Skip to content

3D Convolutional Neural Networks for Human Action Recognition

Shuiwang Ji, Wei Xu, Ming Yang, Kai Yu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2012 · 6,330 citations

No retraction on record in OpenAlex.Check Crossref now

Cite this paper

Ji, S., Xu, W., Yang, M., & Yu, K. (2012). 3D convolutional neural networks for human action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1), 221–231. https://doi.org/10.1109/tpami.2012.59

In text: (Ji et al., 2012)

Ask a question about this research

One question, free, no account. Anchorcite finds the papers, checks each against Crossref and links every sentence of the answer to the passage it comes from.

Abstract

We consider the automated recognition of human actions in surveillance videos. Most current methods build classifiers based on complex handcrafted features computed from the raw inputs. Convolutional neural networks (CNNs) are a type of deep model that can act directly on the raw inputs. However, such models are currently limited to handling 2D inputs. In this paper, we develop a novel 3D CNN model for action recognition. This model extracts features from both the spatial and the temporal dimensions by performing 3D convolutions, thereby capturing the motion information encoded in multiple adjacent frames. The developed model generates multiple channels of information from the input frames, and the final feature representation combines information from all channels. To further boost the performance, we propose regularizing the outputs with high-level features and combining the predictions of a variety of different models. We apply the developed models to recognize human actions in the real-world environment of airport surveillance videos, and they achieve superior performance in comparison to baseline methods.

  1. Densely Connected Convolutional Networks2017
  2. Mask R-CNN2017
  3. Non-local Neural Networks2018
  4. OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields2019
  5. Deep High-Resolution Representation Learning for Visual Recognition2020

Metadata from OpenAlex (CC0). Citations are generated from the published record.