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 411–420 of 483 papers

TitleStatusHype
Breakpoint Transformers for Modeling and Tracking Intermediate BeliefsCode0
Beyond the Doors of Perception: Vision Transformers Represent Relations Between ObjectsCode0
Few-shot Knowledge Graph Relational Reasoning via Subgraph AdaptationCode0
Generalization of CNNs on Relational Reasoning with Bar ChartsCode0
Knowledge Graph Completion via Complex Tensor FactorizationCode0
Modeling Content and Context with Deep Relational LearningCode0
Benchmarking and Understanding Compositional Relational Reasoning of LLMsCode0
Unraveling the geometry of visual relational reasoningCode0
Explaining Local, Global, And Higher-Order Interactions In Deep LearningCode0
Modularized Zero-shot VQA with Pre-trained ModelsCode0
Show:102550
← PrevPage 42 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified