Papers
Topics
Authors
Recent
Search
2000 character limit reached

Activity-Biometrics: Person Identification from Daily Activities

Published 26 Mar 2024 in cs.CV | (2403.17360v1)

Abstract: In this work, we study a novel problem which focuses on person identification while performing daily activities. Learning biometric features from RGB videos is challenging due to spatio-temporal complexity and presence of appearance biases such as clothing color and background. We propose ABNet, a novel framework which leverages disentanglement of biometric and non-biometric features to perform effective person identification from daily activities. ABNet relies on a bias-less teacher to learn biometric features from RGB videos and explicitly disentangle non-biometric features with the help of biometric distortion. In addition, ABNet also exploits activity prior for biometrics which is enabled by joint biometric and activity learning. We perform comprehensive evaluation of the proposed approach across five different datasets which are derived from existing activity recognition benchmarks. Furthermore, we extensively compare ABNet with existing works in person identification and demonstrate its effectiveness for activity-based biometrics across all five datasets. The code and dataset can be accessed at: \url{https://github.com/sacrcv/Activity-Biometrics/}

Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Elastic transform. https://pytorch.org/vision/main/generated/torchvision.transforms.ElasticTransform.html. [Online; accessed 08-November-2023].
  2. Past, present, and future of face recognition: A review. Electronics, 9(8):1188, 2020.
  3. Vivit: A video vision transformer. In ICCV, pages 6836–6846, 2021.
  4. Salient-to-broad transition for video person re-identification. In CVPR, pages 7339–7348, 2022.
  5. Pstr: End-to-end one-step person search with transformers. In CVPR, pages 9458–9467, 2022.
  6. Learning recurrent 3d attention for video-based person re-identification. IEEE TIP, 29:6963–6976, 2020.
  7. Learning 3d shape feature for texture-insensitive person re-identification. In CVPR, pages 8146–8155, 2021.
  8. Masked-attention mask transformer for universal image segmentation. In CVPR, 2022.
  9. Pku-mmd: A large scale benchmark for continuous multi-modal human action understanding. arXiv preprint arXiv:1703.07475, 2017.
  10. Expanding accurate person recognition to new altitudes and ranges: The briar dataset. In WACV, pages 593–602, 2023.
  11. Video person re-identification by temporal residual learning. IEEE TIP, 28(3):1366–1377, 2018.
  12. Video-based person re-identification with spatial and temporal memory networks. In ICCV, pages 12036–12045, 2021.
  13. Gaitpart: Temporal part-based model for gait recognition. In CVPR, pages 14225–14233, 2020.
  14. Opengait: Revisiting gait recognition towards better practicality. In CVPR, pages 9707–9716, 2023.
  15. Appearance-preserving 3d convolution for video-based person re-identification. In ECCV, pages 228–243. Springer, 2020.
  16. Clothes-changing person re-identification with rgb modality only. In CVPR, pages 1060–1069, 2022.
  17. Semantic-aware consistency network for cloth-changing person re-identification. In ACM MM, 2023.
  18. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016.
  19. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015.
  20. Fine-grained shape-appearance mutual learning for cloth-changing person re-identification. In CVPR, pages 10513–10522, 2021.
  21. Bicnet-tks: Learning efficient spatial-temporal representation for video person re-identification. In CVPR, pages 2014–2023, 2021.
  22. Celebrities-reid: A benchmark for clothes variation in long-term person re-identification. In IJCNN, pages 1–8. IEEE, 2019.
  23. Rethinking temporal fusion for video-based person re-identification on semantic and time aspect. In AAAI, pages 11133–11140, 2020.
  24. Cloth-changing person re-identification from a single image with gait prediction and regularization. In CVPR, pages 14278–14287, 2022.
  25. Adam: A method for stochastic optimization. ICLR, 2015.
  26. Mvitv2: Improved multiscale vision transformers for classification and detection. In CVPR, pages 4804–4814, 2022.
  27. Gaitedge: Beyond plain end-to-end gait recognition for better practicality. In ECCV, pages 375–390. Springer, 2022.
  28. Gait recognition via effective global-local feature representation and local temporal aggregation. In ICCV, pages 14648–14656, 2021.
  29. Spatially and temporally efficient non-local attention network for video-based person re-identification. arXiv preprint arXiv:1908.01683, 2019a.
  30. Ntu rgb+ d 120: A large-scale benchmark for 3d human activity understanding. IEEE TPAMI, 42(10):2684–2701, 2019b.
  31. Deep learning face attributes in the wild. In ICCV, 2015.
  32. Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV, pages 10012–10022, 2021.
  33. Magface: A universal representation for face recognition and quality assessment. In CVPR, pages 14225–14234, 2021.
  34. Accenture-mm1: A multimodal person recognition dataset. In WACVW, 2024.
  35. Robust re-identification by multiple views knowledge distillation. In ECCV, pages 93–110. Springer, 2020.
  36. Long-term cloth-changing person re-identification. In ACCV, 2020.
  37. Grounded sam: Assembling open-world models for diverse visual tasks, 2024.
  38. Hollywood in homes: Crowdsourcing data collection for activity understanding. In ECCV, pages 510–526, 2016.
  39. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. NeurIPS, 30, 2017.
  40. Pyramid spatial-temporal aggregation for video-based person re-identification. In ICCV, pages 12026–12035, 2021.
  41. Distilled person re-identification: Towards a more scalable system. In CVPR, pages 1187–1196, 2019.
  42. Person re-identification by contour sketch under moderate clothing change. IEEE TPAMI, 43(6):2029–2046, 2019.
  43. Good is bad: Causality inspired cloth-debiasing for cloth-changing person re-identification. In CVPR, pages 1472–1481, 2023.
  44. Deep learning for person re-identification: A survey and outlook. IEEE TPAMI, 44(6):2872–2893, 2021.
  45. A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In ICPR, pages 441–444, 2006.
  46. Image-to-video person re-identification with temporally memorized similarity learning. IEEE TCSVT, 28(10):2622–2632, 2017.
  47. Gait recognition via disentangled representation learning. In CVPR, pages 4710–4719, 2019.
  48. Scalable person re-identification: A benchmark. In ICCV, pages 1116–1124, 2015.
Citations (2)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free