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 101–110 of 483 papers

TitleStatusHype
Modularized Zero-shot VQA with Pre-trained ModelsCode0
Lifted Inference beyond First-Order LogicCode0
Benchmarking and Understanding Compositional Relational Reasoning of LLMsCode0
LightPath: Lightweight and Scalable Path Representation LearningCode0
Leveraging Relational Information for Learning Weakly Disentangled RepresentationsCode0
Learning the meanings of function words from grounded language using a visual question answering modelCode0
Beyond the Doors of Perception: Vision Transformers Represent Relations Between ObjectsCode0
MDE: Multiple Distance Embeddings for Link Prediction in Knowledge GraphsCode0
Logic Tensor Networks for Semantic Image InterpretationCode0
PARN: Position-Aware Relation Networks for Few-Shot LearningCode0
Show:102550
← PrevPage 11 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified