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 41–50 of 483 papers

TitleStatusHype
RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing ImagesCode1
Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph RepresentationsCode1
DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question AnsweringCode1
Relational VAE: A Continuous Latent Variable Model for Graph Structured DataCode1
Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph CompletionCode1
Prototypical Representation Learning for Relation ExtractionCode1
Inductive Relation Prediction by BERTCode1
Learning Symbolic Operators for Task and Motion PlanningCode1
GraphLog: A Benchmark for Measuring Logical Generalization in Graph Neural NetworksCode1
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive LearningCode1
Show:102550
← PrevPage 5 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified