- A Hyperbolic-to-Hyperbolic Graph Convolutional Network
- Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders
- Mutual CRF-GNN for Few-Shot Learning
- ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-Shot Learning
- Few-Shot Incremental Learning With Continually Evolved Classifiers
- SelfSAGCN: Self-Supervised Semantic Alignment for Graph Convolution Network
- Learning Graphs for Knowledge Transfer With Limited Labels
- Learning Graph Embeddings for Compositional Zero-shot Learning
- Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentation
- Scale-Aware Graph Neural Network for Few-Shot Semantic Segmentation
- Bottom-Up Shift and Reasoning for Referring Image Segmentation
- Deep Occlusion-Aware Instance Segmentation With Overlapping BiLayers
- Towards Part-Based Understanding of RGB-D Scans
- 3D Graph Anatomy Geometry-Integrated Network for Pancreatic Mass Segmentation, Diagnosis, and Quantitative Patient Management
- TSGCNet: Discriminative Geometric Feature Learning with Two-Stream GraphConvolutional Network for 3D Dental Model Segmentation
- Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation
- Quantifying Explainers of Graph Neural Networks in Computational Pathology
- Mol2Image: Improved Conditional Flow Models for Molecule to Image Synthesis
- Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection
- Mutual Graph Learning for Camouflaged Object Detection
- To the Point: Efficient 3D Object Detection in the Range Image With Graph Convolution Kernels
- Graph-Based High-Order Relation Discovery for Fine-Grained Recognition
- Deep Graph Matching under Quadratic Constraint
- LayoutGMN: Neural Graph Matching for Structural Layout Similarity
- Robust Point Cloud Registration Framework Based on Deep Graph Matching
- Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
- Combinatorial Learning of Graph Edit Distance via Dynamic Embedding
- DyGLIP: A Dynamic Graph Model With Link Prediction for Accurate Multi-Camera Multiple Object Tracking
- Learning a Proposal Classifier for Multiple Object Tracking
- Graph Attention Tracking
- StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networks
- PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks
- Self-Point-Flow: Self-Supervised Scene Flow Estimation From Point Clouds With Optimal Transport and Random Walk
- TearingNet: Point Cloud Autoencoder To Learn Topology-Friendly Representations
- Learning Fine-Grained Segmentation of 3D Shapes Without Part Labels
- FAIEr: Fidelity and Adequacy Ensured Image Caption Evaluation
- Scan2Cap: Context-Aware Dense Captioning in RGB-D Scans
- Relation-aware Instance Refinement for Weakly Supervised Visual Grounding
- Explicit Knowledge Incorporation for Visual Reasoning
- KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA
- Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis
- SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
- Neural Scene Graphs for Dynamic Scenes
- Scene Essence
- Holistic 3D Scene Understanding From a Single Image With Implicit Representation
- Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation
- Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation
- Linguistic Structures As Weak Supervision for Visual Scene Graph Generation
- Energy-Based Learning for Scene Graph Generation
- Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos
- Person Re-Identification Using Heterogeneous Local Graph Attention Networks
- Unsupervised Multi-Source Domain Adaptation for Person Re-Identification
- Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation
- Amalgamating Knowledge From Heterogeneous Graph Neural Networks
- Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering
- Learning Asynchronous and Sparse Human-Object Interaction in Videos
- Multi-Modal Relational Graph for Cross-Modal Video Moment Retrieval
- Representing Videos As Discriminative Sub-Graphs for Action Recognition
- Dynamic Probabilistic Graph Convolution for Facial Action Unit Intensity Estimation
- Hybrid Message Passing With Performance-Driven Structures for Facial Action Unit Detection
- Graph-Based High-Order Relation Modeling for Long-Term Action Recognition
- Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking
- Graph Stacked Hourglass Networks for 3D Human Pose Estimation
- Context Modeling in 3D Human Pose Estimation: A Unified Perspective
- Towards Accurate 3D Human Motion Prediction From Incomplete Observations
- SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
- FS-Net: Fast Shape-Based Network for Category-Level 6D Object Pose Estimation With Decoupled Rotation Mechanism
- Keypoint-Graph-Driven Learning Framework for Object Pose Estimation
- Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty
- Deep Active Surface Models
- Picasso: A CUDA-Based Library for Deep Learning Over 3D Meshes
- Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction
- NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go
- Plan2Scene: Converting Floorplans to 3D Scenes
- Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses
- Inferring CAD Modeling Sequences Using Zone Graphs
- BRepNet: A topological message passing system for solid models
- UV-Net: Learning From Boundary Representations
- SOON: Scenario Oriented Object Navigation with Graph-based Exploration
- HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps
- Structure-Aware Face Clustering on a Large-Scale Graph with 10^7 Nodes
- 3DCaricShop: A Dataset and A Baseline Method for Single-view 3D Caricature Face Reconstruction
- Clusformer: A Transformer Based Clustering Approach to Unsupervised Large-Scale Face and Visual Landmark Recognition
- Sequential Graph Convolutional Network for Active Learning
- Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation
- Rethinking Graph Neural Network Search from Message-passing
- DualGraph: A Graph-Based Method for Reasoning About Label Noise
- End-to-End Rotation Averaging With Multi-Source Propagation
- Primitive Representation Learning for Scene Text Recognition
- Hierarchical Layout-Aware Graph Convolutional Network for Unified Aesthetics Assessment
- Fast End-to-End Learning on Protein Surfaces