paper-with-me

홈 › Papers

LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation

2025-06-05 · Biao Guo, Fangmin Guo, Guibo Luo, Xiaonan Luo, Feng Zhang

Most of the current top-down multi-person pose estimation lightweight methods are based on multi-branch parallel pure CNN network architecture, which often struggle to capture the global context required for detecting semantically complex keypoints and are hindered by high latency due to their intricate and redundant structures. In this article, an approximate single-branch lightweight global modeling network (LGM-Pose) is proposed to address these challenges. In the network, a lightweight MobileViM Block is designed with a proposed Lightweight Attentional Representation Module (LARM), which integrates information within and between patches using the Non-Parametric Transformation Operation(NPT-Op) to extract global information. Additionally, a novel Shuffle-Integrated Fusion Module (SFusion) is introduced to effectively integrate multi-scale information, mitigating performance degradation often observed in single-branch structures. Experimental evaluations on the COCO and MPII datasets demonstrate that our approach not only reduces the number of parameters compared to existing mainstream lightweight methods but also achieves superior performance and faster processing speeds.

📄 PDF Abstract BibTeX arXiv:2506.04561

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Person Pose EstimationPose Estimation

Similar Papers 제목 키워드 기반

FSPEN: AN ULTRA-LIGHTWEIGHT NETWORK FOR REAL TIME SPEECH ENAHNCMENT

2024-04-15 · Conference 2024 4 · Lei Yang1, Wei Liu1, Ruijie Meng1, Gunwoo Lee2 외

Deep learning-based speech enhancement methods have shown promising result in recent years. However, in practical applications, the model size and computational complexity are important factors that limit their use in en…

Speech Enhancement

A Lightweight and Effective Image Tampering Localization Network with Vision Mamba

2025-02-14 · Kun Guo, Gang Cao, Zijie Lou, Xianglin Huang 외

Current image tampering localization methods primarily rely on Convolutional Neural Networks (CNNs) and Transformers. While CNNs suffer from limited local receptive fields, Transformers offer global context modeling at t…

DecoderMamba

DualMamba: A Lightweight Spectral-Spatial Mamba-Convolution Network for Hyperspectral Image Classification

2024-06-11 · Jiamu Sheng, Jingyi Zhou, Jiong Wang, Peng Ye 외

The effectiveness and efficiency of modeling complex spectral-spatial relations are both crucial for Hyperspectral image (HSI) classification. Most existing methods based on CNNs and transformers still suffer from heavy …

ClassificationHyperspectral Image Classificationimage-classificationImage Classification+1

Efficient Semantic Segmentation via Lightweight Multiple-Information Interaction Network

2024-10-03 · Yangyang Qiu, Guoan Xu, Guangwei Gao, Zhenhua Guo 외

Recently, integrating the local modeling capabilities of Convolutional Neural Networks (CNNs) with the global dependency strengths of Transformers has created a sensation in the semantic segmentation community. However, …

GPUReal-Time Semantic SegmentationSemantic Segmentation

Efficient Temporal Modeling for Mobile Sleep Staging via Lightweight Random Attention

2026-05-31 · Guisong Liu, Pengfei Wei, Jainsong Zhang, Martin Dresler arxiv

Mobile sleep staging serves as a foundational infrastructure for in-home sleep monitoring and closed-loop modulation. But existing sequential models such as RNNs and Transformers are computationally expensive for mobile …