# Ten Years of Pedestrian Detection, What Have We Learned?

arXiv: https://arxiv.org/abs/1411.4304 · HTML: https://mlsanity.com/paper/1411.4304/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2014.

## Built on by (most cited first, 13 of 13)

- [4D-Net for Learned Multi-Modal Alignment](https://mlsanity.com/paper/2109.01066/) (2021)
- [Cross-Modality Proposal-guided Feature Mining for Unregistered RGB-Thermal Pedestrian Detection](https://mlsanity.com/paper/2308.12111/) (2023)
- [A Culturally-Aware Benchmark for Person Re-Identification in Modest Attire](https://mlsanity.com/paper/2412.18874/) (2024)
- [Diagnosing Errors in Video Relation Detectors](https://mlsanity.com/paper/2110.13110/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Toward Smart Doors: A Position Paper](https://mlsanity.com/paper/2209.11770/) (2022)
- [Deep Learning Techniques for Visual Counting](https://mlsanity.com/paper/2206.03033/) (2022)
- [Crowd counting with segmentation attention convolutional neural network](https://mlsanity.com/paper/2204.07380/) (2022)
- [Automated Sizing and Training of Efficient Deep Autoencoders using Second Order Algorithms](https://mlsanity.com/paper/2308.06221/) (2023)
- [A PST Algorithm for FPs Suppression in Two-stage CNN Detection Methods](https://mlsanity.com/paper/2406.18553/) (2024)
- [Real-Time Pedestrian Detection on IoT Edge Devices: A Lightweight Deep Learning Approach](https://mlsanity.com/paper/2409.15740/) (2024)
- [Automatic Labelling for Low-Light Pedestrian Detection](https://mlsanity.com/paper/2507.02513/) (2025)
- [One-Shot Crowd Counting With Density Guidance For Scene Adaptation](https://mlsanity.com/paper/2602.07955/) (2026)

## Abstract (arXiv)

Paper-by-paper results make it easy to miss the forest for the trees.We analyse the remarkable progress of the last decade by discussing the main ideas explored in the 40+ detectors currently present in the Caltech pedestrian detection benchmark. We observe that there exist three families of approaches, all currently reaching similar detection quality. Based on our analysis, we study the complementarity of the most promising ideas by combining multiple published strategies. This new decision forest detector achieves the current best known performance on the challenging Caltech-USA dataset.