中文
相关论文

相关论文: SMURF: SeMantic and linguistic UndeRstanding Fusio…

200 篇论文

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 simpler caption…

计算机视觉与模式识别 · 计算机科学 2020-09-10 Zeyu Wang , Berthy Feng , Karthik Narasimhan , Olga Russakovsky

Evaluation metrics for image captioning face two challenges. Firstly, commonly used metrics such as CIDEr, METEOR, ROUGE and BLEU often do not correlate well with human judgments. Secondly, each metric has well known blind spots to…

计算机视觉与模式识别 · 计算机科学 2018-06-19 Yin Cui , Guandao Yang , Andreas Veit , Xun Huang , Serge Belongie

Visual captioning benchmarks have become outdated with the emergence of modern multimodal large language models (MLLMs), as the brief ground-truth sentences and traditional metrics fail to assess detailed captions effectively. While recent…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Zhihang Liu , Chen-Wei Xie , Bin Wen , Feiwu Yu , Jixuan Chen , Pandeng Li , Boqiang Zhang , Nianzu Yang , Yinglu Li , Zuan Gao , Yun Zheng , Hongtao Xie

In image captioning where fluency is an important factor in evaluation, e.g., $n$-gram metrics, sequential models are commonly used; however, sequential models generally result in overgeneralized expressions that lack the details that may…

计算机视觉与模式识别 · 计算机科学 2020-07-14 Junjiao Tian , Jean Oh

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…

计算与语言 · 计算机科学 2022-05-20 Jungo Kasai , Keisuke Sakaguchi , Lavinia Dunagan , Jacob Morrison , Ronan Le Bras , Yejin Choi , Noah A. Smith

Visual captioning aims to generate textual descriptions given images or videos. Traditionally, image captioning models are trained on human annotated datasets such as Flickr30k and MS-COCO, which are limited in size and diversity. This…

计算机视觉与模式识别 · 计算机科学 2021-03-01 Marimuthu Kalimuthu , Aditya Mogadala , Marius Mosbach , Dietrich Klakow

Accuracy and Diversity are two essential metrizable manifestations in generating natural and semantically correct captions. Many efforts have been made to enhance one of them with another decayed due to the trade-off gap. In this work, we…

计算机视觉与模式识别 · 计算机科学 2022-09-22 Longzhen Yang , Yihang Liu , Yitao Peng , Lianghua He

Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success, but suffer from excessive noise.…

计算机视觉与模式识别 · 计算机科学 2024-04-08 Qiying Yu , Quan Sun , Xiaosong Zhang , Yufeng Cui , Fan Zhang , Yue Cao , Xinlong Wang , Jingjing Liu

Recently, the state-of-the-art models for image captioning have overtaken human performance based on the most popular metrics, such as BLEU, METEOR, ROUGE, and CIDEr. Does this mean we have solved the task of image captioning? The above…

计算机视觉与模式识别 · 计算机科学 2019-05-16 Qingzhong Wang , Antoni B. Chan

Story visualization is an under-explored task that falls at the intersection of many important research directions in both computer vision and natural language processing. In this task, given a series of natural language captions which…

计算与语言 · 计算机科学 2021-05-24 Adyasha Maharana , Darryl Hannan , Mohit Bansal

Most existing image captioning evaluation metrics focus on assigning a single numerical score to a caption by comparing it with reference captions. However, these methods do not provide an explanation for the assigned score. Moreover,…

计算机视觉与模式识别 · 计算机科学 2024-06-11 Yebin Lee , Imseong Park , Myungjoo Kang

Effectively aligning with human judgment when evaluating machine-generated image captions represents a complex yet intriguing challenge. Existing evaluation metrics like CIDEr or CLIP-Score fall short in this regard as they do not take into…

计算机视觉与模式识别 · 计算机科学 2024-07-31 Sara Sarto , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

Sarcasm is a type of irony, characterized by an inherent mismatch between the literal interpretation and the intended connotation. Though sarcasm detection in text has been extensively studied, there are situations in which textual input…

计算机视觉与模式识别 · 计算机科学 2024-08-06 Sajal Aggarwal , Ananya Pandey , Dinesh Kumar Vishwakarma

Image captioning has become an essential Vision & Language research task. It is about predicting the most accurate caption given a specific image or video. The research community has achieved impressive results by continuously proposing new…

计算机视觉与模式识别 · 计算机科学 2025-01-28 Guillermo Ruiz , Tania Ramírez , Daniela Moctezuma

Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Gonçalo Gomes , Bruno Martins , Chrysoula Zerva

Image captioning as a multimodal task has drawn much interest in recent years. However, evaluation for this task remains a challenging problem. Existing evaluation metrics focus on surface similarity between a candidate caption and a set of…

计算与语言 · 计算机科学 2019-12-20 Huiyuan Xie , Tom Sherborne , Alexander Kuhnle , Ann Copestake

Video captioning is a popular task that challenges models to describe events in videos using natural language. In this work, we investigate the ability of various visual feature representations derived from state-of-the-art convolutional…

计算机视觉与模式识别 · 计算机科学 2021-01-18 Praveen S , Akhilesh Bharadwaj , Harsh Raj , Janhavi Dadhania , Ganesh Samarth C. A , Nikhil Pareek , S R M Prasanna

Saliency methods are a popular class of feature attribution explanation methods that aim to capture a model's predictive reasoning by identifying "important" pixels in an input image. However, the development and adoption of these methods…

机器学习 · 计算机科学 2022-06-20 Joon Sik Kim , Gregory Plumb , Ameet Talwalkar

Automatic evaluation metrics hold a fundamental importance in the development and fine-grained analysis of captioning systems. While current evaluation metrics tend to achieve an acceptable correlation with human judgements at the system…

人工智能 · 计算机科学 2020-12-25 Naeha Sharif , Lyndon White , Mohammed Bennamoun , Wei Liu , Syed Afaq Ali Shah

Recent advances in large language models and vision-language models have led to growing interest in explainable evaluation metrics for image captioning. However, these metrics generate explanations without standardized criteria, and the…

计算与语言 · 计算机科学 2025-07-01 Hyunjong Kim , Sangyeop Kim , Jongheon Jeong , Yeongjae Cho , Sungzoon Cho
‹ 上一页 1 2 3 10 下一页 ›