LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks

@article{Kumawat2019LP3DCNNUL,
  title={LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks},
  author={Sudhakar Kumawat and S. Raman},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={4898-4907}
}
  • Sudhakar Kumawat, S. Raman
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Traditional 3D Convolutional Neural Networks (CNNs) are computationally expensive, memory intensive, prone to overfit, and most importantly, there is a need to improve their feature learning capabilities. [...] Key Method The ReLPV block extracts the phase in a 3D local neighborhood (e.g., 3x3x3) of each position of the input map to obtain the feature maps.Expand
25 Citations
Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition
  • PDF
Dynamic Spatio-Temporal Feature Learning via Graph Convolution in 3D Convolutional Networks
Depthwise-STFT Based Separable Convolutional Neural Networks
  • Sudhakar Kumawat, S. Raman
  • Computer Science, Engineering
  • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2020
  • 2
  • PDF
Optimising 3D-CNN Design towards Human Pose Estimation on Low Power Devices
  • Highly Influenced
  • PDF
FGCN: Deep Feature-based Graph Convolutional Network for Semantic Segmentation of Urban 3D Point Clouds
  • Highly Influenced
  • PDF
View-based weight network for 3D object recognition
  • Qiang Huang, Yongxiong Wang, Zhong Yin
  • Computer Science
  • Image Vis. Comput.
  • 2020
  • 3
DAN: Deep-Attention Network for 3D Shape Recognition
  • Weizhi Nie, Yue Zhao, Dan Song, Yue Gao
  • Computer Science, Medicine
  • IEEE Transactions on Image Processing
  • 2021
Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes
  • 4
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 55 REFERENCES
Learning Spatiotemporal Features with 3D Convolutional Networks
  • 4,161
  • Highly Influential
  • PDF
Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?
  • 694
  • Highly Influential
  • PDF
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
  • 700
  • PDF
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
  • 401
  • PDF
Beam search for learning a deep Convolutional Neural Network of 3D shapes
  • Xu Xu, S. Todorovic
  • Computer Science
  • 2016 23rd International Conference on Pattern Recognition (ICPR)
  • 2016
  • 36
  • PDF
Spatio-Temporal Channel Correlation Networks for Action Classification
  • 80
  • Highly Influential
  • PDF
FusionNet: 3D Object Classification Using Multiple Data Representations
  • 151
  • PDF
Large-Scale Video Classification with Convolutional Neural Networks
  • 4,519
  • PDF
BV-CNNs: Binary Volumetric Convolutional Networks for 3D Object Recognition
  • 18
  • Highly Influential
  • PDF
VoxNet: A 3D Convolutional Neural Network for real-time object recognition
  • Daniel Maturana, S. Scherer
  • Computer Science
  • 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2015
  • 1,627
  • Highly Influential
  • PDF
...
1
2
3
4
5
...