sequences from five heterogeneous sensors, enables systematic single-modal, cross-modal, and multi-modal gait experiments, while the proposed OmniGait baseline learns a shared embedding space across modalities and delivers promising recognition accuracy within one unified framework.

What carries the argument

The MMGait benchmark dataset that integrates twelve modalities from an RGB camera, depth camera, infrared camera, LiDAR scanner, and 4D radar system; OmniGait model that projects diverse modality inputs into a common embedding space.

Load-bearing premise

The five sensors can be synchronized and aligned accurately enough during collection that performance differences reflect genuine complementarity rather than calibration or timing artifacts.

What would settle it

If cross-modal or multi-modal accuracy on MMGait falls to the level of the strongest single modality after explicit checks for alignment errors, the claim that the modalities supply useful complementary information would be falsified.

Figures

Figures reproduced from arXiv: 2604.15979 by Aoqi Li, Chenye Wang, Qingyuan Cai, Saihui Hou, Yongzhen Huang.

Figure 1
Figure 1. Figure 1: Highlights of MMGait. MMGait integrates data from five sensors. It spans twelve modalities, including multi-view, multi-modal [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The collection setup of MMGait. 0 20 40 60 80 100 >=130 Sequence Length (Frames) 0.00 0.01 0.02 0.03 0.04 Sequence Proportion 4D Radar LiDAR IR RGB Depth [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 4
Figure 4. Figure 4: Pairwise cross-modal retrieval performance among the [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Overview of the OmniGait framework, including modal [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Pairwise cross-modal retrieval performance of OmniGait [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Visualization of gait sequences across all sensor modalities, ten viewpoints, and three walking conditions (NM, BG, CL). [PITH_FULL_IMAGE:figures/full_fig_p015_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Visualization of gait sequences across all sensor modalities, ten viewpoints, and three walking conditions (NM, BG, CL). [PITH_FULL_IMAGE:figures/full_fig_p016_8.png] view at source ↗
read the original abstract

Gait recognition has emerged as a powerful biometric technique for identifying individuals at a distance without requiring user cooperation. Most existing methods focus primarily on RGB-derived modalities, which fall short in real-world scenarios requiring multi-modal collaboration and cross-modal retrieval. To overcome these challenges, we present MMGait, a comprehensive multi-modal gait benchmark integrating data from five heterogeneous sensors, including an RGB camera, a depth camera, an infrared camera, a LiDAR scanner, and a 4D Radar system. MMGait contains twelve modalities and 334,060 sequences from 725 subjects, enabling systematic exploration across geometric, photometric, and motion domains. Based on MMGait, we conduct extensive evaluations on single-modal, cross-modal, and multi-modal paradigms to analyze modality robustness and complementarity. Furthermore, we introduce a new task, Omni Multi-Modal Gait Recognition, which aims to unify the above three gait recognition paradigms within a single model. We also propose a simple yet powerful baseline, OmniGait, which learns a shared embedding space across diverse modalities and achieves promising recognition performance. The MMGait benchmark, codebase, and pretrained checkpoints are publicly available at https://github.com/BNU-IVC/MMGait.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Circularity Check

0 steps flagged

No significant circularity: empirical benchmark with direct measurements

full rationale

The paper introduces a new multi-modal gait dataset (MMGait) collected from five heterogeneous sensors and proposes a baseline model (OmniGait) for shared embeddings across modalities. No mathematical derivations, fitted-parameter predictions, self-definitional loops, or load-bearing self-citations are present in the claims. Central results consist of direct empirical evaluations on newly collected sequences, with no reduction of outputs to inputs by construction. The work is self-contained as a benchmark contribution.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claims rest on the assumption that the collected multi-sensor sequences are accurately labeled and synchronized, plus standard machine-learning assumptions about embedding spaces and loss functions for the baseline. No new physical entities or ad-hoc constants are introduced beyond typical neural network hyperparameters.

axioms (1)
  • domain assumption Gait patterns serve as reliable biometric identifiers across different sensing modalities
    Invoked implicitly when claiming the dataset enables gait recognition; standard in the field but not proven in the paper.

pith-pipeline@v0.9.0 · 5517 in / 1327 out tokens · 41937 ms · 2026-05-10T08:59:08.688522+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

