English
Related papers

Related papers: Large-scale representation learning from visually …

200 papers

Multimodal automatic speech recognition systems integrate information from images to improve speech recognition quality, by grounding the speech in the visual context. While visual signals have been shown to be useful for recovering…

Computation and Language · Computer Science 2020-10-07 Tejas Srinivasan , Ramon Sanabria , Florian Metze , Desmond Elliott

There is growing interest in models that can learn from unlabelled speech paired with visual context. This setting is relevant for low-resource speech processing, robotics, and human language acquisition research. Here we study how a…

Computation and Language · Computer Science 2018-11-02 Herman Kamper , Gregory Shakhnarovich , Karen Livescu

During language acquisition, infants have the benefit of visual cues to ground spoken language. Robots similarly have access to audio and visual sensors. Recent work has shown that images and spoken captions can be mapped into a meaningful…

Computation and Language · Computer Science 2017-05-29 Herman Kamper , Shane Settle , Gregory Shakhnarovich , Karen Livescu

Humans learn language by interaction with their environment and listening to other humans. It should also be possible for computational models to learn language directly from speech but so far most approaches require text. We improve on…

Computation and Language · Computer Science 2019-09-25 Danny Merkx , Stefan L. Frank , Mirjam Ernestus

The goal of audio captioning is to translate input audio into its description using natural language. One of the problems in audio captioning is the lack of training data due to the difficulty in collecting audio-caption pairs by crawling…

Audio and Speech Processing · Electrical Eng. & Systems 2020-12-15 Yuma Koizumi , Yasunori Ohishi , Daisuke Niizumi , Daiki Takeuchi , Masahiro Yasuda

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…

Computation and Language · Computer Science 2019-09-25 Danny Merkx , Stefan Frank

In this paper, we propose Language-Guided Contrastive Audio-Visual Masked Autoencoders (LG-CAV-MAE) to improve audio-visual representation learning. LG-CAV-MAE integrates a pretrained text encoder into contrastive audio-visual masked…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Yuchi Ishikawa , Shota Nakada , Hokuto Munakata , Kazuhiro Saito , Tatsuya Komatsu , Yoshimitsu Aoki

Speech is understood better by using visual context; for this reason, there have been many attempts to use images to adapt automatic speech recognition (ASR) systems. Current work, however, has shown that visually adapted ASR models only…

Computation and Language · Computer Science 2020-02-19 Tejas Srinivasan , Ramon Sanabria , Florian Metze

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Chao Jia , Yinfei Yang , Ye Xia , Yi-Ting Chen , Zarana Parekh , Hieu Pham , Quoc V. Le , Yunhsuan Sung , Zhen Li , Tom Duerig

Recently, the AI community has made significant strides in developing powerful foundation models, driven by large-scale multimodal datasets. However, for audio representation learning, existing datasets suffer from limitations in the…

Sound · Computer Science 2024-09-10 Luoyi Sun , Xuenan Xu , Mengyue Wu , Weidi Xie

Recent work has highlighted the advantage of jointly learning grounded sentence representations from multiple languages. However, the data used in these studies has been limited to an aligned scenario: the same images annotated with…

Computation and Language · Computer Science 2019-11-12 Ákos Kádár , Grzegorz Chrupała , Afra Alishahi , Desmond Elliott

While deep-learning models have been shown to perform well on image-to-text datasets, it is difficult to use them in practice for captioning images. This is because captions traditionally tend to be context-dependent and offer complementary…

Machine Learning · Computer Science 2023-06-07 Shinjini Ghosh , Sagnik Anupam

Speech-based image retrieval has been studied as a proxy for joint representation learning, usually without emphasis on retrieval itself. As such, it is unclear how well speech-based retrieval can work in practice -- both in an absolute…

Computation and Language · Computer Science 2021-06-16 Ramon Sanabria , Austin Waters , Jason Baldridge

In this paper we present the first model for directly synthesizing fluent, natural-sounding spoken audio captions for images that does not require natural language text as an intermediate representation or source of supervision. Instead, we…

Computation and Language · Computer Science 2021-01-01 Wei-Ning Hsu , David Harwath , Christopher Song , James Glass

Visually grounded speech systems learn from paired images and their spoken captions. Recently, there have been attempts to utilize the visually grounded models trained from images and their corresponding text captions, such as CLIP, to…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-12 Saurabhchand Bhati , Jesús Villalba , Laureano Moro-Velazquez , Thomas Thebaud , Najim Dehak

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…

Computer Vision and Pattern Recognition · Computer Science 2016-02-22 Hao Fang , Saurabh Gupta , Forrest Iandola , Rupesh Srivastava , Li Deng , Piotr Dollár , Jianfeng Gao , Xiaodong He , Margaret Mitchell , John C. Platt , C. Lawrence Zitnick , Geoffrey Zweig

Visual captioning aims to generate textual descriptions given images or videos. Traditionally, image captioning models are trained on human annotated datasets such as Flickr30k and MS-COCO, which are limited in size and diversity. This…

Computer Vision and Pattern Recognition · Computer Science 2021-03-01 Marimuthu Kalimuthu , Aditya Mogadala , Marius Mosbach , Dietrich Klakow

Recent work has shown that speech paired with images can be used to learn semantically meaningful speech representations even without any textual supervision. In real-world low-resource settings, however, we often have access to some…

Computation and Language · Computer Science 2019-09-04 Ankita Pasad , Bowen Shi , Herman Kamper , Karen Livescu

Grounding-based vision and language models have been successfully applied to low-level vision tasks, aiming to precisely locate objects referred in captions. The effectiveness of grounding representation learning heavily relies on the scale…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Jingru Yi , Burak Uzkent , Oana Ignat , Zili Li , Amanmeet Garg , Xiang Yu , Linda Liu

Learning to understand grounded language, which connects natural language to percepts, is a critical research area. Prior work in grounded language acquisition has focused primarily on textual inputs. In this work we demonstrate the…

Computation and Language · Computer Science 2021-12-28 Gaoussou Youssouf Kebe , Luke E. Richards , Edward Raff , Francis Ferraro , Cynthia Matuszek
‹ Prev 1 2 3 10 Next ›