Conceptual Captions

Dataset Card for Conceptual Captions Dataset Summary Conceptual Captions is a dataset consisting of ~3.3M images annotated with captions. In contrast with the curated style of other image caption annotations, Conceptual Caption images and their raw descriptions are harvested from the web, and therefore represent a wide

Papers using Conceptual Captions (16)

Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation2025 · 1 citesDINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency2026DREAM: Where Visual Understanding Meets Text-to-Image Generation2026Beyond Generation: Multi-Hop Reasoning for Factual Accuracy in Vision-Language Models2025Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?2025ViLU: Learning Vision-Language Uncertainties for Failure Prediction2025Redemption Score: A Multi-Modal Evaluation Framework for Image Captioning via Distributional, Perceptual, and Linguistic Signal Triangulation2025ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks2019 · 1,676 citesVL-BERT: Pre-training of Generic Visual-Linguistic Representations2019 · 785 citesUNITER: UNiversal Image-TExt Representation Learning2019 · 185 citesImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data2020 · 156 citesConceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts2021 · 37 citesLarge-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline2019 · 1 citesImproving Vision-and-Language Navigation with Image-Text Pairs from the Web2020 · 1 citesL-Verse: Bidirectional Generation Between Image and Text2021 · 1 citesUnified Lexical Representation for Interpretable Visual-Language Alignment2024