Visual Genome

Images densely annotated with objects, attributes, relationships, region descriptions, and QA.

Papers using Visual Genome (16)

PRISM-0: A Predicate-Rich Scene Graph Generation Framework for Zero-Shot Open-Vocabulary Tasks2025 · 1 citesGood Scores, Bad Data: A Metric for Multimodal Coherence2026Investigating Spatial Attention Bias in Vision-Language Models2025Multimodal Arabic Captioning With Interpretable Visual Concept Integration2025Dynamic Context-aware Scene Reasoning Using Vision-language Alignment In Zero-shot Real-world Scenarios2025Compositional Image-Text Matching and Retrieval by Grounding Entities2025Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers2020 · 286 citesUNITER: UNiversal Image-TExt Representation Learning2019 · 185 citesEfficient Multi-Modal Embeddings from Structured Data2021 · 1 citesHaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language2023DualFocus: Integrating Macro and Micro Perspectives in Multi-modal Large Language Models2024Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models2024Learning Unsupervised Visual Grounding Through Semantic Self-Supervision2018R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering2018ViCo: Word Embeddings from Visual Co-occurrences2019Text-Region Matching for Multi-Label Image Recognition with Missing Labels2024