中文
相关论文

相关论文: Quantifying the visual concreteness of words and t…

200 篇论文

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…

机器学习 · 计算机科学 2025-08-13 Moran Yanuka , Morris Alper , Hadar Averbuch-Elor , Raja Giryes

The notions of concreteness and imageability, traditionally important in psycholinguistics, are gaining significance in semantic-oriented natural language processing tasks. In this paper we investigate the predictability of these two…

计算与语言 · 计算机科学 2022-09-15 Nikola Ljubešić , Darja Fišer , Anita Peti-Stantić

Understanding and manipulating concrete and abstract concepts is fundamental to human intelligence. Yet, they remain challenging for artificial agents. This paper introduces a multimodal generative approach to high order abstract concept…

计算与语言 · 计算机科学 2024-10-04 Haodong Xie , Rahul Singh Maharjan , Federico Tavella , Angelo Cangelosi

Representing the semantics of words is a long-standing problem for the natural language processing community. Most methods compute word semantics given their textual context in large corpora. More recently, researchers attempted to…

计算与语言 · 计算机科学 2017-11-10 Éloi Zablocki , Benjamin Piwowarski , Laure Soulier , Patrick Gallinari

Two modalities are often used to convey information in a complementary and beneficial manner, e.g., in online news, videos, educational resources, or scientific publications. The automatic understanding of semantic correlations between text…

多媒体 · 计算机科学 2019-06-21 Christian Otto , Matthias Springstein , Avishek Anand , Ralph Ewerth

The challenge of visual grounding and masking in multimodal machine translation (MMT) systems has encouraged varying approaches to the detection and selection of visually-grounded text tokens for masking. We introduce new methods for…

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

Visual inputs are often assumed to improve language understanding in multimodal models. We examine this assumption by asking whether vision-language models (VLMs) can distinguish useful visual evidence from incidental image context in…

计算与语言 · 计算机科学 2026-05-27 Yifan Jiang , Ruoxi Ning , Sheng Yao , Freda Shi

The combination of visual and textual representations has produced excellent results in tasks such as image captioning and visual question answering, but the inference capabilities of multimodal representations are largely untested. In the…

计算与语言 · 计算机科学 2020-04-07 Oier Lopez de Lacalle , Ander Salaberria , Aitor Soroa , Gorka Azkune , Eneko Agirre

Current approaches to learning semantic representations of sentences often use prior word-level knowledge. The current study aims to leverage visual information in order to capture sentence level semantics without the need for word…

计算与语言 · 计算机科学 2019-09-25 Danny Merkx , Stefan Frank

This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image captions. We use multiple instance learning to…

The visual representation of a concept varies significantly depending on its meaning and the context where it occurs; this poses multiple challenges both for vision and multimodal models. Our study focuses on concreteness, a well-researched…

计算与语言 · 计算机科学 2024-10-16 Tarun Tater , Sabine Schulte im Walde , Diego Frassinelli

Nowadays, as cameras are rapidly adopted in our daily routine, images of documents are becoming both abundant and prevalent. Unlike natural images that capture physical objects, document-images contain a significant amount of text with…

计算机视觉与模式识别 · 计算机科学 2021-03-19 Or Perel , Oron Anschel , Omri Ben-Eliezer , Shai Mazor , Hadar Averbuch-Elor

Lexical Semantics is concerned with how words encode mental representations of the world, i.e., concepts . We call this type of concepts, classification concepts . In this paper, we focus on Visual Semantics , namely on how humans build…

人工智能 · 计算机科学 2021-09-15 Fausto Giunchiglia , Luca Erculiani , Andrea Passerini

We introduce a new multi-modal task for computer systems, posed as a combined vision-language comprehension challenge: identifying the most suitable text describing a scene, given several similar options. Accomplishing the task entails…

计算与语言 · 计算机科学 2016-12-26 Nan Ding , Sebastian Goodman , Fei Sha , Radu Soricut

In Multimodal Neural Machine Translation (MNMT), a neural model generates a translated sentence that describes an image, given the image itself and one source descriptions in English. This is considered as the multimodal image caption…

计算与语言 · 计算机科学 2018-06-01 Jean-Benoit Delbrouck , Stéphane Dupont , Omar Seddati

Semantic embeddings have advanced the state of the art for countless natural language processing tasks, and various extensions to multimodal domains, such as visual-semantic embeddings, have been proposed. While the power of visual-semantic…

机器学习 · 计算机科学 2021-02-23 Adam Dahlgren Lindström , Suna Bensch , Johanna Björklund , Frank Drewes

End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of…

计算机视觉与模式识别 · 计算机科学 2017-05-25 Lluis Gomez , Yash Patel , Marçal Rusiñol , Dimosthenis Karatzas , C. V. Jawahar

Multilingual (or cross-lingual) embeddings represent several languages in a unique vector space. Using a common embedding space enables for a shared semantic between words from different languages. In this paper, we propose to embed images…

计算机视觉与模式识别 · 计算机科学 2019-05-15 Maxime Portaz , Hicham Randrianarivo , Adrien Nivaggioli , Estelle Maudet , Christophe Servan , Sylvain Peyronnet

Integrating visual and linguistic information into a single multimodal representation is an unsolved problem with wide-reaching applications to both natural language processing and computer vision. In this paper, we present a simple method…

机器学习 · 统计学 2017-03-28 Guillem Collell , Teddy Zhang , Marie-Francine Moens

Language grounding aims at linking the symbolic representation of language (e.g., words) into the rich perceptual knowledge of the outside world. The general approach is to embed both textual and visual information into a common space -the…

计算与语言 · 计算机科学 2021-09-15 Hassan Shahmohammadi , Hendrik P. A. Lensch , R. Harald Baayen
‹ 上一页 1 2 3 10 下一页 ›