Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline (2205.02692v2)

Published 5 May 2022 in cs.CV

Abstract: Gait benchmarks empower the research community to train and evaluate high-performance gait recognition systems. Even though growing efforts have been devoted to cross-view recognition, academia is restricted by current existing databases captured in the controlled environment. In this paper, we contribute a new benchmark and strong baseline for Gait REcognition in the Wild (GREW). The GREW dataset is constructed from natural videos, which contain hundreds of cameras and thousands of hours of streams in open systems. With tremendous manual annotations, the GREW consists of 26K identities and 128K sequences with rich attributes for unconstrained gait recognition. Moreover, we add a distractor set of over 233K sequences, making it more suitable for real-world applications. Compared with prevailing predefined cross-view datasets, the GREW has diverse and practical view variations, as well as more naturally challenging factors. To the best of our knowledge, this is the first large-scale dataset for gait recognition in the wild. Equipped with this benchmark, we dissect the unconstrained gait recognition problem, where representative appearance-based and model-based methods are explored. The proposed GREW benchmark proves to be essential for both training and evaluating gait recognizers in unconstrained scenarios. In addition, we propose the Single Path One-Shot neural architecture search with uniform sampling for Gait recognition, named SPOSGait, which is the first NAS-based gait recognition model. In experiments, SPOSGait achieves state-of-the-art performance on the CASIA-B, OU-MVLP, Gait3D, and GREW benchmarks, outperforming existing approaches by a large margin. The code will be released at https://github.com/XiandaGuo/SPOSGait.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (124)
  1. https://github.com/NVIDIA/flownet2-pytorch/.
  2. Performance evaluation of model-based gait on multi-view very large population database with pose sequences. TBIOM, 2020.
  3. ProxylessNAS: Direct neural architecture search on target task and hardware. In ICLR, 2019.
  4. VGGFace2: A dataset for recognising faces across pose and age. In FG, 2018.
  5. Lagrange motion analysis and view embeddings for improved gait recognition. In CVPR, 2022.
  6. GaitSet: Regarding gait as a set for cross-view gait recognition. In AAAI, 2019.
  7. C.-H. Chen and D. Ramanan. 3D human pose estimation = 2D pose estimation + matching. In CVPR, 2017.
  8. Hybrid task cascade for instance segmentation. In CVPR, 2019.
  9. Fasterseg: Searching for faster real-time semantic segmentation. ICLR, 2020.
  10. Hierarchical neural architecture search for deep stereo matching. NeurIPS, 2020.
  11. Combining multiple evidences for gait recognition. In ICASSP, 2003.
  12. ArcFace: Additive angular margin loss for deep face recognition. In CVPR, 2019.
  13. Gaitgci: Generative counterfactual intervention for gait recognition. In CVPR, 2023.
  14. Versatilegait: a large-scale synthetic gait dataset with fine-grainedattributes and complicated scenarios. arXiv preprint arXiv:2101.01394, 2021.
  15. Learning gait representation from massive unlabelled walking videos: A benchmark. TPAMI, 2023.
  16. Opengait: Revisiting gait recognition toward better practicality. CVPR, 2023.
  17. GaitPart: Temporal part-based model for gait recognition. In CVPR, 2020.
  18. Densely connected search space for more flexible neural architecture search. arXiv preprint arXiv:1906.09607, 2019.
  19. Horizontal pyramid matching for person re-identification. In AAAI, 2019.
  20. Jointly de-biasing face recognition and demographic attribute estimation. In ECCV, 2020.
  21. R. Gross and J. Shi. The CMU motion of body (MoBo) database. 2001.
  22. MS-Celeb-1M: A dataset and benchmark for large-scale face recognition. In ECCV, 2016.
  23. Single path one-shot neural architecture search with uniform sampling. In ECCV, 2020.
  24. J. Han and B. Bhanu. Individual recognition using gait energy image. TPAMI, 2006.
  25. Mask R-CNN. In ICCV, 2017.
  26. Deep residual learning for image recognition. In CVPR, 2016.
  27. Multi-task GANs for view-specific feature learning in gait recognition. TIFS, 2019.
  28. In defense of the triplet loss for person re-identification. arXiv:1703.07737, 2017.
  29. The TUM gait from audio, image and depth (GAID) database: Multimodal recognition of subjects and traits. JVCIR, 2014.
  30. The tum gait from audio, image and depth (gaid) database: Multimodal recognition of subjects and traits. JVCIR, 2014.
