ABSTRACT
Recent advancements in data science have introduced implicit neural representations as a powerful approach for learning complex, high-dimensional functions, bypassing the need for explicit equations or manual feature engineering. In this paper, we present our research on employing the weights of these implicit neural representations to characterize and classify batches of data, referred to as 'functas.' This approach eliminates the need for manual feature engineering on raw data. Specifically, we showcase the efficacy of the 'functas' method in the domain of human activity recognition, utilizing output data from sensors such as accelerometers and gyroscopes. Our results demonstrate the promising potential of the 'functas' approach, suggesting a potential shift in the paradigm of data science methodologies.
- Matan Atzmon and Yaron Lipman. "Sal: Sign agnostic learning of shapes from raw data". In: Proc. CVPR. 2020.Google ScholarCross Ref
- Rohan Chabra et al. "Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction". In: arXiv preprint arXiv:2003.10983 (2020).Google Scholar
- Sravan Challa, Akhilesh Kumar, and Vijay Semwal. "A multibranch CNN-BiLSTM model for human activity recognition using wearable sensor data". In: The Visual Computer 38 (Aug. 2021). doi: 10.1007/s00371-021-02283--3.Google ScholarCross Ref
- Hao Chen et al. NeRV: Neural Representations for Videos. 2021. arXiv: 2110.13903 [cs.CV].Google Scholar
- Tianqi Chen and Carlos Guestrin. "XGBoost". In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, Aug. 2016. doi: 10.1145/2939672.2939785. url: https://doi.org/10.1145% 2F2939672.2939785.Google ScholarDigital Library
- Zeyuan Chen et al. VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution. 2022. arXiv: 2206.04647 [eess.IV].Google Scholar
- Emilien Dupont et al. From data to functa: Your data point is a function and you can treat it like one. 2022. arXiv: 2201.12204 [cs.LG].Google Scholar
- Brandon Yushan Feng, Susmija Jabbireddy, and Amitabh Varshney. "VIINTER: View Interpolation with Implicit Neural Representations of Images". In: SIGGRAPH Asia 2022 Conference Papers. ACM, Nov. 2022. doi: 10.1145/3550469. 3555417. url: https://doi.org/10.1145%2F3550469.3555417.Google ScholarDigital Library
- Kyle Genova et al. "Deep Structured Implicit Functions". In: arXiv preprint arXiv:1912.06126 (2019).Google Scholar
- Kyle Genova et al. "Learning shape templates with structured implicit functions". In: Proc. ICCV. 2019, pp. 7154--7164.Google Scholar
- Amos Gropp et al. "Implicit geometric regularization for learning shapes". In: arXiv preprint arXiv:2002.10099 (2020).Google Scholar
- Chiyu Jiang et al. "Local implicit grid representations for 3d scenes". In: Proc. CVPR. 2020, pp. 6001--6010.Google Scholar
- Reyes-Ortiz Jorge et al. Human Activity Recognition Using Smartphones. UCI Machine Learning Repository. 2012.Google Scholar
- Dafne van Kuppevelt, Vincent van Hees, and Christiaan Meijer. PAMAP2 dataset preprocessed v0.3.0. Zenodo, July 2017. doi: 10.5281/zenodo.834467. url: https://doi.org/10. 5281/zenodo.834467.Google ScholarCross Ref
- Jennifer R. Kwapisz, Gary M. Weiss, and Samuel A. Moore. "Activity Recognition Using Cell Phone Accelerometers". In: SIGKDD Explor. Newsl. 12.2 (Mar. 2011), pp. 74--82. issn: 1931- 0145. doi: 10.1145/1964897.1964918. url: https://doi.org/10. 1145/1964897.1964918.Google ScholarDigital Library
- Luca A. Lanzendörfer and Roger Wattenhofer. Siamese SIREN: Audio Compression with Implicit Neural Representations. 2023. arXiv: 2306.12957 [cs.SD].Google Scholar
- Mateusz Michalkiewicz et al. "Implicit surface representations as layers in neural networks". In: Proc. ICCV. 2019, pp. 4743--4752.Google Scholar
- Jeong Joon Park et al. "DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation". In: Proc. CVPR (2019).Google Scholar
- Songyou Peng et al. "Convolutional occupancy networks". In: arXiv preprint arXiv:2003.04618 (2020).Google Scholar
- Vincent Sitzmann, Michael Zollhöfer, and Gordon Wetzstein. "Scene Representation Networks: Continuous 3D-StructureAware Neural Scene Representations". In: Proc. NeurIPS. 2019.Google Scholar
- Vincent Sitzmann et al. Implicit Neural Representations with Periodic Activation Functions. 2020. arXiv: 2006.09661 [cs.CV].Google Scholar
- Yannick Strümpler et al. Implicit Neural Representations for Image Compression. 2022. arXiv: 2112.04267 [eess.IV].Google Scholar
- Filip Szatkowski et al. Hypernetworks build Implicit Neural Representations of Sounds. 2023. arXiv: 2302.04959 [cs.LG].Google ScholarDigital Library
- Filip Szatkowski et al. HyperSound: Generating Implicit Neural Representations of Audio Signals with Hypernetworks. 2022. arXiv: 2211.01839 [cs.SD].Google Scholar
- Dejia Xu et al. Signal Processing for Implicit Neural Representations. 2022. arXiv: 2210.08772 [cs.CV]Google Scholar
Index Terms
- Functas Usability for Human Activity Recognition using Wearable Sensor Data
Recommendations
A multibranch CNN-BiLSTM model for human activity recognition using wearable sensor data
AbstractHuman activity recognition (HAR) has become a significant area of research in human behavior analysis, human–computer interaction, and pervasive computing. Recently, deep learning (DL)-based methods have been applied successfully to time-series ...
Transformer-Based Recognition of Activities of Daily Living from Wearable Sensor Data
iWOAR '22: Proceedings of the 7th International Workshop on Sensor-based Activity Recognition and Artificial IntelligenceSmart support systems for the recognition of Activities of Daily Living (ADLs) can help elderly people live independently for longer improving their standard of living. Many machine learning approaches have been proposed lately for Human Activity ...
Hybrid deep learning approaches for smartphone sensor-based human activity recognition
AbstractHuman Activity Recognition (HAR) has become one of the most important research fields to achieve real-time monitoring of human activities for timely decision making in various applications like fall detection, elderly care etc. Now-a-days, most ...
Comments