Fast Video Classification via Adaptive Cascading of Deep Models

@article{Shen2017FastVC,
  title={Fast Video Classification via Adaptive Cascading of Deep Models},
  author={Haichen Shen and Seungyeop Han and Matthai Philipose and Arvind Krishnamurthy},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2017},
  pages={2197-2205}
}
Recent advances have enabled oracle classifiers that can classify across many classes and input distributions with high accuracy without retraining. However, these classifiers are relatively heavyweight, so that applying them to classify video is costly. We show that day-to-day video exhibits highly skewed class distributions over the short term, and that these distributions can be classified by much simpler models. We formulate the problem of detecting the short-term skews online and… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 14 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 13 extracted citations

Pcnn: Environment Adaptive Model without Finetuning

2018
View 5 Excerpts
Highly Influenced

References

Publications referenced by this paper.
Showing 1-10 of 32 references

Deep Face Recognition

View 7 Excerpts
Highly Influenced

Im - agenet classification with deep convolutional neural networks

I. Sutskever A. Krizhevsky, G. E. Hinton.
Proceedings of the Twenty - sixth Annual Conference on Neural Information Processing Systems ( NIPS ) • 2016

A convolutional neural network cascade for face detection

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 1 Excerpt

Going deeper with convolutions

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 3 Excerpts

Long-Term Recurrent Convolutional Networks for Visual Recognition and Description

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2015
View 1 Excerpt

Similar Papers

Loading similar papers…