CLEVR

CLEVR is a dataset designed to evaluate the ability of models to perform visual reasoning and understand complex relationships in images through a series of structured questions and answers.

Papers using CLEVR (12)

Gen-VCoT: Generative Visual Chain-of-Thought Reasoning via Diffusion-Based RGB Intermediate Representations2026Self-Questioning Vision-Language Models: Reinforcement Learning for Compositional Visual Reasoning2026Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models2025Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models2025Visual Entailment: A Novel Task for Fine-Grained Image Understanding2019 · 162 citesMDETR -- Modulated Detection for End-to-End Multi-Modal Understanding2021 · 2 citesCascaded Mutual Modulation for Visual Reasoning2018 · 1 citesCLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images2021VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval2023LCV2: An Efficient Pretraining-Free Framework for Grounded Visual Question Answering2024SADL: An Effective In-Context Learning Method for Compositional Visual QA2024Object-based reasoning in VQA2018