  31. Clothing-invariant gait identification using part-based clothing categorization and adaptive weight control. PR, 2010.
  32. Gait lateral network: Learning discriminative and compact representations for gait recognition. In ECCV, 2020.
  33. Context-sensitive temporal feature learning for gait recognition. In ICCV, 2021.
  34. CurricularFace: adaptive curriculum learning loss for deep face recognition. In CVPR, 2020.
  35. Flownet 2.0: Evolution of optical flow estimation with deep networks. In CVPR, 2017.
  36. S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML, 2015.
  37. The OU-ISIR gait database comprising the large population dataset and performance evaluation of gait recognition. TIFS, 2012.
  38. The MegaFace benchmark: 1 million faces for recognition at scale. In CVPR, 2016.
  39. Combined depth space based architecture search for person re-identification. In CVPR, 2021.
  40. Global-local temporal representations for video person re-identification. In ICCV, 2019.
  41. Unsupervised person re-identification by deep learning tracklet association. In ECCV, 2018.
  42. An in-depth exploration of person re-identification and gait recognition in cloth-changing conditions. In CVPR, 2023.
  43. DeepReID: Deep filter pairing neural network for person re-identification. In CVPR, 2014.
  44. End-to-end model-based gait recognition using synchronized multi-view pose constraint. In ICCVW, 2021.
  45. Multi-view large population gait database with human meshes and its performance evaluation. TBIOM, 2022.
  46. Joint intensity transformer network for gait recognition robust against clothing and carrying status. TIFS, 2019.
  47. Gait recognition via semi-supervised disentangled representation learning to identity and covariate features. In CVPR, 2020.
  48. End-to-end model-based gait recognition. In ACCV, 2020.
  49. Gaitedge: Beyond plain end-to-end gait recognition for better practicality. In ECCV, 2022.
  50. Pose-based temporal-spatial network (PTSN) for gait recognition with carrying and clothing variations. In CCBR, 2017.
  51. A model-based gait recognition method with body pose and human prior knowledge. PR, 2020.
  52. Learning effective representations from global and local features for cross-view gait recognition. arXiv preprint arXiv:2011.01461, 2020.
  53. Microsoft COCO: Common objects in context. In ECCV, 2014.
  54. Auto-deeplab: Hierarchical neural architecture search for semantic image segmentation. In CVPR, 2019.
  55. Memory-based gait recognition. In BMVC, 2016.
  56. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055, 2018.
  57. Human identity and gender recognition from gait sequences with arbitrary walking directions. TIFS, 2014.
  58. Bag of tricks and a strong baseline for deep person re-identification. In CVPR Workshops, 2019.
  59. The OU-ISIR gait database comprising the treadmill dataset. CVA, 2012.
  60. Gait analysis of gender and age using a large-scale multi-view gait database. In ACCV, 2010.
  61. Resgait: The real-scene gait dataset. In IJCB, 2021.
  62. V. Nair and G. E. Hinton. Rectified linear units improve restricted boltzmann machines. In ICML, 2010.
  63. Gait-based person re-identification: A survey. ACM Computing Surveys, 2019.
  64. Pytorch: An imperative style, high-performance deep learning library. In NeurIPS, 2019.
  65. Efficient neural architecture transformation search in channel-level for object detection. In NeurIPS, 2019.
  66. Auto-reid: Searching for a part-aware convnet for person re-identification. In ICCV, 2019.
  67. ImageNet large scale visual recognition challenge. IJCV, 2015.
  68. Autodispnet: Improving disparity estimation with automl. In ICCV, 2019.
  69. The humanID gait challenge problem: Data sets, performance, and analysis. TPAMI, 2005.
  70. FaceNet: A unified embedding for face recognition and clustering. In CVPR, 2015.
  71. Long range gait matching using 3d body fitting with gait-specific motion constraints. In WACV, 2023.
  72. Lidargait: Benchmarking 3d gait recognition with point clouds. In CVPR, 2023.
  73. GEINet: View-invariant gait recognition using a convolutional neural network. In ICB, 2016.
  74. On a large sequence-based human gait database. In Applications and Science in Soft Computing. 2004.
  75. Region-based quality estimation network for large-scale person re-identification. In AAAI, 2018.
  76. Deep high-resolution representation learning for human pose estimation. In CVPR, 2019.
  77. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In ECCV, 2018.
