A Discriminative Model with Multiple Temporal Scales for Action Prediction

@inproceedings{Kong2014ADM,
  title={A Discriminative Model with Multiple Temporal Scales for Action Prediction},
  author={Yu Kong and Dmitry Kit and Yun Fu},
  booktitle={ECCV},
  year={2014}
}
The speed with which intelligent systems can react to an action depends on how soon it can be recognized. [...] Key Method The proposed model captures temporal dynamics of human actions by explicitly considering all the history of observed features as well as features in smaller temporal segments. We develop a new learning formulation, which elegantly captures the temporal evolution over time, and enforces the label consistency between segments and corresponding partial videos. Experimental results on two…Expand
117 Citations
Max-Margin Action Prediction Machine
  • Yu Kong, Yun Fu
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2016
  • 65
  • PDF
Deep Sequential Context Networks for Action Prediction
  • 83
  • PDF
A Novel Double-Layer Framework for Action Prediction
  • PDF
Anticipating Future Relations via Graph Growing for Action Prediction
  • Xinxiao Wu, Jianwei Zhao, Ruiqi Wang
  • 2021
  • PDF
Adversarial Action Prediction Networks
  • 17
  • PDF
Action Prediction From Videos via Memorizing Hard-to-Predict Samples
  • 43
  • PDF
Human Action Recognition and Prediction: A Survey
  • 2
  • Highly Influenced
  • PDF
Human Action Recognition and Prediction: A Survey
  • 107
  • PDF
Skeleton-Based Online Action Prediction Using Scale Selection Network
  • 48
  • PDF
Early Action Prediction by Soft Regression
  • 40
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 30 REFERENCES
Recognize Human Activities from Partially Observed Videos
  • 160
  • Highly Influential
  • PDF
Substructure and boundary modeling for continuous action recognition
  • 32
  • PDF
Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models
  • 136
  • PDF
Poselet Key-Framing: A Model for Human Activity Recognition
  • 203
  • Highly Influential
  • PDF
Human activity prediction: Early recognition of ongoing activities from streaming videos
  • M. Ryoo
  • Computer Science
  • 2011 International Conference on Computer Vision
  • 2011
  • 459
  • Highly Influential
  • PDF
Learning latent temporal structure for complex event detection
  • 369
  • PDF
Real-time Action Recognition by Spatiotemporal Semantic and Structural Forests
  • 139
  • PDF
Modeling Complex Temporal Composition of Actionlets for Activity Prediction
  • 64
  • PDF
Tracklet Descriptors for Action Modeling and Video Analysis
  • 156
  • PDF
...
1
2
3
...