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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–60 of 483 papers

TitleStatusHype
Logic Tensor NetworksCode1
Fusing Context Into Knowledge Graph for Commonsense Question AnsweringCode1
Self-Supervised Time Series Representation Learning by Inter-Intra Relational ReasoningCode1
Play Fair: Frame Attributions in Video ModelsCode1
BayReL: Bayesian Relational Learning for Multi-omics Data IntegrationCode1
Scale-Localized Abstract ReasoningCode1
Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal RepresentationsCode1
Learning from Protein Structure with Geometric Vector PerceptronsCode1
LowFER: Low-rank Bilinear Pooling for Link PredictionCode1
Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational LearningCode1
Show:102550
← PrevPage 6 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified