# Action Machine: Rethinking Action Recognition in Trimmed Videos

arXiv: https://arxiv.org/abs/1812.05770 · HTML: https://mlsanity.com/paper/1812.05770/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2018.

## Built on by (most cited first, 9 of 9)

- [STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition](https://mlsanity.com/paper/2210.07503/) (2022)
- [Cross-Modal Learning with 3D Deformable Attention for Action Recognition](https://mlsanity.com/paper/2212.05638/) (2022)
- [Pose is all you need: The pose only group activity recognition system (POGARS)](https://mlsanity.com/paper/2108.04186/) (2021)
- [Skeleton-based Action Recognition via Temporal-Channel Aggregation](https://mlsanity.com/paper/2205.15936/) (2022)
- [From CNNs to Transformers in Multimodal Human Action Recognition: A Survey](https://mlsanity.com/paper/2405.15813/) (2024)
- [Deep video representation learning: a survey](https://mlsanity.com/paper/2405.06574/) (2024)
- [Transformers in Action Recognition: A Review on Temporal Modeling](https://mlsanity.com/paper/2302.01921/) (2022)
- [A Novel Two Stream Decision Level Fusion of Vision and Inertial Sensors Data for Automatic Multimodal Human Activity Recognition System](https://mlsanity.com/paper/2306.15765/) (2023)
- [LS-HAR: Language Supervised Human Action Recognition with Salient Fusion, Construction Sites as a Use-Case](https://mlsanity.com/paper/2410.01962/) (2024)

## Abstract (arXiv)

Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a conceptually simple, general and high-performance framework for action recognition in trimmed videos, aiming at person-centric modeling. The method, called Action Machine, takes as inputs the videos cropped by person bounding boxes. It extends the Inflated 3D ConvNet (I3D) by adding a branch for human pose estimation and a 2D CNN for pose-based action recognition, being fast to train and test. Action Machine can benefit from the multi-task training of action recognition and pose estimation, the fusion of predictions from RGB images and poses. On NTU RGB-D, Action Machine achieves the state-of-the-art performance with top-1 accuracies of 97.2% and 94.3% on cross-view and cross-subject respectively. Action Machine also achieves competitive performance on another three smaller action recognition datasets: Northwestern UCLA Multiview Action3D, MSR Daily Activity3D and UTD-MHAD. Code will be made available.