Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

HiH: A Multi-modal Hierarchy in Hierarchy Network for Unconstrained Gait Recognition (2311.11210v2)

Published 19 Nov 2023 in cs.CV

Abstract: Gait recognition has achieved promising advances in controlled settings, yet it significantly struggles in unconstrained environments due to challenges such as view changes, occlusions, and varying walking speeds. Additionally, efforts to fuse multiple modalities often face limited improvements because of cross-modality incompatibility, particularly in outdoor scenarios. To address these issues, we present a multi-modal Hierarchy in Hierarchy network (HiH) that integrates silhouette and pose sequences for robust gait recognition. HiH features a main branch that utilizes Hierarchical Gait Decomposer (HGD) modules for depth-wise and intra-module hierarchical examination of general gait patterns from silhouette data. This approach captures motion hierarchies from overall body dynamics to detailed limb movements, facilitating the representation of gait attributes across multiple spatial resolutions. Complementing this, an auxiliary branch, based on 2D joint sequences, enriches the spatial and temporal aspects of gait analysis. It employs a Deformable Spatial Enhancement (DSE) module for pose-guided spatial attention and a Deformable Temporal Alignment (DTA) module for aligning motion dynamics through learned temporal offsets. Extensive evaluations across diverse indoor and outdoor datasets demonstrate HiH's state-of-the-art performance, affirming a well-balanced trade-off between accuracy and efficiency.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. Performance evaluation of model-based gait on multi-view very large population database with pose sequences. IEEE TBIOM, 2(4):421–430, 2020.
  2. Gait recognition using gait entropy image. In ICDP, pages 1–6, 2009.
  3. On using gait in forensic biometrics. Journal of forensic sciences, 56(4):882–889, 2011.
  4. Lagrange motion analysis and view embeddings for improved gait recognition. In CVPR, pages 20249–20258, 2022.
  5. Gaitset: Regarding gait as a set for cross-view gait recognition. In AAAI, pages 8126–8133, 2019.
  6. Multi-modal gait recognition via effective spatial-temporal feature fusion. In CVPR, pages 17949–17957, 2023.
  7. Metagait: Learning to learn an omni sample adaptive representation for gait recognition. In ECCV, pages 357–374. Springer, 2022.
  8. Gaitgci: Generative counterfactual intervention for gait recognition. In CVPR, pages 5578–5588, 2023.
  9. Gaitpart: Temporal part-based model for gait recognition. In CVPR, pages 14225–14233, 2020.
  10. Opengait: Revisiting gait recognition towards better practicality. In CVPR, pages 9707–9716, 2023.
  11. Gait biomechanics in the era of data science. Journal of biomechanics, 49(16):3759–3761, 2016.
  12. Gait recognition based on deep learning: A survey. CSUR, 55(2):1–34, 2022.
  13. Gpgait: Generalized pose-based gait recognition. In ICCV, pages 19595–19604, 2023.
  14. Physics-augmented autoencoder for 3d skeleton-based gait recognition. In ICCV, pages 19627–19638, 2023.
  15. Individual recognition using gait energy image. IEEE TPAMI, 28(2):316–322, 2005.
  16. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016.
  17. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737, 2017.
  18. Gait lateral network: Learning discriminative and compact representations for gait recognition. In ECCV, pages 382–398. Springer, 2020.
  19. Set residual network for silhouette-based gait recognition. IEEE TBIOM, 3(3):384–393, 2021.
  20. Learning temporal attention based keypoint-guided embedding for gait recognition. IEEE JSTSP, 2023.
  21. Context-sensitive temporal feature learning for gait recognition. In ICCV, pages 12909–12918, 2021a.
  22. 3d local convolutional neural networks for gait recognition. In ICCV, pages 14920–14929, 2021b.
