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 1–10 of 483 papers

TitleStatusHype
Visual Causal Scene Refinement for Video Question AnsweringCode3
A Survey on Knowledge Graphs: Representation, Acquisition and ApplicationsCode2
Graph-Aware Isomorphic Attention for Adaptive Dynamics in TransformersCode2
MolTC: Towards Molecular Relational Modeling In Language ModelsCode2
Complex Embeddings for Simple Link PredictionCode2
Your Diffusion Model is Secretly a Zero-Shot ClassifierCode2
From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of ThoughtCode2
3D Interaction Geometric Pre-training for Molecular Relational LearningCode1
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only ModalityCode1
Beyond Graph Neural Networks with Lifted Relational Neural NetworksCode1
Show:102550
← PrevPage 1 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified