computer-vision

Head Detection

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in head-detection

Trend

Dataset

Best Model

Actions

Rebar Head

Libraries

i

Use these libraries to find head-detection models and implementations

Datasets

MinneApple

SCUT-HEAD

Subtasks

No subtasks available.

Most implemented papers

FCHD: Fast and accurate head detection in crowded scenes

Aditya Vora, Vinay Chilaka•Sun Sep 23 2018

This paper proposes FCHD-Fully Convolutional Head Detector, an end-to-end trainable head detection model which is lightweight with low inference time and memory requirements, and has better overall average precision.

30

Content

0

Paper Graph

Context-Aware CNNs for Person Head Detection

Tuan-Hung Vu, I. Laptev, A. Osokin•Mon Nov 23 2015

This work leverage person-scene relations and propose a global CNN model trained to predict positions and scales of heads directly from the full image via energy-based model where the potentials are computed with a CNN framework.

142 0

Paper Graph

Relational Learning for Joint Head and Human Detection

Zhen Lei, S. Li, Junliang Xing, Shifeng Zhang, Xudong Zou, Cheng Chi•Mon Sep 23 2019

This work designs a head-body relationship discriminating module to perform relational learning between heads and human bodies, and leverage this learned relationship to regain the suppressed human detections and reduce head false positives.

59 0

Paper Graph

Weakly supervised one-stage vision and language disease detection using large scale pneumonia and pneumothorax studies

Daguang Xu, Xiaosong Wang, Leo K. Tam, E. Turkbey, Kevin Lu, Yuhong Wen•Thu Jul 30 2020

A challenging new set of radiologist paired bounding box and natural language annotations on the publicly available MIMIC-CXR dataset especially focussed on pneumonia and pneumothorax is presented.

15 0

Paper Graph

Tracking Pedestrian Heads in Dense Crowd

J. Pettré, Ramanathan Sundararaman, Cédric Braga, É. Marchand•Tue Mar 23 2021

A new metric, IDEucl, is proposed, to measure an algorithm’s efficacy in preserving a unique identity for the longest stretch in image coordinate space, thus building a correspondence between pedestrian crowd motion and the performance of a tracking algorithm.

94 0

Paper Graph

Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection

Taojiannan Yang, Chen Chen, Weiping Yu•Fri Nov 06 2020

The Dual Sampler and Head detection Network (DSHNet) is proposed, which is the first work that aims to resolve long-tail distribution in UAV images and achieves new state-of-the-art performance when combining with image cropping methods.

108 0

Paper Graph

RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices

Mengyuan Liu, Chen Chen, Xiandong Meng, Wanpeng Xiao, Qi Ju•Tue Nov 19 2019

A lightweight residual-like backbone with large receptive fields and wide dimensions for low-level features, which are crucial for detection tasks is proposed, and a light-head detection part is designed to match the backbone capability.

24 0

Paper Graph

DPDnet: A robust people detector using deep learning with an overhead depth camera

D. Fuentes-Jiménez, Roberto Martín-López, Cristina Losada-Gutiérrez, D. Casillas-Pérez, Javier Macias-Guarasa, C. Vázquez, Daniel Pizarro-Perez•Thu Apr 30 2020

DPDnet proves to outperform all the evaluated methods with statistically significant differences, and with accuracies that exceed 99%, proving also to achieve high accuracy with varying datasets and experimental conditions.

21 0

Paper Graph

Towards in-store multi-person tracking using head detection and track heatmaps

De Wang, Cheng Li, A. Musaev, Jiangping Wang, Liang Zhu, Yi Chen, Jialin Liu, Wanqi Zhang, Juan Mei•Fri May 15 2020

A dataset collected from a camera in an office environment where participants mimic various behaviors of customers in a supermarket is introduced and a model for recognizing customers and staff based on their movement patterns is proposed.

0 0

Paper Graph

Adding a benchmark result helps the community track progress.