# R-CNNs for Pose Estimation and Action Detection

arXiv: https://arxiv.org/abs/1406.5212 · HTML: https://mlsanity.com/paper/1406.5212/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2014.

## Built on by (most cited first, 12 of 12)

- [Robot Utility Models: General Policies for Zero-Shot Deployment in New Environments](https://mlsanity.com/paper/2409.05865/) (2024)
- [Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2103.11351/) (2021)
- [Video-based Human Action Recognition using Deep Learning: A Review](https://mlsanity.com/paper/2208.03775/) (2022)
- [Deep Multi-Task Learning for Malware Image Classification](https://mlsanity.com/paper/2405.05906/) (2024)
- [Nuisance-Label Supervision: Robustness Improvement by Free Labels](https://mlsanity.com/paper/2110.07118/) (2021)
- [6D Pose Estimation with Combined Deep Learning and 3D Vision Techniques for a Fast and Accurate Object Grasping](https://mlsanity.com/paper/2111.06276/) (2021)
- [Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization](https://mlsanity.com/paper/2412.03179/) (2024)
- [Autonomous Navigation in Dynamic Environments: Deep Learning-Based Approach](https://mlsanity.com/paper/2102.08758/) (2021)
- [Resolving Class Imbalance for LiDAR-based Object Detector by Dynamic Weight Average and Contextual Ground Truth Sampling](https://mlsanity.com/paper/2210.03331/) (2022)
- [UV R-CNN: Stable and Efficient Dense Human Pose Estimation](https://mlsanity.com/paper/2211.02337/) (2022)
- [MultiTaskVIF: Segmentation-oriented visible and infrared image fusion via multi-task learning](https://mlsanity.com/paper/2505.06665/) (2025)
- [HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactions](https://mlsanity.com/paper/2506.19639/) (2025)

## Abstract (arXiv)

We present convolutional neural networks for the tasks of keypoint (pose) prediction and action classification of people in unconstrained images. Our approach involves training an R-CNN detector with loss functions depending on the task being tackled. We evaluate our method on the challenging PASCAL VOC dataset and compare it to previous leading approaches. Our method gives state-of-the-art results for keypoint and action prediction. Additionally, we introduce a new dataset for action detection, the task of simultaneously localizing people and classifying their actions, and present results using our approach.