  78. DeepFace: Closing the gap to human-level performance in face verification. In CVPR, 2014.
  79. On Input/Output architectures for convolutional neural network-based cross-view gait recognition. TCSVT, 2017.
  80. Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition. CVA, 2018.
  81. Efficient night gait recognition based on template matching. In ICPR, 2006.
  82. Efficientdet: Scalable and efficient object detection. arXiv preprint arXiv:1911.09070, 2019.
  83. GaitGraph: Graph convolutional network for skeleton-based gait recognition. arXiv preprint arXiv:2101.11228, 2021.
  84. Silhouette transformation based on walking speed for gait identification. In CVPR, 2010.
  85. The OU-ISIR large population gait database with real-life carried object and its performance evaluation. CVA, 2018.
  86. CosFace: Large margin cosine loss for deep face recognition. In CVPR, 2018.
  87. Silhouette analysis-based gait recognition for human identification. TPAMI, 2003.
  88. M. Wang and W. Deng. Mitigate bias in face recognition using skewness-aware reinforcement learning. arXiv preprint arXiv:1911.10692, 2019.
  89. Racial faces in the wild: Reducing racial bias by information maximization adaptation network. In CVPR, 2019.
  90. Dygait: Exploiting dynamic representations for high-performance gait recognition. 2023.
  91. Gaitstrip: Gait recognition via effective strip-based feature representations and multi-level framework. In ACCV, 2022.
  92. Person re-identification by video ranking. In ECCV, 2014.
  93. Person transfer GAN to bridge domain gap for person re-identification. In CVPR, 2018.
  94. Multi-view gait recognition using 3D convolutional neural networks. In ICIP, 2016.
  95. Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search. In CVPR, 2019.
  96. Spatial-temporal graph attention network for video-based gait recognition. In ACPR, 2019.
  97. Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning. In CVPR, 2018.
  98. A comprehensive study on cross-view gait based human identification with deep CNNs. TPAMI, 2017.
  99. Margin sample mining loss: A deep learning based method for person re-identification. arXiv:1710.00478, 2017.
  100. Gait recognition from a single image using a phase-aware gait cycle reconstruction network. In ECCV, 2020.
  101. The OU-ISIR gait database comprising the large population dataset with age and performance evaluation of age estimation. CVA, 2017.
  102. Y. Xu and Z. Wang. End-to-end model-based gait recognition with matching module based on graph neural networks. In ISAS, 2023.
  103. Person re-identification by contour sketch under moderate clothing change. TPAMI, 2019.
  104. Learning face representation from scratch. arXiv:1411.7923, 2014.
  105. GaitGAN: Invariant gait feature extraction using generative adversarial networks. In CVPRW, 2017.
  106. Invariant feature extraction for gait recognition using only one uniform model. Neurocomputing, 2017.
  107. Cocas: A large-scale clothes changing person dataset for re-identification. In CVPR, 2020.
  108. A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In ICPR, 2006.
  109. Learning joint gait representation via quintuplet loss minimization. In CVPR, 2019.
  110. Learning spatial-temporal representations over walking tracklet for long-term person re-identification in the wild. TMM, 2020.
  111. Realgait: Gait recognition for person re-identification. arXiv preprint arXiv:2201.04806, 2022.
  112. AlignedReID: Surpassing human-level performance in person re-identification. arXiv:1711.08184, 2017.
  113. Cross-view gait recognition by discriminative feature learning. TIP, 2019.
  114. Customizable architecture search for semantic segmentation. In CVPR, 2019.
  115. Gait recognition via disentangled representation learning. In CVPR, 2019.
  116. Gait recognition in the wild with multi-hop temporal switch. In ACM MM, 2022.
  117. Gait recognition in the wild with dense 3d representations and a benchmark. In CVPR, 2022.
  118. MARS: A video benchmark for large-scale person re-identification. In ECCV, 2016.
  119. Scalable person re-identification: A benchmark. In ICCV, 2015.
  120. Person re-identification: Past, present and future. arXiv:1610.02984, 2016.
  121. Unlabeled samples generated by gan improve the person re-identification baseline in vitro. In ICCV, 2017.
  122. N. Zhu. Neural architecture search for deep face recognition. arXiv preprint arXiv:1904.09523, 2019.
  123. Gait recognition in the wild: A benchmark. In ICCV, 2021.
  124. WebFace260M: A benchmark unveiling the power of million-scale deep face recognition. In CVPR, 2021.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now