paper-with-me

Papers

SPICE: Semantic Propositional Image Caption Evaluation

2016-07-29 · Peter Anderson, Basura Fernando, Mark Johnson, Stephen Gould

There is considerable interest in the task of automatically generating image captions. However, evaluation is challenging. Existing automatic evaluation metrics are primarily sensitive to n-gram overlap, which is neither necessary nor sufficient for the task of simulating human judgment. We hypothesize that semantic propositional content is an important component of human caption evaluation, and propose a new automated caption evaluation metric defined over scene graphs coined SPICE. Extensive evaluations across a range of models and datasets indicate that SPICE captures human judgments over model-generated captions better than other automatic metrics (e.g., system-level correlation of 0.88 with human judgments on the MS COCO dataset, versus 0.43 for CIDEr and 0.53 for METEOR). Furthermore, SPICE can answer questions such as which caption-generator best understands colors?' and can caption-generators count?'

📄 PDF Abstract BibTeX arXiv:1607.08822

Code (11)

peteanderson80/SPICE 공식 구현
QQQiwi/coursepaper-2year tf
gabrielsantosrv/coco-caption pytorch
jmhessel/pycocoevalcap pytorch
luoweizhou/coco-caption
lvapeab/coco-caption
mtanti/coco-caption
ruotianluo/coco-caption pytorch
salaniz/pycocoevalcap
shao-chi/ImageCaption pytorch
tylin/coco-caption

Tasks

Image Captioning

Similar Papers 제목 키워드 기반

An Ensemble Model with Attention Based Mechanism for Image Captioning

2025-01-22 · Israa Al Badarneh, Bassam Hammo, Omar Al-Kadi

Image captioning creates informative text from an input image by creating a relationship between the words and the actual content of an image. Recently, deep learning models that utilize transformers have been the most s…

Ensemble LearningImage Captioning

Towards Unique and Informative Captioning of Images

2020-09-08 · ECCV 2020 8 · Zeyu Wang, Berthy Feng, Karthik Narasimhan, Olga Russakovsky

Despite considerable progress, state of the art image captioning models produce generic captions, leaving out important image details. Furthermore, these systems may even misrepresent the image in order to produce a simp…

DiversityImage CaptioningRe-Ranking

Improved Image Captioning via Policy Gradient optimization of SPIDEr

2016-12-01 · ICCV 2017 10 · Si-Qi Liu, Zhenhai Zhu, Ning Ye, Sergio Guadarrama 외

Current image captioning methods are usually trained via (penalized) maximum likelihood estimation. However, the log-likelihood score of a caption does not correlate well with human assessments of quality. Standard synta…

Image Captioning

JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models

2023-11-07 · Yuiga Wada, Kanta Kaneda, Komei Sugiura

Image captioning studies heavily rely on automatic evaluation metrics such as BLEU and METEOR. However, such n-gram-based metrics have been shown to correlate poorly with human evaluation, leading to the proposal of alte…

Image Captioning

Technical Report of NICE Challenge at CVPR 2024: Caption Re-ranking Evaluation Using Ensembled CLIP and Consensus Scores

2024-05-02 · Kiyoon Jeong, Woojun Lee, Woongchan Nam, Minjeong Ma 외

This report presents the ECO (Ensembled Clip score and cOnsensus score) pipeline from team DSBA LAB, which is a new framework used to evaluate and rank captions for a given image. ECO selects the most accurate caption de…

Image CaptioningRe-Ranking