Flickr30k

Flickr30k is a large-scale dataset containing 30,000 images, each paired with five corresponding textual descriptions, used to evaluate cross-modal retrieval and the alignment between visual and textual information.

Papers using Flickr30k (23)

Intra-Modal Neighbors Never Lie: Rectifying Inter-Modal Noisy Correspondence via Graph-Based Intra-Modal Reasoning2026MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data2026LogicGaze: Benchmarking Causal Consistency in Visual Narratives via Counterfactual Verification2026CoT4Det: A Chain-of-Thought Framework for Perception-Oriented Vision-Language Tasks2025SEPS: Semantic-enhanced Patch Slimming Framework for fine-grained cross-modal alignment2025Cross Modal Fine-Grained Alignment via Granularity-Aware and Region-Uncertain Modeling2025A Little More Like This: Text-to-Image Retrieval with Vision-Language Models Using Relevance Feedback2025Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions2025Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge2025Rate-distortion Limits For Multimodal Retrieval: Theory, Optimal Codes, And Finite-sample Guarantees2025Parameter Efficient Multimodal Instruction Tuning For Romanian Vision Language Models2025Covmatch: Cross-covariance Guided Multimodal Dataset Distillation With Trainable Text Encoder2025Robust Vision-language Models Via Tensor Decomposition: A Defense Against Adversarial Attacks2025Compositional Image-Text Matching and Retrieval by Grounding Entities2025Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillation2025Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation2025CIBR: Cross-modal Information Bottleneck Regularization for Robust CLIP Generalization2025CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance2024 · 2 citesLinear Alignment of Vision-language Models for Image Captioning2023Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association2023Feedback-based Modal Mutual Search for Attacking Vision-Language Pre-training Models2024Nearest Neighbor Normalization Improves Multimodal Retrieval2024Towards Fast and Accurate Image-Text Retrieval with Self-Supervised Fine-Grained Alignment2023