Cover Image

A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Urbanek, Jack, Bordes, Florian, Astolfi, Pietro, Williamson, Mary, Sharma, Vasu, Romero-Soriano, Adriana
Format:	Preprint
Published:	2023
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Object-centric Binding in Contrastive Language-Image Pretraining
by: Assouel, Rim, et al.
Published: (2025)

Improving Text-to-Image Consistency via Automatic Prompt Optimization
by: Mañas, Oscar, et al.
Published: (2024)

Improving the Scaling Laws of Synthetic Data with Deliberate Practice
by: Askari-Hemmat, Reyhane, et al.
Published: (2025)

CLIP with Quality Captions: A Strong Pretraining for Vision Tasks
by: Vasu, Pavan Kumar Anasosalu, et al.
Published: (2024)

Feedback-guided Data Synthesis for Imbalanced Classification
by: Hemmat, Reyhane Askari, et al.
Published: (2023)

Tokenization Is More Than Compression
by: Schmidt, Craig W., et al.
Published: (2024)

DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
by: Lebensold, Jonathan, et al.
Published: (2024)

Parrot Captions Teach CLIP to Spot Text
by: Lin, Yiqi, et al.
Published: (2023)

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
by: Wang, Feng, et al.
Published: (2025)

An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
by: Nguyen, Duy-Kien, et al.
Published: (2024)

Consistency-diversity-realism Pareto fronts of conditional image generative models
by: Astolfi, Pietro, et al.
Published: (2024)

Discrete Audio Tokens: More Than a Survey!
by: Mousavi, Pooneh, et al.
Published: (2025)

From Pixels to Prose: A Large Dataset of Dense Image Captions
by: Singla, Vasu, et al.
Published: (2024)

VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation
by: Zheng, Yan, et al.
Published: (2026)

A Text is Worth Several Tokens: Text Embedding from LLMs Secretly Aligns Well with The Key Tokens
by: Nie, Zhijie, et al.
Published: (2024)

StyleHumanCLIP: Text-guided Garment Manipulation for StyleGAN-Human
by: Yoshikawa, Takato, et al.
Published: (2023)

Captions Are Worth a Thousand Words: Enhancing Product Retrieval with Pretrained Image-to-Text Models
by: Tang, Jason, et al.
Published: (2024)

A Picture is Worth a Thousand (Correct) Captions: A Vision-Guided Judge-Corrector System for Multimodal Machine Translation
by: Betala, Siddharth, et al.
Published: (2025)

A Pixel Is Worth More Than One 3D Gaussians in Single-View 3D Reconstruction
by: Shen, Jianghao, et al.
Published: (2024)

Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation
by: Csizmadia, Daniel, et al.
Published: (2025)

Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder
by: Li, Siting, et al.
Published: (2024)

Boosting Latent Diffusion with Perceptual Objectives
by: Berrada, Tariq, et al.
Published: (2024)

iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
by: Hu, Lianyu, et al.
Published: (2024)

MoreHopQA: More Than Multi-hop Reasoning
by: Schnitzler, Julian, et al.
Published: (2024)

Ep. 305: Is Your Typing Style More Secure Than Your Password?
by: Rosehill, Daniel, et al.
Published: (2026)

More Than Efficiency: Embedding Compression Improves Domain Adaptation in Dense Retrieval
by: Zuo, Chunsheng, et al.
Published: (2026)

Words Worth a Thousand Pictures: Measuring and Understanding Perceptual Variability in Text-to-Image Generation
by: Tang, Raphael, et al.
Published: (2024)

Dense Motion Captioning
by: Xu, Shiyao, et al.
Published: (2025)

MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
by: Vasu, Pavan Kumar Anasosalu, et al.
Published: (2023)

A LoRA is Worth a Thousand Pictures
by: Liu, Chenxi, et al.
Published: (2024)

CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech
by: Wang, Helin, et al.
Published: (2025)

SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation
by: Chen, Xiaofu, et al.
Published: (2025)

AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning
by: Kim, Jongsuk, et al.
Published: (2024)

Towards Geographic Inclusion in the Evaluation of Text-to-Image Models
by: Hall, Melissa, et al.
Published: (2024)

Film & Culture: Introduction. The Human/More‐Than‐Human Relationship
by: Laura Camille Tuley, et al.
Published: (2024)

VeCLIP: Improving CLIP Training via Visual-enriched Captions
by: Lai, Zhengfeng, et al.
Published: (2023)

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
by: Kim, Eunji, et al.
Published: (2024)

MiSCHiEF: A Benchmark in Minimal-Pairs of Safety and Culture for Holistic Evaluation of Fine-Grained Image-Caption Alignment
by: Banerjee, Sagarika, et al.
Published: (2026)

Streaming Dense Video Captioning
by: Zhou, Xingyi, et al.
Published: (2024)

A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
by: Liu, Huijie, et al.
Published: (2025)