中文
相关论文

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

200 篇论文

Massive web datasets play a key role in the success of large vision-language models like CLIP and Flamingo. However, the raw web data is noisy, and existing filtering methods to reduce noise often come at the expense of data diversity. Our…

机器学习 · 计算机科学 2023-10-27 Thao Nguyen , Samir Yitzhak Gadre , Gabriel Ilharco , Sewoong Oh , Ludwig Schmidt

We propose OmniCaptioner, a versatile visual captioning framework for generating fine-grained textual descriptions across a wide variety of visual domains. Unlike prior methods limited to specific image types (e.g., natural images or…

There is an intricate relation between the properties of an image and how humans behave while describing the image. This behavior shows ample variation, as manifested in human signals such as eye movements and when humans start to describe…

计算与语言 · 计算机科学 2024-02-05 Ece Takmaz , Sandro Pezzelle , Raquel Fernández

Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and…

计算机视觉与模式识别 · 计算机科学 2024-05-31 Siddharth Karamcheti , Suraj Nair , Ashwin Balakrishna , Percy Liang , Thomas Kollar , Dorsa Sadigh

Many vision-language models (VLMs) that prove very effective at a range of multimodal task, build on CLIP-based vision encoders, which are known to have various limitations. We investigate the hypothesis that the strong language backbone in…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Sho Takishita , Jay Gala , Abdelrahman Mohamed , Kentaro Inui , Yova Kementchedjhieva

In this paper, we aim to learn associations between visual attributes of fonts and the verbal context of the texts they are typically applied to. Compared to related work leveraging the surrounding visual context, we choose to focus only on…

计算与语言 · 计算机科学 2020-05-05 Amirreza Shirani , Franck Dernoncourt , Jose Echevarria , Paul Asente , Nedim Lipka , Thamar Solorio

The evaluation of machine-generated image captions is a complex and evolving challenge. With the advent of Multimodal Large Language Models (MLLMs), image captioning has become a core task, increasing the need for robust and reliable…

计算机视觉与模式识别 · 计算机科学 2025-06-02 Sara Sarto , Marcella Cornia , Rita Cucchiara

Vision-language models (VLMs) mainly rely on contrastive training to learn general-purpose representations of images and captions. We focus on the situation when one image is associated with several captions, each caption containing both…

计算机视觉与模式识别 · 计算机科学 2024-08-02 Maurits Bleeker , Mariya Hendriksen , Andrew Yates , Maarten de Rijke

Recent advancements in dialogue systems have highlighted the significance of integrating multimodal responses, which enable conveying ideas through diverse modalities rather than solely relying on text-based interactions. This enrichment…

计算与语言 · 计算机科学 2024-07-08 Chang-Sheng Kao , Yun-Nung Chen

Social media's global reach amplifies the spread of information, highlighting the need for robust Natural Language Processing tasks like stance detection across languages and modalities. Prior research predominantly focuses on text-only…

计算与语言 · 计算机科学 2025-01-30 Jake Vasilakes , Carolina Scarton , Zhixue Zhao

Image captioning models have lately shown impressive results when applied to standard datasets. Switching to real-life scenarios, however, constitutes a challenge due to the larger variety of visual concepts which are not covered in…

计算机视觉与模式识别 · 计算机科学 2021-06-04 Marco Cagrandi , Marcella Cornia , Matteo Stefanini , Lorenzo Baraldi , Rita Cucchiara

Image Captioning generates descriptive sentences from images using Vision-Language Pre-trained models (VLPs) such as BLIP, which has improved greatly. However, current methods lack the generation of detailed descriptive captions for the…

计算机视觉与模式识别 · 计算机科学 2025-02-25 Youngsik Yun , Jihie Kim

People's visual experiences of the world are easy to carve up and examine along natural language boundaries, e.g., by category labels, attribute labels, etc. However, it is more difficult to elicit detailed visuospatial information about…

计算机视觉与模式识别 · 计算机科学 2021-04-15 Yiyuan Yang , Kenneth Li , Fernanda Eliott , Maithilee Kunda

Pre-trained language models are still far from human performance in tasks that need understanding of properties (e.g. appearance, measurable quantity) and affordances of everyday objects in the real world since the text lacks such…

计算与语言 · 计算机科学 2022-03-18 Woojeong Jin , Dong-Ho Lee , Chenguang Zhu , Jay Pujara , Xiang Ren

Propelling, and propelled by, the "deep learning revolution", recent years have seen the introduction of ever larger corpora of images annotated with natural language expressions. We survey some of these corpora, taking a perspective that…

计算与语言 · 计算机科学 2019-04-17 David Schlangen

Understanding how the brain represents the multifaceted properties of words in context is essential for explaining the neural architecture of human language. Here, we combine large-scale psycholinguistic modeling with naturalistic fMRI to…

神经元与认知 · 定量生物学 2026-01-21 Xuan Yang , Chuanji Gao , Cheng Xiao , Nicholas Riccardi , Rutvik H. Desai

Modern deep-learning architectures need large amounts of data to produce state-of-the-art results. Annotating such huge datasets is time-consuming, expensive, and prone to human error. Recent advances in self-supervised learning allow us to…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Cherish Puniani , Advika Sinha , Shree Singhi , Aayan Yadav

Humans show language-biased image recognition for a word-embedded image, known as picture-word interference. Such interference depends on hierarchical semantic categories and reflects that human language processing highly interacts with…

计算机视觉与模式识别 · 计算机科学 2022-03-15 Yoann Lemesle , Masataka Sawayama , Guillermo Valle-Perez , Maxime Adolphe , Hélène Sauzéon , Pierre-Yves Oudeyer

Lately, researchers in artificial intelligence have been really interested in how language and vision come together, giving rise to the development of multimodal models that aim to seamlessly integrate textual and visual information.…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Rajat Chawla , Arkajit Datta , Tushar Verma , Adarsh Jha , Anmol Gautam , Ayush Vatsal , Sukrit Chaterjee , Mukunda NS , Ishaan Bhola

News Image Captioning aims to create captions from news articles and images, emphasizing the connection between textual context and visual elements. Recognizing the significance of human faces in news images and the face-name co-occurrence…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Tingyu Qu , Tinne Tuytelaars , Marie-Francine Moens