Semi-Supevised Learning

• SimMatchV2: Semi-Supervised Learning with Graph Consistency
• Improved Knowledge Transfer for Semi-Supervised Domain Adaptation via Trico Training Strategy

Scene Graph

• VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering
• SGAligner: 3D Scene Alignment with Scene Graphs
• Visual Traffic Knowledge Graph Generation from Scene Images

Object Detection

• Vision HGNN: An Image is More than a Graph of Nodes
• Detecting Objects with Context-Likelihood Graphs and Graph Refinement

Face Clustering

• Face Clustering via Graph Convolutional Networks with Confidence Edges
• CLIP-Cluster: CLIP-Guided Attribute Hallucination for Face Clustering

Matching

• GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation
• ShapeScaffolder: Structure-Aware 3D Shape Generation from Text
• End2End Multi-View Feature Matching with Differentiable Pose Optimization
• GlueStick: Robust Image Matching by Sticking Points and Lines Together

Point Clouds

• DMNet: Delaunay Meshing Network for 3D Shape Representation
• PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label
• Chasing Clouds: Differentiable Volumetric Rasterisation of Point Clouds as a Highly Efficient and Accurate Loss for Large-Scale Deformable 3D Registration
• CO-PILOT: Dynamic Top-Down Point Cloud with Conditional Neighborhood Aggregation for Multi-Gigapixel Histopathology Image Representation

Trajectory Prediction

• Learning Adaptive Neighborhoods for Graph Neural Networks
• 3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking
• Learn TAROT with MENTOR: A Meta-Learned Self-Supervised Approach for Trajectory Prediction

Benchmarks

• Efficient Deep Space Filling Curve
• DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization

Instance Segmentation

• WaterMask: Instance Segmentation for Underwater Imagery
• Re:PolyWorld - A Graph Neural Network for Polygonal Scene Parsing

Meshes

• Reconstructing Groups of People with Hypergraph Relational Reasoning
• Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image
• Dynamic Hyperbolic Attention Network for Fine Hand-object Reconstruction
• Spectral Graphormer: Spectral Graph-Based Transformer for Egocentric Two-Hand Reconstruction using Multi-View Color Images

Videos

• DCPB: Deformable Convolution Based on the Poincare Ball for Top-view Fisheye Cameras
• Video Action Segmentation via Contextually Refined Temporal Keypoints

Pose Estimation

• HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimation
• GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video
• HDG-ODE: A Hierarchical Continuous-Time Model for Human Pose Forecasting
• CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network
• HandR2N2: Iterative 3D Hand Pose Estimation Using a Residual Recurrent Neural Network
• Normalizing Flows for Human Pose Anomaly Detection

Action Recognition

• SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
• Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching
• FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation

Skeleton-based Action Recognition

• SkeleTR: Towards Skeleton-based Action Recognition in the Wild
• Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition

Gait Recognition

• Physics-Augmented Autoencoder for 3D Skeleton-Based Gait Recognition
• GPGait: Generalized Pose-based Gait Recognition

Spatio-Temporal Data

• Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
• ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking

Spatial Relationships

• Fg-T2M: Fine-Grained Text-Driven Human Motion Generation via Diffusion Model
• Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning

Contrastive Learning

• Scene Graph Contrastive Learning for Embodied Navigation
• MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learning
• ReactioNet: Learning High-Order Facial Behavior from Universal Stimulus-Reaction by Dyadic Relation Reasoning

Miscellaneous

• GlobalMapper: Arbitrary-Shaped Urban Layout Generation
• Persistent-Transient Duality: A Multi-Mechanism Approach for Modeling Human-Object Interaction
• RLSAC: Reinforcement Learning Enhanced Sample Consensus for End-to-End Robust Estimation
• Virtual Try-On with Pose-Garment Keypoints Guided Inpainting
• VertexSerum: Poisoning Graph Neural Networks for Link Inference
• MolGrapher: Graph-based Visual Recognition of Chemical Structures
• Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
• CoSign: Exploring Co-occurrence Signals in Skeleton-based Continuous Sign Language Recognition
• Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views
• HM-ViT: Hetero-Modal Vehicle-to-Vehicle Cooperative Perception with Vision Transformer