paper-with-me

홈 › Papers

ViLBERTScore: Evaluating Image Caption Using Vision-and-Language BERT

2020-11-01 · EMNLP (Eval4NLP) 2020 11 · Hwanhee Lee, Seunghyun Yoon, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Kyomin Jung

In this paper, we propose an evaluation metric for image captioning systems using both image and text information. Unlike the previous methods that rely on textual representations in evaluating the caption, our approach uses visiolinguistic representations. The proposed method generates image-conditioned embeddings for each token using ViLBERT from both generated and reference texts. Then, these contextual embeddings from each of the two sentence-pair are compared to compute the similarity score. Experimental results on three benchmark datasets show that our method correlates significantly better with human judgments than all existing metrics.

📄 PDF Abstract BibTeX

Code (1)

hwanheelee1993/vilbertscore 공식 구현 pytorch

Tasks

Image CaptioningSentence

Similar Papers 제목 키워드 기반

Prompt-Based Caption Generation for Single-Tooth Dental Images Using Vision-Language Models

2026-03-08 · Anastasiia Sukhanova, Aiden Taylor, Julian Myers, Zichun Wang 외 arxiv

Digital dentistry has made significant advances with the advent of deep learning. However, the majority of these deep learning-based dental image analysis models focus on very specific tasks such as tooth segmentation, t…

Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning

2024-02-27 · Maurits Bleeker, Mariya Hendriksen, Andrew Yates, Maarten de Rijke

Vision-language models (VLMs) mainly rely on contrastive training to learn general-purpose representations of images and captions. We focus on the situation when one image is associated with several captions, each captio…

Contrastive LearningRepresentation Learning

"It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models

2025-11-12 · Kapil Garg, Xinru Tang, Jimin Heo, Dwayne R. Morgan 외 arxiv

Vision-Language Models (VLMs) are increasingly used by blind and low-vision (BLV) people to identify and understand products in their everyday lives, such as food, personal care items, and household goods. Despite their …

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

2023-12-14 · CVPR 2024 1 · Jack Urbanek, Florian Bordes, Pietro Astolfi, Mary Williamson 외

Curation methods for massive vision-language datasets trade off between dataset size and quality. However, even the highest quality of available curated captions are far too short to capture the rich visual detail in an …

Image Captioning

UIT-OpenViIC: A Novel Benchmark for Evaluating Image Captioning in Vietnamese

2023-05-07 · Doanh C. Bui, Nghia Hieu Nguyen, Khang Nguyen

Image Captioning is one of the vision-language tasks that still interest the research community worldwide in the 2020s. MS-COCO Caption benchmark is commonly used to evaluate the performance of advanced captioning models…

Image CaptioningVietnamese Image CaptioningVietnamese Multimodal Learning