# CA3D: Convolutional-Attentional 3D Nets for Efficient Video Activity Recognition on the Edge

arXiv: https://arxiv.org/abs/2505.19928 · HTML: https://mlsanity.com/paper/2505.19928/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 50 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [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)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [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)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification](https://mlsanity.com/paper/1712.04851/) (2017)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks](https://mlsanity.com/paper/1807.10029/) (2018)
- [Low-bit Quantization of Neural Networks for Efficient Inference](https://mlsanity.com/paper/1902.06822/) (2019)
- [UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning](https://mlsanity.com/paper/2201.04676/) (2022)
- [Vision Transformer for Small-Size Datasets](https://mlsanity.com/paper/2112.13492/) (2021)
- [UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer](https://mlsanity.com/paper/2211.09552/) (2022)
- [VidTr: Video Transformer Without Convolutions](https://mlsanity.com/paper/2104.11746/) (2021)
- [An Image is Worth 16x16 Words, What is a Video Worth?](https://mlsanity.com/paper/2103.13915/) (2021)

## Abstract (arXiv)

In this paper, we introduce a deep learning solution for video activity recognition that leverages an innovative combination of convolutional layers with a linear-complexity attention mechanism. Moreover, we introduce a novel quantization mechanism to further improve the efficiency of our model during both training and inference. Our model maintains a reduced computational cost, while preserving robust learning and generalization capabilities. Our approach addresses the issues related to the high computing requirements of current models, with the goal of achieving competitive accuracy on consumer and edge devices, enabling smart home and smart healthcare applications where efficiency and privacy issues are of concern. We experimentally validate our model on different established and publicly available video activity recognition benchmarks, improving accuracy over alternative models at a competitive computing cost.