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 171–180 of 483 papers

TitleStatusHype
DEVICE: DEpth and VIsual ConcEpts Aware Transformer for TextCaps—0
Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation TypesCode0
Knowledge-augmented Graph Neural Networks with Concept-aware Attention for Adverse Drug Event Detection—0
ReVoLT: Relational Reasoning and Voronoi Local Graph Planning for Target-driven Navigation—0
Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning—0
SrTR: Self-reasoning Transformer with Visual-linguistic Knowledge for Scene Graph Generation—0
Breakpoint Transformers for Modeling and Tracking Intermediate BeliefsCode0
Learning Probabilistic Temporal Safety Properties from Examples in Relational Domains—0
Lifted Inference with Linear Order Axiom—0
Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning—0
Show:102550
← PrevPage 18 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified