# Optimization Planning for 3D ConvNets

arXiv: https://arxiv.org/abs/2201.04021 · HTML: https://mlsanity.com/paper/2201.04021/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 56 references that are in the map.
- First posted on arXiv 11 Jan 2022.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [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)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [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)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification](https://mlsanity.com/paper/1712.04851/) (2017)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [Convolutional Two-Stream Network Fusion for Video Action Recognition](https://mlsanity.com/paper/1604.06573/) (2016)
- [A Short Note about Kinetics-600](https://mlsanity.com/paper/1808.01340/) (2018)
- [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://mlsanity.com/paper/1904.11492/) (2019)
- [Video Classification with Channel-Separated Convolutional Networks](https://mlsanity.com/paper/1904.02811/) (2019)
- [Temporal Segment Networks for Action Recognition in Videos](https://mlsanity.com/paper/1705.02953/) (2017)
- [Videos as Space-Time Region Graphs](https://mlsanity.com/paper/1806.01810/) (2018)
- [TEA: Temporal Excitation and Aggregation for Action Recognition](https://mlsanity.com/paper/2004.01398/) (2020)
- [STM: SpatioTemporal and Motion Encoding for Action Recognition](https://mlsanity.com/paper/1908.02486/) (2019)
- [Gaussian Temporal Awareness Networks for Action Localization](https://mlsanity.com/paper/1909.03877/) (2019)
- [Long-term Temporal Convolutions for Action Recognition](https://mlsanity.com/paper/1604.04494/) (2016)
- [The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares](https://mlsanity.com/paper/1904.12838/) (2019)
- [Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition](https://mlsanity.com/paper/1907.13369/) (2019)
- [More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation](https://mlsanity.com/paper/1912.00869/) (2019)
- [Appearance-and-Relation Networks for Video Classification](https://mlsanity.com/paper/1711.09125/) (2017)
- [Learning Spatio-Temporal Representation with Local and Global Diffusion](https://mlsanity.com/paper/1906.05571/) (2019)
- [Grouped Spatial-Temporal Aggregation for Efficient Action Recognition](https://mlsanity.com/paper/1909.13130/) (2019)
- [A Multigrid Method for Efficiently Training Video Models](https://mlsanity.com/paper/1912.00998/) (2019)

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

- [Stand-Alone Inter-Frame Attention in Video Models](https://mlsanity.com/paper/2206.06931/) (2022)
- [MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing](https://mlsanity.com/paper/2206.06292/) (2022)
- [Dynamic Temporal Filtering in Video Models](https://mlsanity.com/paper/2211.08252/) (2022)
- [RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts](https://mlsanity.com/paper/2212.04005/) (2022)
- [Selective Volume Mixup for Video Action Recognition](https://mlsanity.com/paper/2309.09534/) (2023)

## Abstract (arXiv)

It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. The most common hand-tuning process starts from learning 3D ConvNets using short video clips and then is followed by learning long-term temporal dependency using lengthy clips, while gradually decaying the learning rate from high to low as training progresses. The fact that such process comes along with several heuristic settings motivates the study to seek an optimal "path" to automate the entire training. In this paper, we decompose the path into a series of training "states" and specify the hyper-parameters, e.g., learning rate and the length of input clips, in each state. The estimation of the knee point on the performance-epoch curve triggers the transition from one state to another. We perform dynamic programming over all the candidate states to plan the optimal permutation of states, i.e., optimization path. Furthermore, we devise a new 3D ConvNets with a unique design of dual-head classifier to improve spatial and temporal discrimination. Extensive experiments on seven public video recognition benchmarks demonstrate the advantages of our proposal. With the optimization planning, our 3D ConvNets achieves superior results when comparing to the state-of-the-art recognition methods. More remarkably, we obtain the top-1 accuracy of 80.5% and 82.7% on Kinetics-400 and Kinetics-600 datasets, respectively. Source code is available at https://github.com/ZhaofanQiu/Optimization-Planning-for-3D-ConvNets.