  23. Transgait: Multimodal-based gait recognition with set transformer. Applied Intelligence, 53(2):1535–1547, 2023.
  24. End-to-end model-based gait recognition using synchronized multi-view pose constraint. In ICCV, pages 4106–4115, 2021.
  25. Gaitedge: Beyond plain end-to-end gait recognition for better practicality. In ECCV, pages 375–390. Springer, 2022.
  26. A model-based gait recognition method with body pose and human prior knowledge. PR, 98:107069, 2020.
  27. Gait recognition via effective global-local feature representation and local temporal aggregation. In ICCV, pages 14648–14656, 2021.
  28. Bag of tricks and a strong baseline for deep person re-identification. In CVPRW, pages 0–0, 2019.
  29. Dynamic aggregated network for gait recognition. In CVPR, pages 22076–22085, 2023a.
  30. Fine-grained unsupervised domain adaptation for gait recognition. In ICCV, pages 11313–11322, 2023b.
  31. Forensic gait analysis and recognition: standards of evidence admissibility. Journal of forensic sciences, 64(5):1294–1303, 2019.
  32. Learning rich features for gait recognition by integrating skeletons and silhouettes. Multimedia Tools and Applications, pages 1–22, 2023.
  33. Kinematic gait patterns in healthy runners: A hierarchical cluster analysis. Journal of biomechanics, 48(14):3897–3904, 2015.
  34. User verification leveraging gait recognition for smartphone enabled mobile healthcare systems. IEEE TMC, 14(9):1961–1974, 2014.
  35. Forensic gait analysis—morphometric assessment from surveillance footage. Forensic science international, 296:57–66, 2019.
  36. Deep gait recognition: A survey. IEEE TPAMI, 45(1):264–284, 2022.
  37. Gaitnet: An end-to-end network for gait based human identification. PR, 96:106988, 2019.
  38. Gait-based identification for elderly users in wearable healthcare systems. Information fusion, 53:134–144, 2020.
  39. Deep high-resolution representation learning for human pose estimation. In CVPR, pages 5693–5703, 2019.
  40. Multi-view large population gait dataset and its performance evaluation for cross-view gait recognition. IPSJ TCVA, 10:1–14, 2018.
  41. Gaitgraph: Graph convolutional network for skeleton-based gait recognition. In ICIP, pages 2314–2318, 2021.
  42. Towards a deeper understanding of skeleton-based gait recognition. In CVPR, pages 1569–1577, 2022.
  43. Iwin: Human-object interaction detection via transformer with irregular windows. In ECCV, pages 87–103, 2022.
  44. A survey on gait recognition. CSUR, 51(5):1–35, 2018.
  45. Silhouette analysis-based gait recognition for human identification. IEEE TPAMI, 25(12):1505–1518, 2003.
  46. Hierarchical spatio-temporal representation learning for gait recognition. In ICCV, pages 19639–19649, 2023a.
  47. Gaitmm: Multi-granularity motion sequence learning for gait recognition. In ICIP, pages 845–849. IEEE, 2023b.
  48. Dygait: Exploiting dynamic representations for high-performance gait recognition. In ICCV, pages 13424–13433, 2023c.
  49. Vision transformer with deformable attention. In CVPR, pages 4794–4803, 2022.
  50. Occlusion-aware human mesh model-based gait recognition. IEEE TIFS, 18:1309–1321, 2023.
  51. A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In ICPR, pages 441–444, 2006.
  52. Gait recognition via disentangled representation learning. In CVPR, pages 4710–4719, 2019.
  53. Gait recognition in the wild with multi-hop temporal switch. In ACM MM, pages 6136–6145, 2022a.
  54. Gait recognition in the wild with dense 3d representations and a benchmark. In CVPR, pages 20228–20237, 2022b.
  55. Parsing is all you need for accurate gait recognition in the wild. In ACM MM, pages 116–124, 2023.
  56. Gaitref: Gait recognition with refined sequential skeletons. arXiv preprint arXiv:2304.07916, 2023.
  57. Gait recognition in the wild: A benchmark. In ICCV, pages 14789–14799, 2021.

Summary

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

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