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 91–100 of 483 papers

TitleStatusHype
Shift-Robust Molecular Relational Learning with Causal SubstructureCode1
In-Context Analogical Reasoning with Pre-Trained Language ModelsCode0
Modularized Zero-shot VQA with Pre-trained ModelsCode0
Visual Causal Scene Refinement for Video Question AnsweringCode3
Continual Reasoning: Non-Monotonic Reasoning in Neurosymbolic AI using Continual Learning—0
Conditional Graph Information Bottleneck for Molecular Relational LearningCode1
Cluster Flow: how a hierarchical clustering layer make allows deep-NNs more resilient to hacking, more human-like and easily implements relational reasoning—0
Retrieval-based Knowledge Augmented Vision Language Pre-training—0
Geometric Relational Embeddings: A Survey—0
Relational Context Learning for Human-Object Interaction DetectionCode1
Show:102550
← PrevPage 10 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified