SOTAVerified

Relational Reasoning

The goal of Relational Reasoning is to figure out the relationships among different entities, such as image pixels, words or sentences, human skeletons or interactive moving agents.

Source: Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network

Papers

Showing 2650 of 483 papers

TitleStatusHype
LowFER: Low-rank Bilinear Pooling for Link PredictionCode1
3D Interaction Geometric Pre-training for Molecular Relational LearningCode1
Evaluating Logical Generalization in Graph Neural NetworksCode1
Graph-Based Social Relation ReasoningCode1
Fast Graph Representation Learning with PyTorch GeometricCode1
Inductive Relation Prediction by BERTCode1
Generative 3D Part Assembly via Dynamic Graph LearningCode1
Fusing Context Into Knowledge Graph for Commonsense Question AnsweringCode1
Generative Adversarial Zero-Shot Relational Learning for Knowledge GraphsCode1
Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image InterpretationCode1
CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from TextCode1
GraphLog: A Benchmark for Measuring Logical Generalization in Graph Neural NetworksCode1
GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational ReasoningCode1
Beyond Graph Neural Networks with Lifted Relational Neural NetworksCode1
Computer-aided Tuberculosis Diagnosis with Attribute Reasoning AssistanceCode1
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only ModalityCode1
Global-Reasoned Multi-Task Learning Model for Surgical Scene UnderstandingCode1
Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in TransformersCode1
Conditional Graph Information Bottleneck for Molecular Relational LearningCode1
CORE-Text: Improving Scene Text Detection with Contrastive Relational ReasoningCode1
Cross-Modal Causal Relational Reasoning for Event-Level Visual Question AnsweringCode1
DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question AnsweringCode1
EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question AnsweringCode1
BayReL: Bayesian Relational Learning for Multi-omics Data IntegrationCode1
Inductive Relation Prediction by Subgraph ReasoningCode1
Show:102550
← PrevPage 2 of 20Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99Unverified