96 extracted references · 12 canonical work pages · 1 internal anchor

  1. [1]

    2v-gait: Gait recognition us- ing 3d lidar robust to changes in walking direction and mea- surement distance

    Jeongho Ahn, Kazuto Nakashima, Koki Yoshino, Yumi Iwashita, and Ryo Kurazume. 2v-gait: Gait recognition us- ing 3d lidar robust to changes in walking direction and mea- surement distance. In2022 IEEE/SICE International Sym- posium on System Integration (SII), pages 602–607. IEEE,

  2. [2]

    Lidar-based gait analysis and activity recognition in a 4d surveillance system.IEEE Transactions on Circuits and Sys- tems for Video Technology, 28(1):101–113, 2016

    Csaba Benedek, Bence G ´alai, Bal´azs Nagy, and Zsolt Jank´o. Lidar-based gait analysis and activity recognition in a 4d surveillance system.IEEE Transactions on Circuits and Sys- tems for Video Technology, 28(1):101–113, 2016. 4

    2016

  3. [3]

    Disentangled diffusion-based 3d human pose estimation with hierarchical spatial and temporal de- noiser

    Qingyuan Cai, Xuecai Hu, Saihui Hou, Li Yao, and Yongzhen Huang. Disentangled diffusion-based 3d human pose estimation with hierarchical spatial and temporal de- noiser. InProceedings of the AAAI conference on artificial intelligence, pages 882–890, 2024. 2

    2024

  4. [4]

    Fastddhpose: Towards unified, efficient, and disentangled 3d human pose estimation.arXiv preprint arXiv:2512.14162, 2025

    Qingyuan Cai, Linxin Zhang, Xuecai Hu, Saihui Hou, and Yongzhen Huang. Fastddhpose: Towards unified, efficient, and disentangled 3d human pose estimation.arXiv preprint arXiv:2512.14162, 2025. 2

    work page arXiv 2025

  5. [5]

    Domain-specific batch normalization for unsupervised domain adaptation

    Woong-Gi Chang, Tackgeun You, Seonguk Seo, Suha Kwak, and Bohyung Han. Domain-specific batch normalization for unsupervised domain adaptation. InProceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 7354–7362, 2019. 5

    2019

  6. [6]

    Gaitset: Regarding gait as a set for cross-view gait recognition

    Hanqing Chao, Yiwei He, Junping Zhang, and Jianfeng Feng. Gaitset: Regarding gait as a set for cross-view gait recognition. InProceedings of the AAAI conference on arti- ficial intelligence, pages 8126–8133, 2019. 4, 1

    2019

  7. [7]

    Edino- gait: Transferring large visual models to event-based vision for enhancing gait recognition.IEEE Transactions on Multi- media, 2025

    Liaogehao Chen, Zhenjun Zhang, and Yaonan Wang. Edino- gait: Transferring large visual models to event-based vision for enhancing gait recognition.IEEE Transactions on Multi- media, 2025. 3, 1

    2025

  8. [8]

    Person reidentification based on automotive radar point clouds.IEEE Transactions on Geoscience and Remote Sensing, 60:1–13, 2021

    Yuwei Cheng and Yimin Liu. Person reidentification based on automotive radar point clouds.IEEE Transactions on Geoscience and Remote Sensing, 60:1–13, 2021. 3

    2021

  9. [9]

    On model and data scaling for skeleton-based self-supervised gait recognition.arXiv preprint arXiv:2504.07598, 2025

    Adrian Cosma, Andy C ˇatrunˇa, and Emilian R ˇadoi. On model and data scaling for skeleton-based self-supervised gait recognition.arXiv preprint arXiv:2504.07598, 2025. 1

    work page arXiv 2025

  10. [10]

    Multi-modal gait recognition via effective spatial-temporal feature fusion

    Yufeng Cui and Yimei Kang. Multi-modal gait recognition via effective spatial-temporal feature fusion. InProceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 17949–17957, 2023. 1

    2023

  11. [11]

    Licaf: Lidar- camera asymmetric fusion for gait recognition

    Yunze Deng, Haijun Xiong, and Bin Feng. Licaf: Lidar- camera asymmetric fusion for gait recognition. In2024 IEEE International Conference on Image Processing (ICIP), pages 2424–2430. IEEE, 2024. 1

