# Resource Efficient 3D Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1904.02422 · HTML: https://mlsanity.com/paper/1904.02422/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 30 of 50)

- [FrameExit: Conditional Early Exiting for Efficient Video Recognition](https://mlsanity.com/paper/2104.13400/) (2021)
- [How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild](https://mlsanity.com/paper/2106.03932/) (2021)
- [Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection](https://mlsanity.com/paper/2207.07783/) (2022)
- [PrivHAR: Recognizing Human Actions From Privacy-preserving Lens](https://mlsanity.com/paper/2206.03891/) (2022)
- [Joint Audio-Visual Idling Vehicle Detection with Streamlined Input Dependencies](https://mlsanity.com/paper/2410.21170/) (2024)
- [Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories](https://mlsanity.com/paper/2104.01198/) (2021)
- [Clinically-Inspired Multi-Agent Transformers for Disease Trajectory Forecasting from Multimodal Data](https://mlsanity.com/paper/2210.13889/) (2022)
- [Continual 3D Convolutional Neural Networks for Real-time Processing of Videos](https://mlsanity.com/paper/2106.00050/) (2021)
- [Inflating 2D Convolution Weights for Efficient Generation of 3D Medical Images](https://mlsanity.com/paper/2208.03934/) (2022)
- [Transformer-based Video Saliency Prediction with High Temporal Dimension Decoding](https://mlsanity.com/paper/2401.07942/) (2024)
- [COVID Detection and Severity Prediction with 3D-ConvNeXt and Custom Pretrainings](https://mlsanity.com/paper/2206.15073/) (2022)
- [Survey: Exploiting Data Redundancy for Optimization of Deep Learning](https://mlsanity.com/paper/2208.13363/) (2022)
- [YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection](https://mlsanity.com/paper/2302.06848/) (2023)
- [PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer](https://mlsanity.com/paper/2404.14034/) (2024)
- [Real-Time Driver Monitoring Systems through Modality and View Analysis](https://mlsanity.com/paper/2210.09441/) (2022)
- [How Do Deepfakes Move? Motion Magnification for Deepfake Source Detection](https://mlsanity.com/paper/2212.14033/) (2022)
- [RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Model](https://mlsanity.com/paper/2407.06162/) (2024)
- [Predicting Knee Osteoarthritis Progression from Structural MRI using Deep Learning](https://mlsanity.com/paper/2201.10849/) (2022)
- [Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates](https://mlsanity.com/paper/2204.04674/) (2022)
- [3D Brain and Heart Volume Generative Models: A Survey](https://mlsanity.com/paper/2210.05952/) (2022)
- [Video Mobile-Former: Video Recognition with Efficient Global Spatial-temporal Modeling](https://mlsanity.com/paper/2208.12257/) (2022)
- [Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification](https://mlsanity.com/paper/2210.07983/) (2022)
- [PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations](https://mlsanity.com/paper/2401.03167/) (2024)
- [A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning](https://mlsanity.com/paper/2504.06153/) (2025)
- [PLSM: A Parallelized Liquid State Machine for Unintentional Action Detection](https://mlsanity.com/paper/2105.09909/) (2021)
- [YOWO-Plus: An Incremental Improvement](https://mlsanity.com/paper/2210.11219/) (2022)
- [SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural Networks](https://mlsanity.com/paper/2404.19668/) (2024)
- [EHWGesture -- A dataset for multimodal understanding of clinical gestures](https://mlsanity.com/paper/2509.07525/) (2025)
- [RADE-Net: Robust Attention Network for Radar-Only Object Detection in Adverse Weather](https://mlsanity.com/paper/2602.19994/) (2026)
- [Efficient Action Recognition Using Confidence Distillation](https://mlsanity.com/paper/2109.02137/) (2021)

## Abstract (arXiv)

Recently, convolutional neural networks with 3D kernels (3D CNNs) have been very popular in computer vision community as a result of their superior ability of extracting spatio-temporal features within video frames compared to 2D CNNs. Although there has been great advances recently to build resource efficient 2D CNN architectures considering memory and power budget, there is hardly any similar resource efficient architectures for 3D CNNs. In this paper, we have converted various well-known resource efficient 2D CNNs to 3D CNNs and evaluated their performance on three major benchmarks in terms of classification accuracy for different complexity levels. We have experimented on (1) Kinetics-600 dataset to inspect their capacity to learn, (2) Jester dataset to inspect their ability to capture motion patterns, and (3) UCF-101 to inspect the applicability of transfer learning. We have evaluated the run-time performance of each model on a single Titan XP GPU and a Jetson TX2 embedded system. The results of this study show that these models can be utilized for different types of real-world applications since they provide real-time performance with considerable accuracies and memory usage. Our analysis on different complexity levels shows that the resource efficient 3D CNNs should not be designed too shallow or narrow in order to save complexity. The codes and pretrained models used in this work are publicly available.