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 71–80 of 483 papers

TitleStatusHype
Fast Graph Representation Learning with PyTorch GeometricCode1
EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question AnsweringCode1
Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image InterpretationCode1
Neural Logic MachinesCode1
MLPs Learn In-Context on Regression and Classification TasksCode1
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only ModalityCode1
ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive LearningCode1
Evaluating Logical Generalization in Graph Neural NetworksCode1
Few-shot Relational Reasoning via Connection Subgraph PretrainingCode1
Reasoning with Latent Structure Refinement for Document-Level Relation ExtractionCode1
Show:102550
← PrevPage 8 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified