COCO

The COCO dataset is a large-scale benchmark containing images with corresponding captions, used to evaluate the performance of models in understanding and generating fine-grained visual and textual concepts.

Papers using COCO (50)

Gaze Heads: How VLMs Look at What They Describe2026RF-DETR: Neural Architecture Search For Real-time Detection Transformers2025 · 2 citesVision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions2025 · 1 citesPosellm: Enhancing Language-guided Human Pose Estimation With MLP Alignment2025How Well Does Gpt-4o Understand Vision? Evaluating Multimodal Foundation Models On Standard Computer Vision Tasks2026Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial Instructions2026A novel Framework for Open-Vocabulary Multi-Object Recognition using CLIP2026QATMA: Quantization-Aware Training with Multimodal Alignment for Open-Vocabulary Object Detection2026Good Scores, Bad Data: A Metric for Multimodal Coherence2026Cognitively-Inspired Tokens Overcome Egocentric Bias in Multimodal Models2026Efficient Vision-Language Reasoning via Adaptive Token Pruning2025RGBT-Ground Benchmark: Visual Grounding Beyond RGB in Complex Real-World Scenarios2025A Little More Like This: Text-to-Image Retrieval with Vision-Language Models Using Relevance Feedback2025Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?2025Semantic-guided Natural Language And Visual Fusion For Cross-modal Interaction Based On Tiny Object Detection2025Covmatch: Cross-covariance Guided Multimodal Dataset Distillation With Trainable Text Encoder2025The Telephone Game: Evaluating Semantic Drift in Unified Models2025When Does Supervised Training Pay Off? The Hidden Economics Of Object Detection In The Era Of Vision-language Models2025Gm-skip: Metric-guided Transformer Block Skipping For Efficient Vision-language Models2025Robust Vision-language Models Via Tensor Decomposition: A Defense Against Adversarial Attacks2025CLASH: A Benchmark For Cross-modal Contradiction Detection2025Dynamic Context-aware Scene Reasoning Using Vision-language Alignment In Zero-shot Real-world Scenarios2025Common Inpainted Objects In-n-out Of Context2025LaViDa: A Large Diffusion Language Model for Multimodal Understanding2025COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation2025Re-ranking the Context for Multimodal Retrieval Augmented Generation2025X-Linear Attention Networks for Image Captioning2020 · 689 citesProbabilistic Embeddings for Cross-Modal Retrieval2021 · 226 citesUNITER: UNiversal Image-TExt Representation Learning2019 · 185 citesImage as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks2022 · 151 citesCAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval2019 · 31 citesUnderstanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task2016 · 7 citesLightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval2021 · 6 citesSemantic-Conditional Diffusion Networks for Image Captioning2022 · 6 citesRevisiting Few-Shot Object Detection with Vision-Language Models2023 · 4 citesSecuring Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks2024 · 4 citesMixGen: A New Multi-Modal Data Augmentation2022 · 2 citesVLDeformer: Vision-Language Decomposed Transformer for Fast Cross-Modal Retrieval2021 · 1 citesFine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection2022 · 1 citesSelf-Supervised Image Captioning with CLIP2023 · 1 citesEfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning2022SLAN: Self-Locator Aided Network for Cross-Modal Understanding2022Cross-Modal Similarity-Based Curriculum Learning for Image Captioning2022Fine-grained Cross-modal Fusion based Refinement for Text-to-Image Synthesis2023Making the Most of What You Have: Adapting Pre-trained Visual Language Models in the Low-data Regime2023ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models2023Enhancing Conceptual Understanding in Multimodal Contrastive Learning through Hard Negative Samples2024ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes2024Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)2024Leveraging Retrieval-Augmented Tags for Large Vision-Language Understanding in Complex Scenes2024