English
Related papers

Related papers: Crossmodal-3600: A Massively Multilingual Multimod…

200 papers

Image captioning has conventionally relied on reference-based automatic evaluations, where machine captions are compared against captions written by humans. This is in contrast to the reference-free manner in which humans assess caption…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Jack Hessel , Ari Holtzman , Maxwell Forbes , Ronan Le Bras , Yejin Choi

Generating image descriptions in different languages is essential to satisfy users worldwide. However, it is prohibitively expensive to collect large-scale paired image-caption dataset for every target language which is critical for…

Computer Vision and Pattern Recognition · Computer Science 2019-08-16 Yuqing Song , Shizhe Chen , Yida Zhao , Qin Jin

Multimodal large language models (MLLMs) have demonstrated promising results in a variety of tasks that combine vision and language. As these models become more integral to research and applications, conducting comprehensive evaluations of…

Computer Vision and Pattern Recognition · Computer Science 2024-06-06 Fuwen Luo , Chi Chen , Zihao Wan , Zhaolu Kang , Qidong Yan , Yingjie Li , Xiaolong Wang , Siyu Wang , Ziyue Wang , Xiaoyue Mi , Peng Li , Ning Ma , Maosong Sun , Yang Liu

We introduce XED, a multilingual fine-grained emotion dataset. The dataset consists of human-annotated Finnish (25k) and English sentences (30k), as well as projected annotations for 30 additional languages, providing new resources for many…

Computation and Language · Computer Science 2020-11-09 Emily Öhman , Marc Pàmies , Kaisla Kajava , Jörg Tiedemann

Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this…

Computation and Language · Computer Science 2021-09-10 Yiheng Xu , Tengchao Lv , Lei Cui , Guoxin Wang , Yijuan Lu , Dinei Florencio , Cha Zhang , Furu Wei

Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However, their ability to jointly reason over omni-modal (visual, audio, and textual) signals in long and…

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. To show the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Jack Urbanek , Florian Bordes , Pietro Astolfi , Mary Williamson , Vasu Sharma , Adriana Romero-Soriano

Multimodal Large Language Models (MLLMs) struggle with accurately capturing camera-object relations, especially for object orientation, camera viewpoint, and camera shots. This stems from the fact that existing MLLMs are trained on images…

In biomedical vision-language modeling, datasets are typically mined from scientific literature, pairing compound figures with captions that are short, context-dependent, and oftern partially informative. Prior work on subfigure extraction…

Computer Vision and Pattern Recognition · Computer Science 2025-12-08 Negin Baghbanzadeh , Mohammed Saidul Islam , Sajad Ashkezari , Elham Dolatabadi , Arash Afkanpour

We introduce a new large-scale dataset that links the assessment of image quality issues to two practical vision tasks: image captioning and visual question answering. First, we identify for 39,181 images taken by people who are blind…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Tai-Yin Chiu , Yinan Zhao , Danna Gurari

Current conversational recommendation systems focus predominantly on text. However, real-world recommendation settings are generally multimodal, causing a significant gap between existing research and practical applications. To address this…

Multimedia · Computer Science 2025-04-16 Zihan Wang , Xiaocui Yang , Yongkang Liu , Shi Feng , Daling Wang , Yifei Zhang

Multimodal models excel in English, supported by abundant image-text and audio-text data, but performance drops sharply for other languages due to limited multilingual multimodal resources. Existing solutions rely on machine translation,…

Machine Learning · Computer Science 2026-01-22 Piyush Singh Pasi

Multimodal learning has revolutionized general domain tasks, yet its application in scientific discovery is hindered by the profound semantic gap between complex scientific imagery and sparse textual descriptions. We present S1-MMAlign, a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-07 He Wang , Longteng Guo , Pengkang Huo , Xuanxu Lin , Yichen Yuan , Jie Jiang , Jing Liu

Contemporary works on abstractive text summarization have focused primarily on high-resource languages like English, mostly due to the limited availability of datasets for low/mid-resource ones. In this work, we present XL-Sum, a…

Computation and Language · Computer Science 2021-06-29 Tahmid Hasan , Abhik Bhattacharjee , Md Saiful Islam , Kazi Samin , Yuan-Fang Li , Yong-Bin Kang , M. Sohel Rahman , Rifat Shahriyar

Abstractive summarization has enjoyed renewed interest in recent years, thanks to pre-trained language models and the availability of large-scale datasets. Despite promising results, current models still suffer from generating factually…

Computation and Language · Computer Science 2024-01-08 Roee Aharoni , Shashi Narayan , Joshua Maynez , Jonathan Herzig , Elizabeth Clark , Mirella Lapata

Human annotations of mood in music are essential for music generation and recommender systems. However, existing datasets predominantly focus on Western songs with terms derived from English, which may limit generalizability across diverse…

Information Retrieval · Computer Science 2025-10-29 Harin Lee , Elif Çelen , Peter Harrison , Manuel Anglada-Tort , Pol van Rijn , Minsu Park , Marc Schönwiesner , Nori Jacoby

Most vision-and-language pretraining research focuses on English tasks. However, the creation of multilingual multimodal evaluation datasets (e.g. Multi30K, xGQA, XVNLI, and MaRVL) poses a new challenge in finding high-quality training data…

Computation and Language · Computer Science 2022-10-25 Chen Qiu , Dan Oneata , Emanuele Bugliarello , Stella Frank , Desmond Elliott

State-of-the-art natural language processing systems rely on supervision in the form of annotated data to learn competent models. These models are generally trained on data in a single language (usually English), and cannot be directly used…

Computation and Language · Computer Science 2018-09-14 Alexis Conneau , Guillaume Lample , Ruty Rinott , Adina Williams , Samuel R. Bowman , Holger Schwenk , Veselin Stoyanov

Web-scale training on paired text-image data is becoming increasingly central to multimodal learning, but is challenged by the highly noisy nature of datasets in the wild. Standard data filtering approaches succeed in removing mismatched…

Machine Learning · Computer Science 2025-08-13 Moran Yanuka , Morris Alper , Hadar Averbuch-Elor , Raja Giryes

Rare word representation has recently enjoyed a surge of interest, owing to the crucial role that effective handling of infrequent words can play in accurate semantic understanding. However, there is a paucity of reliable benchmarks for…

Computation and Language · Computer Science 2018-08-29 Mohammad Taher Pilehvar , Dimitri Kartsaklis , Victor Prokhorov , Nigel Collier