Relational Reasoning

149 papers with code • 1 benchmarks • 12 datasets

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

Libraries

Use these libraries to find Relational Reasoning models and implementations

Latest papers with no code

Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation

no code yet • 25 Mar 2024

We hypothesize that the underlying phenomenological coverage has not been proportionally scaled up, leading to a skew of the presented phenomenon which harms generalization.

TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models

no code yet • 25 Mar 2024

Next, TRIP executes a residual-like dual-path scheme for noise prediction: 1) a shortcut path that directly takes image noise prior as the reference noise of each frame to amplify the alignment between the first frame and subsequent frames; 2) a residual path that employs 3D-UNet over noised video and static image latent codes to enable inter-frame relational reasoning, thereby easing the learning of the residual noise for each frame.

Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents

no code yet • 23 Mar 2024

This approach aims to generate relation representations that are more aware of the spatial context and unseen relation in a manner similar to human perception.

SeCG: Semantic-Enhanced 3D Visual Grounding via Cross-modal Graph Attention

no code yet • 13 Mar 2024

3D visual grounding aims to automatically locate the 3D region of the specified object given the corresponding textual description.

Deep Generative Models for Ultra-High Granularity Particle Physics Detector Simulation: A Voyage From Emulation to Extrapolation

no code yet • 5 Mar 2024

Then, it presents the Intra-Event Aware Generative Adversarial Network (IEA-GAN), a new geometry-aware generative model that introduces a relational attentive reasoning and Self-Supervised Learning to approximate an "event" in the detector.

Boosting gets full Attention for Relational Learning

no code yet • 22 Feb 2024

Second, what has been learned progresses back bottom-up via attention and aggregation mechanisms, progressively crafting new features that complete at the end the set of observation features over which a single tree is learned, boosting's iteration clock is incremented and new class residuals are computed.

Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation

no code yet • 22 Jan 2024

In this paper, we propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures, and we demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation.

LLMs for Relational Reasoning: How Far are We?

no code yet • 17 Jan 2024

Large language models (LLMs) have revolutionized many areas (e. g. natural language processing, software engineering, etc.)

MLAD: A Unified Model for Multi-system Log Anomaly Detection

no code yet • 15 Jan 2024

In spite of the rapid advancements in unsupervised log anomaly detection techniques, the current mainstream models still necessitate specific training for individual system datasets, resulting in costly procedures and limited scalability due to dataset size, thereby leading to performance bottlenecks.

EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering

no code yet • 19 Dec 2023

Earth vision research typically focuses on extracting geospatial object locations and categories but neglects the exploration of relations between objects and comprehensive reasoning.