# Efficient Action Recognition Using Confidence Distillation

arXiv: https://arxiv.org/abs/2109.02137 · HTML: https://mlsanity.com/paper/2109.02137/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 70 references that are in the map.
- First posted on arXiv 5 Sep 2021.

## Builds on (most cited first, 30 of 53)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Born Again Neural Networks](https://mlsanity.com/paper/1805.04770/) (2018)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [A Short Note about Kinetics-600](https://mlsanity.com/paper/1808.01340/) (2018)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [A Short Note on the Kinetics-700 Human Action Dataset](https://mlsanity.com/paper/1907.06987/) (2019)
- [Video Classification with Channel-Separated Convolutional Networks](https://mlsanity.com/paper/1904.02811/) (2019)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)

## Built on by (most cited first, 1 of 1)

- [Context-LSTM: a robust classifier for video detection on UCF101](https://mlsanity.com/paper/2203.06610/) (2022)

## Abstract (arXiv)

Modern neural networks are powerful predictive models. However, when it comes to recognizing that they may be wrong about their predictions, they perform poorly. For example, for one of the most common activation functions, the ReLU and its variants, even a well-calibrated model can produce incorrect but high confidence predictions. In the related task of action recognition, most current classification methods are based on clip-level classifiers that densely sample a given video for non-overlapping, same-sized clips and aggregate the results using an aggregation function - typically averaging - to achieve video level predictions. While this approach has shown to be effective, it is sub-optimal in recognition accuracy and has a high computational overhead. To mitigate both these issues, we propose the confidence distillation framework to teach a representation of uncertainty of the teacher to the student sampler and divide the task of full video prediction between the student and the teacher models. We conduct extensive experiments on three action recognition datasets and demonstrate that our framework achieves significant improvements in action recognition accuracy (up to 20%) and computational efficiency (more than 40%).