paper-with-me

Papers

Transparent Human Evaluation for Image Captioning

2021-11-17 · NAACL 2022 7 · Jungo Kasai, Keisuke Sakaguchi, Lavinia Dunagan, Jacob Morrison, Ronan Le Bras, Yejin Choi, Noah A. Smith

We establish THumB, a rubric-based human evaluation protocol for image captioning models. Our scoring rubrics and their definitions are carefully developed based on machine- and human-generated captions on the MSCOCO dataset. Each caption is evaluated along two main dimensions in a tradeoff (precision and recall) as well as other aspects that measure the text quality (fluency, conciseness, and inclusive language). Our evaluations demonstrate several critical problems of the current evaluation practice. Human-generated captions show substantially higher quality than machine-generated ones, especially in coverage of salient information (i.e., recall), while most automatic metrics say the opposite. Our rubric-based results reveal that CLIPScore, a recent metric that uses image features, better correlates with human judgments than conventional text-only metrics because it is more sensitive to recall. We hope that this work will promote a more transparent evaluation protocol for image captioning and its automatic metrics.

📄 PDF Abstract BibTeX arXiv:2111.08940

Code (2)

jungokasai/thumb 공식 구현
jungokasai/billboard

Tasks

Image Captioning

Similar Papers 제목 키워드 기반

Transparent Human Evaluation for Image Captioning

2022-01-16 · ACL ARR January 2022 1 · Anonymous

We establish a rubric-based human evaluation protocol for image captioning models. Our scoring rubrics and their definitions are carefully developed based on machine- and human-generated captions on the MSCOCO dataset. E…

Image Captioning

G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4o

2024-12-18 · Tony Cheng Tong, Sirui He, Zhiwen Shao, Dit-yan Yeung

Evaluation metric of visual captioning is important yet not thoroughly explored. Traditional metrics like BLEU, METEOR, CIDEr, and ROUGE often miss semantic depth, while trained metrics such as CLIP-Score, PAC-S, and Pol…

Image CaptioningVideo Captioning

Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy and Novel Ensemble Method

2024-08-09 · Uri Berger, Gabriel Stanovsky, Omri Abend, Lea Frermann

The task of image captioning has recently been gaining popularity, and with it the complex task of evaluating the quality of image captioning models. In this work, we present the first survey and taxonomy of over 70 diff…

DiversityImage Captioning

BEV-LLM: Leveraging Multimodal BEV Maps for Scene Captioning in Autonomous Driving

2025-07-25 · Felix Brandstaetter, Erik Schuetz, Katharina Winter, Fabian Flohr arxiv

Autonomous driving technology has the potential to transform transportation, but its wide adoption depends on the development of interpretable and transparent decision-making systems. Scene captioning, which generates na…

Autonomous DrivingPoint Clouds

Polos: Multimodal Metric Learning from Human Feedback for Image Captioning

2024-02-28 · CVPR 2024 1 · Yuiga Wada, Kanta Kaneda, Daichi Saito, Komei Sugiura

Establishing an automatic evaluation metric that closely aligns with human judgments is essential for effectively developing image captioning models. Recent data-driven metrics have demonstrated a stronger correlation wi…

Contrastive LearningImage CaptioningMetric Learning