Scientific Research Publishing

Geo-Refined Point Transformer: Coordinate-Aware Excitation and Positional Upsampling for 3D Scene Segmentation ()

The proposed Coordinate-Aware Feature Excitation (CAFE) module and Position-Aware Upsampling (Pos-Up) module both adhere to ...
IEEE

Double-Chain Graph Convolution Transformer for 3D Human Pose Estimation

Abstract: Reconstructing 3D poses from 2D poses lacking depth information is particularly challenging due to the complexity and diversity of human motion. The key is to effectively model the spatial ...
IEEE

Adaptive Graph Convolution and Semantic-Guided Attention for Multimodal Risk Detection in Social Networks

Abstract: This paper focuses on the detection of potentially dangerous tendencies of social media users in an innovative multimodal way. We integrate Natural Language Processing (NLP) and Graph Neural ...
GitHub

ImpSGNv2: Improved Semantic-Guided Networkwith Attention-based Graph Convolution (GCNs)For Skeleton-based Action Recognition

A critical challenge in skeleton-based action recognition lies in effectively extracting meaningful features from skeleton joints. However, existing state-of-the-art networks for this task are often ...
GitHub

Graph Convolutional Network for Link Prediction

This project implements a Graph Convolutional Network (GCN) to perform link prediction on a social network graph. The objective is to learn node representations from graph structure and use them to ...