IEEE

SPGformer: Serial–Parallel Hybrid GCN-Transformer With Graph-Oriented Encoder for 2-D-to-3-D Human Pose Estimation

Abstract: Accurate acquisition of 3-D human joint poses holds significant implications for tasks such as human action recognition. Monocular single-frame 2-D -to-3-D pose estimation focuses on ...
GitHub

EdgeSHAPer: Bond-Centric Shapley Value-Based Explanation Method for Graph Neural Networks

This is the official implementation for EdgeSHAPer: Bond-Centric Shapley Value-Based Explanation Method for Graph Neural Networks. The methodology relies on Shapley values approximations to determine ...
IEEE

Learning Joint 2-D and 3-D Graph Diffusion Models for Complete Molecule Generation

Abstract: Designing new molecules is essential for drug discovery and material science. Recently, deep generative models that aim to model molecule distribution have made promising progress in ...
GitHub

Graph Contrastive Learning with Cohesive Subgraph Awareness

Our research paper has been accepted to The Web Conference 2024. . ├─ framework.png ├─ get_sub_counts.py ├─ main.py ├─ README.md │ ├─ CTAug │ ├─ evaluate.py │ ├─ model.py │ ├─ preprocess.py │ ├─ utils ...