# Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification

arXiv: https://arxiv.org/abs/1608.08851 · HTML: https://mlsanity.com/paper/1608.08851/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2016.

## Built on by (most cited first, 5 of 5)

- [CNN-Based Action Recognition and Pose Estimation for Classifying Animal Behavior from Videos: A Survey](https://mlsanity.com/paper/2301.06187/) (2023)
- [DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition](https://mlsanity.com/paper/2212.03384/) (2022)
- [Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition](https://mlsanity.com/paper/2306.13783/) (2023)
- [TransNet: A Transfer Learning-Based Network for Human Action Recognition](https://mlsanity.com/paper/2309.06951/) (2023)
- [Texture-Based Input Feature Selection for Action Recognition](https://mlsanity.com/paper/2303.00138/) (2023)

## Abstract (arXiv)

The video and action classification have extremely evolved by deep neural networks specially with two stream CNN using RGB and optical flow as inputs and they present outstanding performance in terms of video analysis. One of the shortcoming of these methods is handling motion information extraction which is done out side of the CNNs and relatively time consuming also on GPUs. So proposing end-to-end methods which are exploring to learn motion representation, like 3D-CNN can achieve faster and accurate performance. We present some novel deep CNNs using 3D architecture to model actions and motion representation in an efficient way to be accurate and also as fast as real-time. Our new networks learn distinctive models to combine deep motion features into appearance model via learning optical flow features inside the network.