# TransNet: A Transfer Learning-Based Network for Human Action Recognition

arXiv: https://arxiv.org/abs/2309.06951 · HTML: https://mlsanity.com/paper/2309.06951/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 84 references that are in the map.
- First posted on arXiv 13 Sep 2023.

## Builds on (most cited first, 30 of 31)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [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)
- [Human Action Recognition and Prediction: A Survey](https://mlsanity.com/paper/1806.11230/) (2018)
- [TDN: Temporal Difference Networks for Efficient Action Recognition](https://mlsanity.com/paper/2012.10071/) (2020)
- [TEA: Temporal Excitation and Aggregation for Action Recognition](https://mlsanity.com/paper/2004.01398/) (2020)
- [Human Action Recognition from Various Data Modalities: A Review](https://mlsanity.com/paper/2012.11866/) (2020)
- [A Comprehensive Study of Deep Video Action Recognition](https://mlsanity.com/paper/2012.06567/) (2020)
- [Exploring Sparsity in Recurrent Neural Networks](https://mlsanity.com/paper/1704.05119/) (2017)
- [MotionSqueeze: Neural Motion Feature Learning for Video Understanding](https://mlsanity.com/paper/2007.09933/) (2020)
- [Video Prediction Recalling Long-term Motion Context via Memory Alignment Learning](https://mlsanity.com/paper/2104.00924/) (2021)
- [In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations](https://mlsanity.com/paper/1904.03289/) (2019)
- [AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures](https://mlsanity.com/paper/1905.13209/) (2019)
- [Differential Recurrent Neural Networks for Action Recognition](https://mlsanity.com/paper/1504.06678/) (2015)
- [Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection](https://mlsanity.com/paper/1704.00616/) (2017)
- [A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images](https://mlsanity.com/paper/1912.10230/) (2019)
- [Learning for Video Super-Resolution through HR Optical Flow Estimation](https://mlsanity.com/paper/1809.08573/) (2018)
- [View-invariant Deep Architecture for Human Action Recognition using late fusion](https://mlsanity.com/paper/1912.03632/) (2019)
- [An Efficient 3D CNN for Action/Object Segmentation in Video](https://mlsanity.com/paper/1907.08895/) (2019)
- [Morph: Flexible Acceleration for 3D CNN-based Video Understanding](https://mlsanity.com/paper/1810.06807/) (2018)
- [A unified model for continuous conditional video prediction](https://mlsanity.com/paper/2210.05810/) (2022)
- [Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification](https://mlsanity.com/paper/1608.08851/) (2016)
- [Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis](https://mlsanity.com/paper/2109.14306/) (2021)
- [High Speed Human Action Recognition using a Photonic Reservoir Computer](https://mlsanity.com/paper/2305.15283/) (2023)
- [An Information-rich Sampling Technique over Spatio-Temporal CNN for Classification of Human Actions in Videos](https://mlsanity.com/paper/2002.02100/) (2020)
- [Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition](https://mlsanity.com/paper/2204.07270/) (2022)

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

- [RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model](https://mlsanity.com/paper/2407.06162/) (2024)

## Abstract (arXiv)

Human action recognition (HAR) is a high-level and significant research area in computer vision due to its ubiquitous applications. The main limitations of the current HAR models are their complex structures and lengthy training time. In this paper, we propose a simple yet versatile and effective end-to-end deep learning architecture, coined as TransNet, for HAR. TransNet decomposes the complex 3D-CNNs into 2D- and 1D-CNNs, where the 2D- and 1D-CNN components extract spatial features and temporal patterns in videos, respectively. Benefiting from its concise architecture, TransNet is ideally compatible with any pretrained state-of-the-art 2D-CNN models in other fields, being transferred to serve the HAR task. In other words, it naturally leverages the power and success of transfer learning for HAR, bringing huge advantages in terms of efficiency and effectiveness. Extensive experimental results and the comparison with the state-of-the-art models demonstrate the superior performance of the proposed TransNet in HAR in terms of flexibility, model complexity, training speed and classification accuracy.