    2024

  12. [12]

    Clash: Complementary learning with neural architec- ture search for gait recognition.IEEE Transactions on Image Processing, 2024

    Huanzhang Dou, Pengyi Zhang, Yuhan Zhao, Lu Jin, and Xi Li. Clash: Complementary learning with neural architec- ture search for gait recognition.IEEE Transactions on Image Processing, 2024. 1

    2024

  13. [13]

    A density-based algorithm for discovering clusters in large spatial databases with noise

    Martin Ester, Hans-Peter Kriegel, J ¨org Sander, Xiaowei Xu, et al. A density-based algorithm for discovering clusters in large spatial databases with noise. Inkdd, pages 226–231,

  14. [14]

    Gaitpart: Temporal part-based model for gait recognition

    Chao Fan, Yunjie Peng, Chunshui Cao, Xu Liu, Saihui Hou, Jiannan Chi, Yongzhen Huang, Qing Li, and Zhiqiang He. Gaitpart: Temporal part-based model for gait recognition. In Proceedings of the IEEE/CVF conference on computer vi- sion and pattern recognition, pages 14225–14233, 2020. 4

    2020

  15. [15]

    Ex- ploring deep models for practical gait recognition.arXiv preprint arXiv:2303.03301, 2023

    Chao Fan, Saihui Hou, Yongzhen Huang, and Shiqi Yu. Ex- ploring deep models for practical gait recognition.arXiv preprint arXiv:2303.03301, 2023. 4, 1

    work page arXiv 2023

  16. [16]

    Opengait: Revisiting gait recognition towards better practicality

    Chao Fan, Junhao Liang, Chuanfu Shen, Saihui Hou, Yongzhen Huang, and Shiqi Yu. Opengait: Revisiting gait recognition towards better practicality. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9707–9716, 2023. 4, 1, 2

    2023

  17. [17]

    Skeletongait: Gait recognition using skeleton maps

    Chao Fan, Jingzhe Ma, Dongyang Jin, Chuanfu Shen, and Shiqi Yu. Skeletongait: Gait recognition using skeleton maps. InProceedings of the AAAI conference on artificial intelligence, pages 1662–1669, 2024. 4, 6, 1

    2024

  18. [18]

    Gpgait: Generalized pose-based gait recognition

    Yang Fu, Shibei Meng, Saihui Hou, Xuecai Hu, and Yongzhen Huang. Gpgait: Generalized pose-based gait recognition. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 19595–19604, 2023. 4, 1

    2023

  19. [19]

    Cut out the middleman: Revisiting pose-based gait recognition

    Yang Fu, Saihui Hou, Shibei Meng, Xuecai Hu, Chunshui Cao, Xu Liu, and Yongzhen Huang. Cut out the middleman: Revisiting pose-based gait recognition. InEuropean Confer- ence on Computer Vision, pages 112–128. Springer, 2024. 1

    2024

  20. [20]

    Physics-augmented autoencoder for 3d skeleton-based gait recognition

    Hongji Guo and Qiang Ji. Physics-augmented autoencoder for 3d skeleton-based gait recognition. InProceedings of the IEEE/CVF International Conference on Computer Vi- sion, pages 19627–19638, 2023. 1

    2023

  21. [21]

    Camera-lidar cross-modality gait recognition

    Wenxuan Guo, Yingping Liang, Zhiyu Pan, Ziheng Xi, Jian- jiang Feng, and Jie Zhou. Camera-lidar cross-modality gait recognition. InEuropean Conference on Computer Vision, pages 439–455. Springer, 2024. 1, 5, 2

    2024

  22. [22]

    Lidar-based person re-identification

    Wenxuan Guo, Zhiyu Pan, Yingping Liang, Ziheng Xi, Zhicheng Zhong, Jianjiang Feng, and Jie Zhou. Lidar-based person re-identification. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17437–17447, 2024. 1, 3

    2024

  23. [23]

    Gaitcontour: Efficient gait recognition based on a contour-pose representation

    Yuxiang Guo, Anshul Shah, Jiang Liu, Ayush Gupta, Rama Chellappa, and Cheng Peng. Gaitcontour: Efficient gait recognition based on a contour-pose representation. In2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 1051–1061. IEEE, 2025. 1

