# Learning Spatiotemporal Features with 3D Convolutional Networks

arXiv: https://arxiv.org/abs/1412.0767 · HTML: https://mlsanity.com/paper/1412.0767/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2014.

## Built on by (most cited first, 30 of 43)

- [WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection](https://mlsanity.com/paper/2101.01456/) (2021)
- [BEVT: BERT Pretraining of Video Transformers](https://mlsanity.com/paper/2112.01529/) (2021)
- [TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?](https://mlsanity.com/paper/2106.11297/) (2021)
- [Vision-Language Pre-training: Basics, Recent Advances, and Future Trends](https://mlsanity.com/paper/2210.09263/) (2022)
- [Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning](https://mlsanity.com/paper/2212.04500/) (2022)
- [Spatiotemporal Inconsistency Learning for DeepFake Video Detection](https://mlsanity.com/paper/2109.01860/) (2021)
- [Progressive Temporal Feature Alignment Network for Video Inpainting](https://mlsanity.com/paper/2104.03507/) (2021)
- [Coarse-Fine Networks for Temporal Activity Detection in Videos](https://mlsanity.com/paper/2103.01302/) (2021)
- [DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection](https://mlsanity.com/paper/2306.00863/) (2023)
- [No frame left behind: Full Video Action Recognition](https://mlsanity.com/paper/2103.15395/) (2021)
- [RAG-based Explainable Prediction of Road Users Behaviors for Automated Driving using Knowledge Graphs and Large Language Models](https://mlsanity.com/paper/2405.00449/) (2024)
- [Video Moment Retrieval from Text Queries via Single Frame Annotation](https://mlsanity.com/paper/2204.09409/) (2022)
- [Recognizing Actions in Videos from Unseen Viewpoints](https://mlsanity.com/paper/2103.16516/) (2021)
- [Video Question Answering with Iterative Video-Text Co-Tokenization](https://mlsanity.com/paper/2208.00934/) (2022)
- [Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition](https://mlsanity.com/paper/2110.14994/) (2021)
- [Temporal Perceiving Video-Language Pre-training](https://mlsanity.com/paper/2301.07463/) (2023)
- [Behavioral Research and Practical Models of Drivers' Attention](https://mlsanity.com/paper/2104.05677/) (2021)
- [Towards cumulative race time regression in sports: I3D ConvNet transfer learning in ultra-distance running events](https://mlsanity.com/paper/2208.11191/) (2022)
- [RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection](https://mlsanity.com/paper/2307.10642/) (2023)
- [Anomaly detection in surveillance videos using transformer based attention model](https://mlsanity.com/paper/2206.01524/) (2022)
- [Adaptive Intermediate Representations for Video Understanding](https://mlsanity.com/paper/2104.07135/) (2021)
- [Video Mobile-Former: Video Recognition with Efficient Global Spatial-temporal Modeling](https://mlsanity.com/paper/2208.12257/) (2022)
- [Leveraging Self-Supervised Training for Unintentional Action Recognition](https://mlsanity.com/paper/2209.11870/) (2022)
- [GazeForensics: DeepFake Detection via Gaze-guided Spatial Inconsistency Learning](https://mlsanity.com/paper/2311.07075/) (2023)
- [HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition](https://mlsanity.com/paper/2104.09760/) (2021)
- [When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs](https://mlsanity.com/paper/2202.08138/) (2022)
- [Exploiting long-term temporal dynamics for video captioning](https://mlsanity.com/paper/2202.10828/) (2022)
- [Human Pose Driven Object Effects Recommendation](https://mlsanity.com/paper/2209.08353/) (2022)
- [Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding](https://mlsanity.com/paper/2303.16341/) (2023)
- [An X3D Neural Network Analysis for Runner's Performance Assessment in a Wild Sporting Environment](https://mlsanity.com/paper/2307.12183/) (2023)

## Abstract (arXiv)

We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold: 1) 3D ConvNets are more suitable for spatiotemporal feature learning compared to 2D ConvNets; 2) A homogeneous architecture with small 3x3x3 convolution kernels in all layers is among the best performing architectures for 3D ConvNets; and 3) Our learned features, namely C3D (Convolutional 3D), with a simple linear classifier outperform state-of-the-art methods on 4 different benchmarks and are comparable with current best methods on the other 2 benchmarks. In addition, the features are compact: achieving 52.8% accuracy on UCF101 dataset with only 10 dimensions and also very efficient to compute due to the fast inference of ConvNets. Finally, they are conceptually very simple and easy to train and use.