TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Adaptive NMS: Refining Pedestrian Detection in a Crowd

Adaptive NMS: Refining Pedestrian Detection in a Crowd

Songtao Liu, Di Huang, Yunhong Wang

2019-04-07CVPR 2019 6Pedestrian DetectionObject Detection
PaperPDF

Abstract

Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel Non-Maximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose adaptive-NMS, which applies a dynamic suppression threshold to an instance, according to the target density; (2) we design an efficient subnetwork to learn density scores, which can be conveniently embedded into both the single-stage and two-stage detectors; and (3) we achieve state of the art results on the CityPersons and CrowdHuman benchmarks.

Results

TaskDatasetMetricValueModel
Object DetectionCrowdHuman (full body)AP84.71Adaptive NMS (Faster RCNN, ResNet50)
Object DetectionCrowdHuman (full body)mMR49.73Adaptive NMS (Faster RCNN, ResNet50)
3DCrowdHuman (full body)AP84.71Adaptive NMS (Faster RCNN, ResNet50)
3DCrowdHuman (full body)mMR49.73Adaptive NMS (Faster RCNN, ResNet50)
2D ClassificationCrowdHuman (full body)AP84.71Adaptive NMS (Faster RCNN, ResNet50)
2D ClassificationCrowdHuman (full body)mMR49.73Adaptive NMS (Faster RCNN, ResNet50)
2D Object DetectionCrowdHuman (full body)AP84.71Adaptive NMS (Faster RCNN, ResNet50)
2D Object DetectionCrowdHuman (full body)mMR49.73Adaptive NMS (Faster RCNN, ResNet50)
16kCrowdHuman (full body)AP84.71Adaptive NMS (Faster RCNN, ResNet50)
16kCrowdHuman (full body)mMR49.73Adaptive NMS (Faster RCNN, ResNet50)

Related Papers

A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains2025-07-17RS-TinyNet: Stage-wise Feature Fusion Network for Detecting Tiny Objects in Remote Sensing Images2025-07-17Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection2025-07-17Dual LiDAR-Based Traffic Movement Count Estimation at a Signalized Intersection: Deployment, Data Collection, and Preliminary Analysis2025-07-17Vision-based Perception for Autonomous Vehicles in Obstacle Avoidance Scenarios2025-07-16Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping2025-07-15ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge2025-07-08YOLO-APD: Enhancing YOLOv8 for Robust Pedestrian Detection on Complex Road Geometries2025-07-07