Papers
Topics
Authors
Recent
2000 character limit reached

Density-Guided Label Smoothing for Temporal Localization of Driving Actions (2403.06616v1)

Published 11 Mar 2024 in cs.CV

Abstract: Temporal localization of driving actions plays a crucial role in advanced driver-assistance systems and naturalistic driving studies. However, this is a challenging task due to strict requirements for robustness, reliability and accurate localization. In this work, we focus on improving the overall performance by efficiently utilizing video action recognition networks and adapting these to the problem of action localization. To this end, we first develop a density-guided label smoothing technique based on label probability distributions to facilitate better learning from boundary video-segments that typically include multiple labels. Second, we design a post-processing step to efficiently fuse information from video-segments and multiple camera views into scene-level predictions, which facilitates elimination of false positives. Our methodology yields a competitive performance on the A2 test set of the naturalistic driving action recognition track of the 2022 NVIDIA AI City Challenge with an F1 score of 0.271.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. World Health Organization. Global status report on road safety 2015. World Health Organization, 2015.
  2. Rethinking the faster r-cnn architecture for temporal action localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1130–1139, 2018.
  3. Graph convolutional networks for temporal action localization. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 7094–7103, 2019.
  4. The lear submission at thumos 2014, 2014.
  5. Action recognition and detection by combining motion and appearance features. THUMOS14 Action Recognition Challenge, 1(2):2, 2014.
  6. A markov clustering topic model for mining behaviour in video. In 2009 IEEE 12th International Conference on Computer Vision, pages 1165–1172. IEEE, 2009.
  7. Louis Kratz and Ko Nishino. Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In 2009 IEEE conference on computer vision and pattern recognition, pages 1446–1453. IEEE, 2009.
  8. Online detection of unusual events in videos via dynamic sparse coding. In CVPR 2011, pages 3313–3320. IEEE, 2011.
  9. Adaptive sparse representations for video anomaly detection. IEEE Transactions on Circuits and Systems for Video Technology, 24(4):631–645, 2013.
  10. Histograms of oriented optical flow and binet-cauchy kernels on nonlinear dynamical systems for the recognition of human actions. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 1932–1939. IEEE, 2009.
  11. Histograms of optical flow orientation and magnitude and entropy to detect anomalous events in videos. IEEE Transactions on Circuits and Systems for Video Technology, 27(3):673–682, 2016.
  12. Anomaly detection and localization in crowded scenes. IEEE transactions on pattern analysis and machine intelligence, 36(1):18–32, 2013.
  13. Sparse reconstruction cost for abnormal event detection. In CVPR 2011, pages 3449–3456. IEEE, 2011.
  14. Deep analysis of cnn-based spatio-temporal representations for action recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6165–6175, 2021.
  15. Temporal segment networks: Towards good practices for deep action recognition. In European conference on computer vision, pages 20–36. Springer, 2016.
  16. Temporal shift module for efficient video understanding. corr abs/1811.08383 (2018), 1811.
  17. More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation. Advances in Neural Information Processing Systems, 32, 2019.
  18. Learning spatiotemporal features with 3d convolutional networks. In Proceedings of the IEEE international conference on computer vision, pages 4489–4497, 2015.
  19. Quo vadis, action recognition? a new model and the kinetics dataset. In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 6299–6308, 2017.
  20. Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet? In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 6546–6555, 2018.
  21. Grouped spatial-temporal aggregation for efficient action recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5512–5521, 2019.
  22. Gate-shift networks for video action recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1102–1111, 2020.
  23. Slowfast networks for video recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 6202–6211, 2019.
  24. Fast saliency based pooling of fisher encoded dense trajectories. In ECCV THUMOS Workshop, volume 1, page 5, 2014.
  25. Temporal action localization with pyramid of score distribution features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3093–3102, 2016.
  26. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28, 2015.
  27. Driver anomaly detection: A dataset and contrastive learning approach. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 91–100, 2021.
  28. Drive&act: A multi-modal dataset for fine-grained driver behavior recognition in autonomous vehicles. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2801–2810, 2019.
  29. Driver distraction identification with an ensemble of convolutional neural networks. Journal of Advanced Transportation, 2019, 2019.
  30. The kinetics human action video dataset. arXiv preprint arXiv:1705.06950, 2017.
  31. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826, 2016.
  32. Synthetic distracted driving (syndd1) dataset for analyzing distracted behaviors and various gaze zones of a driver, 2022.
Citations (4)
View on Semantic Scholar

Summary

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

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

Open Problems

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

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

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up