中文
相关论文

相关论文: A Large-Scale Multilingual Study of Visual Constra…

200 篇论文

Vision and language are two fundamental capabilities of human intelligence. Humans routinely perform tasks through the interactions between vision and language, supporting the uniquely human capacity to talk about what they see or…

计算机视觉与模式识别 · 计算机科学 2020-04-01 Tao Mei , Wei Zhang , Ting Yao

In recent years, a substantial body of work in visually grounded natural language processing has focused on real-life multimodal scenarios such as describing content depicted in images or videos. However, comparatively less attention has…

计算与语言 · 计算机科学 2025-08-21 Aditya K Surikuchi , Raquel Fernández , Sandro Pezzelle

Image captioning models are becoming increasingly successful at describing the content of images in restricted domains. However, if these models are to function in the wild - for example, as assistants for people with impaired vision - a…

计算机视觉与模式识别 · 计算机科学 2018-11-29 Peter Anderson , Stephen Gould , Mark Johnson

When we experience a visual stimulus as beautiful, how much of that experience derives from perceptual computations we cannot describe versus conceptual knowledge we can readily translate into natural language? Disentangling perception from…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Colin Conwell , Christopher Hamblin , Chelsea Boccagno , David Mayo , Jesse Cummings , Leyla Isik , Andrei Barbu

Visual imagery does not consist of solitary objects, but instead reflects the composition of a multitude of fluid concepts. While there have been great advances in visual representation learning, such advances have focused on building…

计算机视觉与模式识别 · 计算机科学 2025-04-07 Austin Stone , Hagen Soltau , Robert Geirhos , Xi Yi , Ye Xia , Bingyi Cao , Kaifeng Chen , Abhijit Ogale , Jonathon Shlens

Describing images with text is a fundamental problem in vision-language research. Current studies in this domain mostly focus on single image captioning. However, in various real applications (e.g., image editing, difference interpretation,…

计算与语言 · 计算机科学 2019-06-20 Hao Tan , Franck Dernoncourt , Zhe Lin , Trung Bui , Mohit Bansal

By describing the features and abstractions of our world, language is a crucial tool for human learning and a promising source of supervision for machine learning models. We use language to improve few-shot visual classification in the…

计算机视觉与模式识别 · 计算机科学 2020-06-11 Jesse Mu , Percy Liang , Noah Goodman

Multilingual vision-language models (VLMs) promise universal image-text retrieval, yet their social biases remain underexplored. We perform the first systematic audit of four public multilingual CLIP variants: M-CLIP, NLLB-CLIP,…

计算与语言 · 计算机科学 2025-11-20 Zahraa Al Sahili , Ioannis Patras , Matthew Purver

Humans can effortlessly describe what they see, yet establishing a shared representational format between vision and language remains a significant challenge. Emerging evidence suggests that human brain representations in both vision and…

神经元与认知 · 定量生物学 2025-07-30 Katerina Marie Simkova , Adrien Doerig , Clayton Hickey , Ian Charest

The impact of culture in visual emotion perception has recently captured the attention of multimedia research. In this study, we pro- vide powerful computational linguistics tools to explore, retrieve and browse a dataset of 16K…

计算与语言 · 计算机科学 2016-06-09 Nikolaos Pappas , Miriam Redi , Mercan Topkara , Brendan Jou , Hongyi Liu , Tao Chen , Shih-Fu Chang

Understanding the functional organization of higher visual cortex is a central focus in neuroscience. Past studies have primarily mapped the visual and semantic selectivity of neural populations using hand-selected stimuli, which may…

机器学习 · 计算机科学 2024-05-06 Andrew F. Luo , Margaret M. Henderson , Michael J. Tarr , Leila Wehbe

Image captioning involves generating textual descriptions from input images, bridging the gap between computer vision and natural language processing. Recent advancements in transformer-based models have significantly improved caption…

计算机视觉与模式识别 · 计算机科学 2025-06-09 Israa A. Albadarneh , Bassam H. Hammo , Omar S. Al-Kadi

Cross-lingual representation learning is an important step in making NLP scale to all the world's languages. Recent work on bilingual lexicon induction suggests that it is possible to learn cross-lingual representations of words based on…

计算与语言 · 计算机科学 2017-09-19 Mareike Hartmann , Anders Soegaard

An image captioning model flexibly switching its language pattern, e.g., descriptiveness and length, should be useful since it can be applied to diverse applications. However, despite the dramatic improvement in generative vision-language…

计算机视觉与模式识别 · 计算机科学 2025-07-03 Kuniaki Saito , Donghyun Kim , Kwanyong Park , Atsushi Hashimoto , Yoshitaka Ushiku

Most multilingual vision-and-language (V&L) research aims to accomplish multilingual and multimodal capabilities within one model. However, the scarcity of multilingual captions for images has hindered the development. To overcome this…

计算与语言 · 计算机科学 2024-02-06 Guojun Wu

Recent work has documented striking heterogeneity in the performance of state-of-the-art vision language models (VLMs), including both multimodal language models and text-to-image models. These models are able to describe and generate a…

Language-image pre-training largely relies on how precisely and thoroughly a text describes its paired image. In practice, however, the contents of an image can be so rich that well describing them requires lengthy captions (e.g., with 10…

计算机视觉与模式识别 · 计算机科学 2024-03-26 Kecheng Zheng , Yifei Zhang , Wei Wu , Fan Lu , Shuailei Ma , Xin Jin , Wei Chen , Yujun Shen

Automatically generating descriptive captions for images is a well-researched area in computer vision. However, existing evaluation approaches focus on measuring the similarity between two sentences disregarding fine-grained semantics of…

计算机视觉与模式识别 · 计算机科学 2019-08-07 Philipp Harzig , Dan Zecha , Rainer Lienhart , Carolin Kaiser , René Schallner

Recent studies show that deep vision-only and language-only models--trained on disjoint modalities--nonetheless project their inputs into a partially aligned representational space. Yet we still lack a clear picture of where in each network…

计算机视觉与模式识别 · 计算机科学 2025-09-26 Zoe Wanying He , Sean Trott , Meenakshi Khosla

We introduce EXAMS-V, a new challenging multi-discipline multimodal multilingual exam benchmark for evaluating vision language models. It consists of 20,932 multiple-choice questions across 20 school disciplines covering natural science,…