paper-with-me

홈 › Papers

CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era

2025-03-16 · Kanzhi Cheng, Wenpo Song, Jiaxin Fan, Zheng Ma, Qiushi Sun, Fangzhi Xu, Chenyang Yan, Nuo Chen, Jianbing Zhang, Jiajun Chen

Image captioning has been a longstanding challenge in vision-language research. With the rise of LLMs, modern Vision-Language Models (VLMs) generate detailed and comprehensive image descriptions. However, benchmarking the quality of such captions remains unresolved. This paper addresses two key questions: (1) How well do current VLMs actually perform on image captioning, particularly compared to humans? We built CapArena, a platform with over 6000 pairwise caption battles and high-quality human preference votes. Our arena-style evaluation marks a milestone, showing that leading models like GPT-4o achieve or even surpass human performance, while most open-source models lag behind. (2) Can automated metrics reliably assess detailed caption quality? Using human annotations from CapArena, we evaluate traditional and recent captioning metrics, as well as VLM-as-a-Judge. Our analysis reveals that while some metrics (e.g., METEOR) show decent caption-level agreement with humans, their systematic biases lead to inconsistencies in model ranking. In contrast, VLM-as-a-Judge demonstrates robust discernment at both the caption and model levels. Building on these insights, we release CapArena-Auto, an accurate and efficient automated benchmark for detailed captioning, achieving 94.3% correlation with human rankings at just $4 per test. Data and resources will be open-sourced at https://caparena.github.io.

📄 PDF Abstract BibTeX arXiv:2503.12329

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingImage Captioning

Similar Papers 제목 키워드 기반

ReflectCAP: Detailed Image Captioning with Reflective Memory

2026-04-14 · Kyungmin Min, Minbeom Kim, Kang-il Lee, Seunghyun Yoon 외 arxiv

Detailed image captioning demands both factual grounding and fine-grained coverage, yet existing methods have struggled to achieve them simultaneously. We address this tension with Reflective Note-Guided Captioning (Refl…

Image Captioning

BalCapRL: A Balanced Framework for RL-Based MLLM Image Captioning

2026-05-08 · Shaokai Ye, Vasileios Saveris, Yihao Qian, Jiaming Hu 외 arxiv

Image captioning is one of the most fundamental tasks in computer vision. Owing to its open-ended nature, it has received significant attention in the era of multimodal large language models (MLLMs). In pursuit of ever m…

Reinforcement LearningQuestion AnsweringImage Captioning

RubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioning

2026-03-10 · Tzu-Heng Huang, Sirajul Salekin, Javier Movellan, Frederic Sala 외 arxiv

Dense image captioning is critical for cross-modal alignment in vision-language pretraining and text-to-image generation, but scaling expert-quality annotations is prohibitively expensive. While synthetic captioning via …

Text-to-Image GenerationReinforcement LearningImage Captioning

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage

2024-12-20 · Saehyung Lee, Seunghyun Yoon, Trung Bui, Jing Shi 외

Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations. Our analysis reveals that existing hallucination detection methods struggle with detailed captions. …

AttributeBenchmarkingHallucinationImage Captioning+1

Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives

2025-03-18 · Sara Sarto, Marcella Cornia, Rita Cucchiara

The evaluation of machine-generated image captions is a complex and evolving challenge. With the advent of Multimodal Large Language Models (MLLMs), image captioning has become a core task, increasing the need for robust…

Image Captioning