Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos

@article{Hou2017TubeCN,
  title={Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos},
  author={Rui Hou and C. Chen and M. Shah},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={5823-5832}
}
  • Rui Hou, C. Chen, M. Shah
  • Published 2017
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
Deep learning has been demonstrated to achieve excellent results for image classification and object detection. However, the impact of deep learning on video analysis has been limited due to complexity of video data and lack of annotations. Previous convolutional neural networks (CNN) based video action detection approaches usually consist of two major steps: frame-level action proposal generation and association of proposals across frames. Also, most of these methods employ two-stream CNN… Expand
185 Citations
An End-to-end 3D Convolutional Neural Network for Action Detection and Segmentation in Videos
  • 35
  • PDF
An Efficient 3D CNN for Action/Object Segmentation in Video
  • 5
  • PDF
VideoCapsuleNet: A Simplified Network for Action Detection
  • 81
  • PDF
Event Recognition Based on 3D Convolutional Networks
  • Rong Chen, Yuanlong Yu, Z. Huang
  • Computer Science
  • 2018 IEEE 8th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER)
  • 2018
Multi-Stream Single Shot Spatial-Temporal Action Detection
  • 1
  • PDF
A study on deep learning spatiotemporal models and feature extraction techniques for video understanding
  • 1
  • Highly Influenced
Trajectory-aware three-stream CNN for video action recognition
  • 3
Asymmetric 3D Convolutional Neural Networks for action recognition
  • 63
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 34 REFERENCES
Two-Stream Convolutional Networks for Action Recognition in Videos
  • 4,481
  • PDF
Beyond short snippets: Deep networks for video classification
  • 1,673
  • PDF
Multi-region Two-Stream R-CNN for Action Detection
  • 261
  • PDF
Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks
  • 378
  • PDF
Large-Scale Video Classification with Convolutional Neural Networks
  • 4,446
  • PDF
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
  • 22,574
  • PDF
3D Convolutional Neural Networks for Human Action Recognition
  • 3,513
  • PDF
Actionness Estimation Using Hybrid Fully Convolutional Networks
  • 73
  • PDF
Learning Spatiotemporal Features with 3D Convolutional Networks
  • 4,014
  • Highly Influential
  • PDF
Fast R-CNN
  • Ross B. Girshick
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
  • 10,482
  • PDF
...
1
2
3
4
...