# Improving Detection of Person Class Using Dense Pooling

arXiv: https://arxiv.org/abs/2410.20966 · HTML: https://mlsanity.com/paper/2410.20966/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 28 Oct 2024.

## Builds on (most cited first, 28 of 28)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [Object Detection in 20 Years: A Survey](https://mlsanity.com/paper/1905.05055/) (2019)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks](https://mlsanity.com/paper/1312.6229/) (2013)
- [Imbalance Problems in Object Detection: A Review](https://mlsanity.com/paper/1909.00169/) (2019)
- [IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval](https://mlsanity.com/paper/2003.03772/) (2020)
- [A Survey of Modern Deep Learning based Object Detection Models](https://mlsanity.com/paper/2104.11892/) (2021)
- [Continuous Surface Embeddings](https://mlsanity.com/paper/2011.12438/) (2020)
- [Learning to Segment Object Candidates](https://mlsanity.com/paper/1506.06204/) (2015)
- [A comprehensive review of Binary Neural Network](https://mlsanity.com/paper/2110.06804/) (2021)
- [Convolutional Feature Masking for Joint Object and Stuff Segmentation](https://mlsanity.com/paper/1412.1283/) (2014)
- [What makes for effective detection proposals?](https://mlsanity.com/paper/1502.05082/) (2015)
- [Scalable Object Detection using Deep Neural Networks](https://mlsanity.com/paper/1312.2249/) (2013)
- [Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding](https://mlsanity.com/paper/2206.03484/) (2022)
- [Discovering Relationships between Object Categories via Universal Canonical Maps](https://mlsanity.com/paper/2106.09758/) (2021)
- [Scalable, High-Quality Object Detection](https://mlsanity.com/paper/1412.1441/) (2014)
- [BodyMap: Learning Full-Body Dense Correspondence Map](https://mlsanity.com/paper/2205.09111/) (2022)
- [Object-Proposal Evaluation Protocol is 'Gameable'](https://mlsanity.com/paper/1505.05836/) (2015)
- [How good are detection proposals, really?](https://mlsanity.com/paper/1406.6962/) (2014)

## Abstract (arXiv)

Lately, the continuous development of deep learning models by many researchers in the area of computer vision has attracted more researchers to further improve the accuracy of these models. FasterRCNN [32] has already provided a state-of-the-art approach to improve the accuracy and detection of 80 different objects given in the COCO dataset. To further improve the performance of person detection we have conducted a different approach which gives the state-of-the-art conclusion. An ROI is a step in FasterRCNN that extract the features from the given image with a fixed size and transfer into for further classification. To enhance the ROI performance, we have conducted an approach that implements dense pooling and converts the image into a 3D model to further transform into UV(ultra Violet) images which makes it easy to extract the right features from the images. To implement our approach we have approached the state-of-the-art COCO datasets and extracted 6982 images that include a person object and our final achievements conclude that using our approach has made significant results in detecting the person object in the given image