中文
相关论文

相关论文: Incorporating Probing Signals into Multimodal Mach…

200 篇论文

Multimodal machine translation (MMT) aims to improve translation quality by equipping the source sentence with its corresponding image. Despite the promising performance, MMT models still suffer the problem of input degradation: models…

计算机视觉与模式识别 · 计算机科学 2022-10-18 Baijun Ji , Tong Zhang , Yicheng Zou , Bojie Hu , Si Shen

The increasing availability of multimodal data across text, tables, and images presents new challenges for developing models capable of complex cross-modal reasoning. Existing methods for Multimodal Multi-hop Question Answering (MMQA) often…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Qi Zhi Lim , Chin Poo Lee , Kian Ming Lim , Kalaiarasi Sonai Muthu Anbananthen

Recently, there has been a surge in research in multimodal machine translation (MMT), where additional modalities such as images are used to improve translation quality of textual systems. A particular use for such multimodal systems is the…

计算与语言 · 计算机科学 2022-07-07 Veneta Haralampieva , Ozan Caglayan , Lucia Specia

Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the ``pre-training & finetuning'' learning paradigm significantly improves the VQA performance, the adversarial…

计算机视觉与模式识别 · 计算机科学 2024-02-20 Ziyi Yin , Muchao Ye , Tianrong Zhang , Jiaqi Wang , Han Liu , Jinghui Chen , Ting Wang , Fenglong Ma

Multimodal Machine Translation (MMT) focuses on enhancing text-only translation with visual features, which has attracted considerable attention from both natural language processing and computer vision communities. Recent advances still…

计算与语言 · 计算机科学 2022-11-29 Hongcheng Guo , Jiaheng Liu , Haoyang Huang , Jian Yang , Zhoujun Li , Dongdong Zhang , Zheng Cui , Furu Wei

Recent research in the field of multimodal machine translation (MMT) has indicated that the visual modality is either dispensable or offers only marginal advantages. However, most of these conclusions are drawn from the analysis of…

计算与语言 · 计算机科学 2024-04-10 Zi Long , Zhenhao Tang , Xianghua Fu , Jian Chen , Shilong Hou , Jinze Lyu

Multimodal machine translation (MMT) systems have been shown to outperform their text-only neural machine translation (NMT) counterparts when visual context is available. However, recent studies have also shown that the performance of MMT…

计算与语言 · 计算机科学 2021-09-09 Jiaoda Li , Duygu Ataman , Rico Sennrich

A good evaluation framework should evaluate multimodal machine translation (MMT) models by measuring 1) their use of visual information to aid in the translation task and 2) their ability to translate complex sentences such as done for…

计算与语言 · 计算机科学 2024-03-06 Vipin Vijayan , Braeden Bowen , Scott Grigsby , Timothy Anderson , Jeremy Gwinnup

A neural multimodal machine translation (MMT) system is one that aims to perform better translation by extending conventional text-only translation models with multimodal information. Many recent studies report improvements when equipping…

计算与语言 · 计算机科学 2021-06-01 Zhiyong Wu , Lingpeng Kong , Wei Bi , Xiang Li , Ben Kao

Current work on multimodal machine translation (MMT) has suggested that the visual modality is either unnecessary or only marginally beneficial. We posit that this is a consequence of the very simple, short and repetitive sentences used in…

计算与语言 · 计算机科学 2019-06-04 Ozan Caglayan , Pranava Madhyastha , Lucia Specia , Loïc Barrault

Recently, numbers of works shows that the performance of neural machine translation (NMT) can be improved to a certain extent with using visual information. However, most of these conclusions are drawn from the analysis of experimental…

计算机视觉与模式识别 · 计算机科学 2022-09-07 ZhenHao Tang , XiaoBing Zhang , Zi Long , XiangHua Fu

Multimodal machine translation (MMT) aims to improve translation quality by incorporating information from other modalities, such as vision. Previous MMT systems mainly focus on better access and use of visual information and tend to…

计算与语言 · 计算机科学 2023-09-06 Yaoming Zhu , Zewei Sun , Shanbo Cheng , Luyang Huang , Liwei Wu , Mingxuan Wang

Continual Visual Question Answering (CVQA) based on pre-trained models(PTMs) has achieved promising progress by leveraging prompt tuning to enable continual multi-modal learning. However, most existing methods adopt cross-modal prompt…

计算机视觉与模式识别 · 计算机科学 2025-09-12 Xu Li , Fan Lyu

Previous work on multimodal machine translation (MMT) has focused on the way of incorporating vision features into translation but little attention is on the quality of vision models. In this work, we investigate the impact of vision models…

计算与语言 · 计算机科学 2022-03-18 Bei Li , Chuanhao Lv , Zefan Zhou , Tao Zhou , Tong Xiao , Anxiang Ma , JingBo Zhu

While most current work in multimodal machine translation (MMT) uses the Multi30k dataset for training and evaluation, we find that the resulting models overfit to the Multi30k dataset to an extreme degree. Consequently, these models…

计算与语言 · 计算机科学 2024-03-06 Vipin Vijayan , Braeden Bowen , Scott Grigsby , Timothy Anderson , Jeremy Gwinnup

We introduce a novel multimodal machine translation model that utilizes parallel visual and textual information. Our model jointly optimizes the learning of a shared visual-language embedding and a translator. The model leverages a visual…

计算与语言 · 计算机科学 2018-08-29 Mingyang Zhou , Runxiang Cheng , Yong Jae Lee , Zhou Yu

Multimodal Machine Translation (MMT) enriches the source text with visual information for translation. It has gained popularity in recent years, and several pipelines have been proposed in the same direction. Yet, the task lacks quality…

计算与语言 · 计算机科学 2021-06-29 Kshitij Gupta , Devansh Gautam , Radhika Mamidi

Visual question answering (VQA) demands simultaneous comprehension of both the image visual content and natural language questions. In some cases, the reasoning needs the help of common sense or general knowledge which usually appear in the…

计算机视觉与模式识别 · 计算机科学 2018-11-30 Hui Li , Peng Wang , Chunhua Shen , Anton van den Hengel

Visual question answering (VQA) is one of the crucial vision-and-language tasks. Yet, existing VQA research has mostly focused on the English language, due to a lack of suitable evaluation resources. Previous work on cross-lingual VQA has…

计算与语言 · 计算机科学 2023-06-12 Chen Liu , Jonas Pfeiffer , Anna Korhonen , Ivan Vulić , Iryna Gurevych

Visual Question Answering (VQA) is a challenging task of predicting the answer to a question about the content of an image. Prior works directly evaluate the answering models by simply calculating the accuracy of predicted answers. However,…

计算机视觉与模式识别 · 计算机科学 2025-06-11 Kun Li , George Vosselman , Michael Ying Yang
‹ 上一页 1 2 3 10 下一页 ›