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 381–390 of 483 papers

TitleStatusHype
Position: Topological Deep Learning is the New Frontier for Relational Learning—0
Post-Hoc Robustness Enhancement in Graph Neural Networks with Conditional Random Fields—0
Post-Proceedings of the First International Workshop on Learning and Nonmonotonic Reasoning—0
Pre and Post Counting for Scalable Statistical-Relational Model Discovery—0
Propagating Over Phrase Relations for One-Stage Visual Grounding—0
Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis—0
Randomly Weighted, Untrained Neural Tensor Networks Achieve Greater Relational Expressiveness—0
Leveraging Relational Information for Learning Weakly Disentangled RepresentationsCode0
Lifted Inference beyond First-Order LogicCode0
Graph-Based Global Reasoning NetworksCode0
Show:102550
← PrevPage 39 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified