An Investigation of Frequency-Domain Pruning Algorithms for Accelerating Human Activity Recognition Tasks Based on Sensor Data
Source abstract
Abstract
The rapidly advancing Convolutional Neural Networks (CNNs) have brought about a paradigm shift in various computer vision tasks, while also garnering increasing interest and application in sensor-based Human Activity Recognit... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Context-Aware Activity Recognition Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (55)
Show source-provided references
1. Human activity recognition using temporal convolutional neural network architecture10.1016/j.eswa.2021.116287 ↗
2. A hybrid tuple selection pipeline for smartphone based human activity recognition10.1016/j.eswa.2023.119536 ↗
3. Smartphone-based human activity recognition using lightweight multiheaded temporal convolutional network
4. A tutorial on human activity recognition using body-worn inertial sensors10.1145/2499621 ↗
5. Nohar-novelty discrete data stream for human activity recognition based on smartphones with inertial sensors10.1016/j.eswa.2020.114093 ↗
6. Fine-grained and real-time gesture recognition by using IMU sensors10.1109/TMC.2021.3120475 ↗
7. Meal: Multi-model ensemble via adversarial learning
8. H. Li, A. Kadav, I. Durdanovic, H. Samet, and H. P. Graf, “Pruning filters for efficient convnets,” 2017. doi: 10.48550/arXiv.1608.08710.
9. Combining weight pruning and knowledge distillation for CNN compression
10. S. Guo, Y. Wang, Q. Li, and J. Yan, “DMCP: Differentiable markov channel pruning for neural networks,” 2020. doi: 10.48550/arXiv.2005.03354.10.1109/CVPR42600.2020.00161 ↗
11. Pedestrian and vehicle detection based on pruning yolov4 with cloud-edge collaboration
12. Exploiting similarity-induced redundancies in correlation topology for channel pruning in deep convolutional neural networks
13. J. -H. Luo and J. Wu, “An entropy-based pruning method for CNN compression,” 2017. doi: 10.48550/arXiv.1706.05791.
14. M. Lin et al., “HRank: Filter pruning using high-rank feature map,” 2020. doi: 10.48550/arXiv.2002.10179.10.1109/CVPR42600.2020.00160 ↗
15. Imagenet classification with deep convolutional neural networks10.1145/3065386 ↗
16. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 2015. doi: 10.48550/arXiv.1409.1556.
17. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2015. doi: 10.1109/CVPR.2016.90.10.1109/CVPR.2016.90 ↗
18. G. Huang, Z. Liu, L. Van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” 2018. doi: 10.1109/CVPR.2017.243.10.1109/CVPR.2017.243 ↗
19. R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” 2014. doi: 10.1109/CVPR.2014.81.10.1109/CVPR.2014.81 ↗
20. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
21. B. Singh, M. Najibi, and L. S. Davis, “SNIPER: Efficient multi-scale training,” 2018. doi: 10.48550/arXiv.1805.09300.
22. Improved YOLOv8n model for detecting helmets and license plates on electric bicycles
23. Fully convolutional networks for semantic segmentation10.1109/TPAMI.2016.2572683 ↗
24. Asymmetric non-local neural networks for semantic segmentation
25. Deep learning for video object segmentation: A review10.1007/s10462-022-10176-7 ↗
26. M. Zeng et al., “Understanding and improving recurrent networks for human activity recognition by continuous attention,” 2018. doi: 10.1145/3267242.3267286.10.1145/3267242.3267286 ↗
27. Human activity recognition with smartphone sensors using deep learning neural networks10.1016/j.eswa.2016.04.032 ↗
28. Deep convolutional neural networks on multichannel time series for human activity recognition
29. Second order derivatives for network pruning: Optimal brain surgeon
30. Aghasi · Neural Information Processing Systems · 2016
31. Y. He, G. Kang, X. Dong, Y. Fu, and Y. Yang, “Soft filter pruning for accelerating deep convolutional neural networks,” 2018. doi: 10.48550/arXiv.1808.06866.10.24963/ijcai.2018/309 ↗
32. You · Advances in Neural Information Processing Systems · 2019 · 32
33. Efficient filter pruning: Reducing model complexity through redundancy graph decomposition10.1016/j.neucom.2024.128108 ↗
34. A graphical approach for filter pruning by exploring the similarity relation between feature maps10.1016/j.patrec.2022.12.028 ↗
35. Y. Tang et al., “Scop: Scientific control for reliable neural network pruning,” 2021. doi: 10.48550/arXiv.2010.10732.
36. Filter pruning via geometric median for deep convolutional neural networks acceleration
37. H. Hu, R. Peng, Y. Tai, and C. Tang, “Network trimming: A data-driven neuron pruning approach towards efficient deep architectures,” 2016. doi: 10.48550/arXiv.1607.03250.
38. Z. Liu, J. Li, Z. Shen, G. Huang, S. Yan and C. Zhang, “Learning efficient convolutional networks through network slimming,” 2017. doi: 10.48550/arXiv.1708.06519.10.1109/ICCV.2017.298 ↗
39. P. Singh, V. K. Verma, P. Rai, and V. P. Namboodiri, “Leveraging filter correlations for deep model compression,” 2020. doi: 10.48550/arXiv.1811.10559.10.1109/WACV45572.2020.9093331 ↗
40. Auto-balanced filter pruning for efficient convolutional neural networks
41. H. Wang, C. Qin, Y. Zhang, and Y. Fu, “Neural pruning via growing regularization,” 2021. doi: 10.48550/arXiv.2012.09243.
42. Deep learning for sensor-based human activity recognition: Overview, challenges, and opportunities
43. Sensor-based and vision-based human activity recognition: A comprehensive survey
44. Anguita · Ambient Assisted Living and Home Care · 2012 · 21610.1007/978-3-642-35395-6_30 ↗
45. Activity recognition using cell phone accelerometers10.1145/1964897.1964918 ↗
46. Introducing a new benchmarked dataset for activity monitoring
47. Convolutional neural networks for human activity recognition using mobile sensors
48. A. Paszke et al., “PyTorch: An imperative style, high-performance deep learning library,” 2019. doi: 10.48550/arXiv.1912.01703.
49. An automatic network structure search via channel pruning for accelerating human activity inference on mobile devices10.1016/j.eswa.2023.122180 ↗
50. Evidential reasoning with hesitant fuzzy belief structures for human activity recognition10.1109/TFUZZ.2021.3079495 ↗
51. Real-time human activity recognition from accelerometer data using convolutional neural networks10.1016/j.asoc.2017.09.027 ↗
52. Deep convolutional networks with tunable speed accuracy tradeoff for human activity recognition using wearables10.1109/TIM.2022.3216413 ↗
53. Human activity recognition using wearable sensors by heterogeneous convolutional neural networks10.1016/j.eswa.2022.116764 ↗
54. AttnSense: Multi-level attention mechanism for multimodal human activity recognition
55. K. Xu, M. Qin, F. Sun, Y. Wang, Y. Chen and F. Ren, “Learning in the frequency domain,” 2020. doi: 10.1109/CVPR42600.2020.10.1109/CVPR42600.2020.00181 ↗