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 21–30 of 483 papers

TitleStatusHype
Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in TransformersCode1
Beyond Graph Neural Networks with Lifted Relational Neural NetworksCode1
Deep Relational Reasoning Graph Network for Arbitrary Shape Text DetectionCode1
Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image InterpretationCode1
CORE-Text: Improving Scene Text Detection with Contrastive Relational ReasoningCode1
Few-shot Relational Reasoning via Connection Subgraph PretrainingCode1
3D Interaction Geometric Pre-training for Molecular Relational LearningCode1
Conditional Graph Information Bottleneck for Molecular Relational LearningCode1
COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only ModalityCode1
Cross-Modal Causal Relational Reasoning for Event-Level Visual Question AnsweringCode1
Show:102550
← PrevPage 3 of 49Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CTP A4 Hops0.99—Unverified