    2025

  24. [24]

    mmreid: Person re-identification based on commod- ity millimeter-wave radar.IEEE Internet of Things Journal,

    Chong Han, Siyu Chen, Biyun Sheng, Jian Guo, and Lijuan Sun. mmreid: Person re-identification based on commod- ity millimeter-wave radar.IEEE Internet of Things Journal,

  25. [25]

    Gait recognition in large- scale free environment via single lidar

    Xiao Han, Yiming Ren, Peishan Cong, Yujing Sun, Jingya Wang, Lan Xu, and Yuexin Ma. Gait recognition in large- scale free environment via single lidar. InProceedings of the 32nd ACM International Conference on Multimedia, pages 380–389, 2024. 1, 4

    2024

  26. [26]

    Micro-doppler based target recognition with radars: A review.IEEE Sensors Journal, 22(4):2948–2961, 2022

    Ali Hanif, Muhammad Muaz, Azhar Hasan, and Muhammad Adeel. Micro-doppler based target recognition with radars: A review.IEEE Sensors Journal, 22(4):2948–2961, 2022. 3

    2022

  27. [27]

    Recurrent attention models for depth-based person identification

    Albert Haque, Alexandre Alahi, and Li Fei-Fei. Recurrent attention models for depth-based person identification. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1229–1238, 2016. 3

    2016

  28. [28]

    Instruct-reid++: Towards universal purpose instruction-guided person re-identification.IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 2025

    Weizhen He, Yiheng Deng, Yunfeng Yan, Feng Zhu, Yizhou Wang, Lei Bai, Qingsong Xie, Rui Zhao, Donglian Qi, Wanli Ouyang, et al. Instruct-reid++: Towards universal purpose instruction-guided person re-identification.IEEE Transac- tions on Pattern Analysis and Machine Intelligence, 2025. 1

    2025

  29. [29]

    Martin Hofmann, J ¨urgen Geiger, Sebastian Bachmann, Bj¨orn Schuller, and Gerhard Rigoll. The tum gait from audio, image and depth (gaid) database: Multimodal recognition of subjects and traits.Journal of Visual Communication and Image Representation, 25(1):195–206, 2014. 4

    2014

  30. [30]

    Gaitsnippet: Gait recognition be- yond unordered sets and ordered sequences.arXiv preprint arXiv:2508.07782, 2025

    Saihui Hou, Chenye Wang, Wenpeng Lang, Zhengxiang Lan, and Yongzhen Huang. Gaitsnippet: Gait recognition be- yond unordered sets and ordered sequences.arXiv preprint arXiv:2508.07782, 2025. 1

    work page arXiv 2025

  31. [31]

    Gaitasset: In defense of regard- ing gait as a set.IEEE Transactions on Information Forensics and Security, 20:12301–12316, 2025

    Saihui Hou, Chenye Wang, Aoqi Li, Jilong Wang, Liang Wang, and Yongzhen Huang. Gaitasset: In defense of regard- ing gait as a set.IEEE Transactions on Information Forensics and Security, 20:12301–12316, 2025. 1

    2025

  32. [32]

    v2e: From video frames to realistic dvs events

    Yuhuang Hu, Shih-Chii Liu, and Tobi Delbruck. v2e: From video frames to realistic dvs events. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1312–1321, 2021. 2

    2021

  33. [33]

    Normalization techniques in training dnns: Method- ology, analysis and application.IEEE transactions on pat- tern analysis and machine intelligence, 45(8):10173–10196,

    Lei Huang, Jie Qin, Yi Zhou, Fan Zhu, Li Liu, and Ling Shao. Normalization techniques in training dnns: Method- ology, analysis and application.IEEE transactions on pat- tern analysis and machine intelligence, 45(8):10173–10196,

  34. [34]

    V ocabulary-guided gait recognition

    Panjian Huang, Saihui Hou, Chunshui Cao, Xu Liu, and Yongzhen Huang. V ocabulary-guided gait recognition. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. 1

  35. [35]

    Occluded gait recognition with mixture of experts: an action detection perspective

    Panjian Huang, Yunjie Peng, Saihui Hou, Chunshui Cao, Xu Liu, Zhiqiang He, and Yongzhen Huang. Occluded gait recognition with mixture of experts: an action detection perspective. InEuropean Conference on Computer Vision, pages 380–397. Springer, 2024. 1

    2024

  36. [36]

    Learning a unified template for gait recognition

    Panjian Huang, Saihui Hou, Junzhou Huang, and Yongzhen Huang. Learning a unified template for gait recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 12459–12469, 2025. 1

    2025

  37. [37]

    Condition-adaptive graph convolution learning for skeleton-based gait recogni- tion.IEEE Transactions on Image Processing, 32:4773– 4784, 2023

    Xiaohu Huang, Xinggang Wang, Zhidianqiu Jin, Bo Yang, Botao He, Bin Feng, and Wenyu Liu. Condition-adaptive graph convolution learning for skeleton-based gait recogni- tion.IEEE Transactions on Image Processing, 32:4773– 4784, 2023. 1

    2023

  38. [38]

    L4dr: Lidar-4dradar fusion for weather-robust 3d ob- ject detection

    Xun Huang, Ziyu Xu, Hai Wu, Jinlong Wang, Qiming Xia, Yan Xia, Jonathan Li, Kyle Gao, Chenglu Wen, and Cheng Wang. L4dr: Lidar-4dradar fusion for weather-robust 3d ob- ject detection. InProceedings of the AAAI Conference on Artificial Intelligence, pages 3806–3814, 2025. 3

    2025

  39. [39]

    Ex- ploring more from multiple gait modalities for human identi- fication

    Dongyang Jin, Chao Fan, Weihua Chen, and Shiqi Yu. Ex- ploring more from multiple gait modalities for human identi- fication. InProceedings of the AAAI Conference on Artificial Intelligence, pages 4120–4128, 2025. 6, 1, 5

    2025

  40. [40]

    On denoising walking videos for gait recognition

    Dongyang Jin, Chao Fan, Jingzhe Ma, Jingkai Zhou, Wei- hua Chen, and Shiqi Yu. On denoising walking videos for gait recognition. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 12347–12357, 2025. 1

    2025

  41. [41]

    Adam: A Method for Stochastic Optimization

    Diederik P Kingma. Adam: A method for stochastic opti- mization.arXiv preprint arXiv:1412.6980, 2014. 2

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  42. [42]

    Beyond sparse keypoints: Dense pose modeling for robust gait recog- nition

    Wenpeng Lang, Saihui Hou, and Yongzhen Huang. Beyond sparse keypoints: Dense pose modeling for robust gait recog- nition. InProceedings of the 33rd ACM International Con- ference on Multimedia, pages 669–678, 2025. 1

    2025

  43. [43]

    Patch- work++: Fast and robust ground segmentation solving partial under-segmentation using 3d point cloud

    Seungjae Lee, Hyungtae Lim, and Hyun Myung. Patch- work++: Fast and robust ground segmentation solving partial under-segmentation using 3d point cloud. In2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 13276–13283. IEEE, 2022. 2

    2022

  44. [44]

    Aerialgait: Bridging aerial and ground views for gait recognition

    Aoqi Li, Saihui Hou, Chenye Wang, Qingyuan Cai, and Yongzhen Huang. Aerialgait: Bridging aerial and ground views for gait recognition. InProceedings of the 32nd ACM International Conference on Multimedia, pages 1139–1147,

  45. [45]

    All in one frame- work for multimodal re-identification in the wild

    He Li, Mang Ye, Ming Zhang, and Bo Du. All in one frame- work for multimodal re-identification in the wild. InPro- ceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17459–17469, 2024. 2, 1

    2024

  46. [46]

    An in-depth ex- ploration of person re-identification and gait recognition in cloth-changing conditions

    Weijia Li, Saihui Hou, Chunjie Zhang, Chunshui Cao, Xu Liu, Yongzhen Huang, and Yao Zhao. An in-depth ex- ploration of person re-identification and gait recognition in cloth-changing conditions. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13824–13833, 2023. 4, 1

    2023

  47. [47]

    Towards anytime retrieval: A benchmark for anytime person re-identification,

    Xulin Li, Yan Lu, Bin Liu, Jiaze Li, Qinhong Yang, Tao Gong, Qi Chu, Mang Ye, and Nenghai Yu. Towards anytime retrieval: A benchmark for anytime person re-identification. arXiv preprint arXiv:2509.16635, 2025. 5

    work page arXiv 2025

  48. [48]

    A model-based gait recognition method with body pose and human prior knowledge.Pattern Recognition, 98:107069,

    Rijun Liao, Shiqi Yu, Weizhi An, and Yongzhen Huang. A model-based gait recognition method with body pose and human prior knowledge.Pattern Recognition, 98:107069,

  49. [49]

    Gaitgl: Learning discriminative global-local feature representations for gait recognition,

    Beibei Lin, Shunli Zhang, Ming Wang, Lincheng Li, and Xin Yu. Gaitgl: Learning discriminative global-local fea- ture representations for gait recognition.arXiv preprint arXiv:2208.01380, 2022. 4

    work page arXiv 2022

  50. [50]

    Cross-modality se- mantic consistency learning for visible-infrared person re- identification.IEEE Transactions on Multimedia, 2024

    Min Liu, Zhu Zhang, Yuan Bian, Xueping Wang, Yeqing Sun, Baida Zhang, and Yaonan Wang. Cross-modality se- mantic consistency learning for visible-infrared person re- identification.IEEE Transactions on Multimedia, 2024. 1

    2024

  51. [51]

    Paddleseg: A high-efficient development toolkit for image segmentation.arXiv preprint arXiv:2101.06175, 2021

    Yi Liu, Lutao Chu, Guowei Chen, Zewu Wu, Zeyu Chen, Baohua Lai, and Yuying Hao. Paddleseg: A high-efficient development toolkit for image segmentation.arXiv preprint arXiv:2101.06175, 2021. 2

    work page arXiv 2021

  52. [52]

    Dynamic aggregated network for gait recognition

    Kang Ma, Ying Fu, Dezhi Zheng, Chunshui Cao, Xuecai Hu, and Yongzhen Huang. Dynamic aggregated network for gait recognition. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22076– 22085, 2023. 1

    2023

  53. [53]

    Learning visual prompt for gait recognition

    Kang Ma, Ying Fu, Chunshui Cao, Saihui Hou, Yongzhen Huang, and Dezhi Zheng. Learning visual prompt for gait recognition. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 593–603,

  54. [54]

    Real-time human recognition at night via inte- grated face and gait recognition technologies.Sensors, 21 (13):4323, 2021

    Samah AF Manssor, Shaoyuan Sun, and Mohammed AM Elhassan. Real-time human recognition at night via inte- grated face and gait recognition technologies.Sensors, 21 (13):4323, 2021. 3

    2021

  55. [55]

    Fastposegait: A toolbox and bench- mark for efficient pose-based gait recognition.arXiv preprint arXiv:2309.00794, 2023

    Shibei Meng, Yang Fu, Saihui Hou, Chunshui Cao, Xu Liu, and Yongzhen Huang. Fastposegait: A toolbox and bench- mark for efficient pose-based gait recognition.arXiv preprint arXiv:2309.00794, 2023. 2

    work page arXiv 2023

  56. [56]

    From fastposegait to gpgait++: Bridging the past and future for pose-based gait recognition.IEEE Transactions on Pattern Analysis and Ma- chine Intelligence, 2025

    Shibei Meng, Yang Fu, Saihui Hou, Xuecai Hu, Chunshui Cao, Xu Liu, and Yongzhen Huang. From fastposegait to gpgait++: Bridging the past and future for pose-based gait recognition.IEEE Transactions on Pattern Analysis and Ma- chine Intelligence, 2025. 1, 4, 2

    2025

  57. [57]

    Gait recognition for co-existing multiple people using millimeter wave sensing

    Zhen Meng, Song Fu, Jie Yan, Hongyuan Liang, Anfu Zhou, Shilin Zhu, Huadong Ma, Jianhua Liu, and Ning Yang. Gait recognition for co-existing multiple people using millimeter wave sensing. InProceedings of the AAAI conference on artificial intelligence, pages 849–856, 2020. 3

    2020

  58. [58]

    Infrared database for gait recognition in dynamic outdoor environment

    Sonam Nahar and Sasan Mahmoodi. Infrared database for gait recognition in dynamic outdoor environment. InInter- national Conference on Pattern Recognition, pages 326–341. Springer, 2024. 3

    2024

  59. [59]

    Glgait: a global-local temporal re- ceptive field network for gait recognition in the wild

    Guozhen Peng, Yunhong Wang, Yuwei Zhao, Shaoxiong Zhang, and Annan Li. Glgait: a global-local temporal re- ceptive field network for gait recognition in the wild. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 826–835, 2024. 1

    2024

  60. [60]

    A stochastic approxi- mation method.The annals of mathematical statistics, pages 400–407, 1951

    Herbert Robbins and Sutton Monro. A stochastic approxi- mation method.The annals of mathematical statistics, pages 400–407, 1951. 2

    1951

  61. [61]

    Deep gait recognition: A survey.IEEE transactions on pattern analy- sis and machine intelligence, 45(1):264–284, 2022

    Alireza Sepas-Moghaddam and Ali Etemad. Deep gait recognition: A survey.IEEE transactions on pattern analy- sis and machine intelligence, 45(1):264–284, 2022. 1

    2022

  62. [62]

    Ntu rgb+ d: A large scale dataset for 3d human activity anal- ysis

    Amir Shahroudy, Jun Liu, Tian-Tsong Ng, and Gang Wang. Ntu rgb+ d: A large scale dataset for 3d human activity anal- ysis. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 1010–1019, 2016. 3

    2016

  63. [63]

    Lidargait: Benchmarking 3d gait recognition with point clouds

    Chuanfu Shen, Chao Fan, Wei Wu, Rui Wang, George Q Huang, and Shiqi Yu. Lidargait: Benchmarking 3d gait recognition with point clouds. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1054–1063, 2023. 1, 4, 2

    2023

  64. [64]

    A comprehensive survey on deep gait recogni- tion: Algorithms, datasets, and challenges.IEEE Transac- tions on Biometrics, Behavior, and Identity Science, 2024

    Chuanfu Shen, Shiqi Yu, Jilong Wang, George Q Huang, and Liang Wang. A comprehensive survey on deep gait recogni- tion: Algorithms, datasets, and challenges.IEEE Transac- tions on Biometrics, Behavior, and Identity Science, 2024. 1

    2024

  65. [65]

    Li- dargait++: Learning local features and size awareness from lidar point clouds for 3d gait recognition

    Chuanfu Shen, Rui Wang, Lixin Duan, and Shiqi Yu. Li- dargait++: Learning local features and size awareness from lidar point clouds for 3d gait recognition. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 6627–6636, 2025. 3, 4, 1, 2

    2025

  66. [66]

    Trigait: hybrid fusion strategy for mul- timodal alignment and integration in gait recognition.IEEE Transactions on Biometrics, Behavior, and Identity Science, 7(1):82–94, 2024

    Yan Sun, Xueling Feng, Xiaolei Liu, Liyan Ma, Long Hu, and Mark S Nixon. Trigait: hybrid fusion strategy for mul- timodal alignment and integration in gait recognition.IEEE Transactions on Biometrics, Behavior, and Identity Science, 7(1):82–94, 2024. 1

    2024

  67. [67]

    Multi-view large popu- lation gait dataset and its performance evaluation for cross- view gait recognition.IPSJ transactions on Computer Vision and Applications, 10:1–14, 2018

    Noriko Takemura, Yasushi Makihara, Daigo Muramatsu, Tomio Echigo, and Yasushi Yagi. Multi-view large popu- lation gait dataset and its performance evaluation for cross- view gait recognition.IPSJ transactions on Computer Vision and Applications, 10:1–14, 2018. 1

    2018

  68. [68]

    Efficient night gait recognition based on template match- ing

    Daoliang Tan, Kaiqi Huang, Shiqi Yu, and Tieniu Tan. Efficient night gait recognition based on template match- ing. In18th international conference on pattern recognition (ICPR’06), pages 1000–1003. IEEE, 2006. 3, 4

    2006

  69. [69]

    Gaitgraph: Graph convo- lutional network for skeleton-based gait recognition

    Torben Teepe, Ali Khan, Johannes Gilg, Fabian Herzog, Ste- fan H¨ormann, and Gerhard Rigoll. Gaitgraph: Graph convo- lutional network for skeleton-based gait recognition. In2021 IEEE international conference on image processing (ICIP), pages 2314–2318. IEEE, 2021. 4, 1

    2021

  70. [70]

    Towards a deeper under- standing of skeleton-based gait recognition

    Torben Teepe, Johannes Gilg, Fabian Herzog, Stefan H¨ormann, and Gerhard Rigoll. Towards a deeper under- standing of skeleton-based gait recognition. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1569–1577, 2022. 4, 1

    2022

  71. [71]

    Ra-gar: A richly annotated benchmark for gait attribute recognition

    Chenye Wang, Saihui Hou, Aoqi Li, Qingyuan Cai, and Yongzhen Huang. Ra-gar: A richly annotated benchmark for gait attribute recognition. InProceedings of the AAAI Con- ference on Artificial Intelligence, pages 7591–7599, 2025. 3

    2025

  72. [72]

    Deep high-resolution repre- sentation learning for visual recognition.IEEE transactions on pattern analysis and machine intelligence, 43(10):3349– 3364, 2020

    Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, et al. Deep high-resolution repre- sentation learning for visual recognition.IEEE transactions on pattern analysis and machine intelligence, 43(10):3349– 3364, 2020. 2

    2020

  73. [73]

    Gaitc 3 i: Robust cross-covariate gait recognition via causal in- tervention.IEEE Transactions on Circuits and Systems for Video Technology, 2025

    Jilong Wang, Saihui Hou, Xianda Guo, Yan Huang, Yongzhen Huang, Tianzhu Zhang, and Liang Wang. Gaitc 3 i: Robust cross-covariate gait recognition via causal in- tervention.IEEE Transactions on Circuits and Systems for Video Technology, 2025. 3

    2025

  74. [74]

    Combining the sil- houette and skeleton data for gait recognition

    Likai Wang, Ruize Han, and Wei Feng. Combining the sil- houette and skeleton data for gait recognition. InICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. IEEE,

    2023

  75. [75]

    Hu- man motion recognition exploiting radar with stacked recur- rent neural network.Digital Signal Processing, 87:125–131,

    Mingyang Wang, Yimin D Zhang, and Guolong Cui. Hu- man motion recognition exploiting radar with stacked recur- rent neural network.Digital Signal Processing, 87:125–131,

  76. [76]

    Pointgait: Boosting end-to-end 3d gait recogni- tion with point clouds via spatiotemporal modeling

    Rui Wang, Chuanfu Shen, Chao Fan, George Q Huang, and Shiqi Yu. Pointgait: Boosting end-to-end 3d gait recogni- tion with point clouds via spatiotemporal modeling. In2023 IEEE International Joint Conference on Biometrics (IJCB), pages 1–10. IEEE, 2023. 1

    2023

  77. [77]

    Cross-modality gait recog- nition: Bridging lidar and camera modalities for human iden- tification

    Rui Wang, Chuanfu Shen, Manuel J Marin-Jimenez, George Q Huang, and Shiqi Yu. Cross-modality gait recog- nition: Bridging lidar and camera modalities for human iden- tification. In2024 IEEE International Joint Conference on Biometrics (IJCB), pages 1–11. IEEE, 2024. 1

    2024

  78. [78]

    Causality-inspired discriminative feature learning in triple domains for gait recognition

    Haijun Xiong, Bin Feng, Xinggang Wang, and Wenyu Liu. Causality-inspired discriminative feature learning in triple domains for gait recognition. InEuropean Conference on Computer Vision, pages 251–270. Springer, 2024. 1, 3

    2024

  79. [79]

    Gait-based person iden- tification using 3d lidar and long short-term memory deep networks.Advanced Robotics, 34(18):1201–1211, 2020

    Hiroyuki Yamada, Jeongho Ahn, Oscar Martinez Mozos, Yumi Iwashita, and Ryo Kurazume. Gait-based person iden- tification using 3d lidar and long short-term memory deep networks.Advanced Robotics, 34(18):1201–1211, 2020. 4

    2020

  80. [80]

    Bridging gait recognition and large language models sequence modeling

    Shaopeng Yang, Jilong Wang, Saihui Hou, Xu Liu, Chun- shui Cao, Liang Wang, and Yongzhen Huang. Bridging gait recognition and large language models sequence modeling. InProceedings of the Computer Vision and Pattern Recogni- tion Conference, pages 3460–3469, 2025. 1

    2025

Showing first 80 references.