Article

SimpleCID: Skeleton-Guided Lightweight Heatmap Refinement for Robust Multi-Person Pose Estimation in Crowded Scenes

2026-04-01

Abstract excerpt

<title>Abstract</title> <p>Multi-person pose estimation in crowded scenes remains difficult because heavy overlap and occlusion frequently break independently predicted keypoint heatmaps. Contextual Instance Decoupling (CID) improves crowded-scene estimation by generating instance-aware feature maps, yet its final joint heatmaps are still produced channel by channel without explicit structural coupling. This pape...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 773ec915-7d25-55a7-9623-ac27c2616efa
DOI: 10.21203/rs.3.rs-9225509/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

SimpleCID: Skeleton-Guided Lightweight Heatmap Refinement for Robust Multi-Person Pose Estimation in Crowded ScenesDOI 10.21203/rs.3.rs-9225509/v1Read

Boosting Human Pose Estimation via Heatmap RefinementSemantic proximity Read

Lightweight Context-aware Feature Transformer Network for Human Pose EstimationSemantic proximity Read

2D Human Pose Estimation with Deep Learning: A ReviewSemantic proximity Read

MSTPose: Learning Enriched Visual Information with Multi-Scale Transformers for Human Pose EstimationSemantic proximity Read

Occlusion-aware heatmap generation for enhancing 3D human pose estimation in multi-person environmentsSemantic proximity Read

A Spatiotemporal Bidirectional Mamba Network with Global–Local Skeletal Enhancement for 3D Human Pose EstimationSemantic proximity Read

Monocular 3D Human Pose-Estimation Networks for Coherent Humanoid-Model DrivingSemantic proximity Read

A Two-Stream Deep Learning Approach for Enhanced Two-Person Human Interaction Recognition in VideosSemantic proximity Read

SRHPENet: Super-Resolution Network for human pose estimationSemantic proximity Read

SADNet: Generating Immersive Virtual Reality Avatars by Real-time Monocular Pose EstimationSemantic proximity Read

Semantically Enhanced Attention Map-Driven Occluded Person Re-identificationSemantic proximity Read

TransMODAL: A Dual-Stream Transformer with Adaptive Co-Attention for Efficient Human Action RecognitionSemantic proximity Read