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 241–250 of 483 papers

TitleStatusHype
Imagine, Reason and Write: Visual Storytelling with Graph Knowledge and Relational Reasoning—0
Agent-Centric Representations for Multi-Agent Reinforcement Learning—0
Object-Centric Representation Learning for Video Question Answering—0
Unified Graph Structured Models for Video Understanding—0
Graph-based Facial Affect Analysis: A Review—0
Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQACode0
A Relational-learning Perspective to Multi-label Chest X-ray Classification—0
A Universal Model for Cross Modality Mapping by Relational Reasoning—0
Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking—0
A Statistical Relational Approach to Learning Distance-based GCNs—0
Show:102550
← PrevPage 25 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified