Corpus ID: 19192906

Action Prediction From Videos via Memorizing Hard-to-Predict Samples

@inproceedings{Kong2018ActionPF,
  title={Action Prediction From Videos via Memorizing Hard-to-Predict Samples},
  author={Yu Kong and Shangqian Gao and B. Sun and Y. Fu},
  booktitle={AAAI},
  year={2018}
}
Action prediction based on video is an important problem in computer vision field with many applications, such as preventing accidents and criminal activities. [...] Key Method Our method uses Convolution Neural Network (CNN) and Long Short-Term Memory (LSTM) to model partial observed video input. We augment LSTM with a memory module to remember challenging video instances.Expand
Early Action Prediction by Soft Regression
Action prediction via deep residual feature learning and weighted loss
Anticipating Future Relations via Graph Growing for Action Prediction
  • Xinxiao Wu, Jianwei Zhao, Ruiqi Wang
  • Computer Science
  • AAAI
  • 2021
Forecasting Future Sequence of Actions to Complete an Activity
CoReHAR: A Hybrid Deep Network for Video Action Recognition
Deep Residual Feature Learning for Action Prediction
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 28 REFERENCES
Deep Sequential Context Networks for Action Prediction
Max-Margin Action Prediction Machine
  • Yu Kong, Y. Fu
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2016
A Discriminative Model with Multiple Temporal Scales for Action Prediction
Unsupervised Learning of Video Representations using LSTMs
Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification
Two-Stream Convolutional Networks for Action Recognition in Videos
Learning to Remember Rare Events
Human activity prediction: Early recognition of ongoing activities from streaming videos
  • M. Ryoo
  • Computer Science
  • 2011 International Conference on Computer Vision
  • 2011
Recognize Human Activities from Partially Observed Videos
...
1
2
3
...