Do you hear what I see?

Fine, Ione

doi:10.1038/508461a

Cited by 6 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the metamodal hypothesis has led scientists to look for similarities rather than differences between early-blind and sighted individuals. Examining functional responses using a data-driven approach or selecting stimuli and tasks from a nonsighted perspective may yet reveal overlooked differences in the neural representations of blind and sighted individuals (Fine 2014).…”

Section: Metamodal Plasticitymentioning

confidence: 99%

Blindness and Human Brain Plasticity

Fine

Park

2018

Annu. Rev. Vis. Sci.

Self Cite

View full text Add to dashboard Cite

Early blindness causes fundamental alterations of neural function across more than 25% of cortex-changes that span the gamut from metabolism to behavior and collectively represent one of the most dramatic examples of plasticity in the human brain. The goal of this review is to describe how the remarkable behavioral and neuroanatomical compensations demonstrated by blind individuals provide insights into the extent, mechanisms, and limits of human brain plasticity.

show abstract

Section: Metamodal Plasticitymentioning

confidence: 99%

Blindness and Human Brain Plasticity

Fine

Park

2018

Annu. Rev. Vis. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Nearly one-quarter of the brain is normally devoted to processing visual information, for example, reading text 21. Yet in congenitally blind people, most of the ‘visual’ cortex responds strongly to tactile and auditory input instead of visual stimuli, a phenomenon called cross-modal plasticity.…”

Section: Faces and The Blindmentioning

confidence: 99%

Face transplantation for the blind: more than being blind in a sighted world

Lee

2018

J Med Ethics

View full text Add to dashboard Cite

Face transplantation (FT) is a landmark in reconstructive surgery involving vascularised composite allotransplantation. a recent issue of FT for patients who are blind has arisen. Some bioethicists recommend not excluding a patient who is blind, as this may amount to discrimination. From an ethical standpoint, FT for those with blindness is appropriate in selected candidates. This article seeks to add to the clinical evidence supporting FT for those with blindness by detailing a complementary psychosocial perspective. Currently, there is little relevant research about the subjectivity of the blind. This is critical since the arguments against FT for the blind refer to their inability to see their face and to view the reaction of others to their disfigured faces. We begin with a brief look at examples of FT involving blindness and associated arguments. The next part is a multidisciplinary investigation of the experiences of the blind. These are gleaned from a close reading of the literature and drawing inferences, as direct studies are rare. The discussion analyses identity themes of the blind in relation to their faces: as they experience it; the face they wish to show to the world; and how others perceive and react to their face in a saturated environment of imagery and visual communication. Disability and the blind person's experience of faces are well-founded considerations for medical practitioners and ethics boards in the process of FT decision-making.

show abstract

“…understand the physical world [13]. In the image captioning area, the texts contained in images are also of critical importance and often provide valuable information [5,19,20,34,41] for caption generation.…”

Section: Introductionmentioning

confidence: 99%

“…In this sense, Sidorov et al [40] propose a fine-grained image captioning task, i.e., text-based image captioning (TextCap), aiming to generate image captions that not only 'describe' visual contents but also 'read' the texts in images, such as billboards, road signs, commodity prices and etc. This task is very practical since the fine-grained image captions with rich text information can aid visually impaired people to comprehensively understand their surroundings [13] Some preliminary tries for the TextCap task seek to directly extend existing image captioning methods [2,19,21] to this new setting. However, such methods usually tend to describe prominent visual objects or overall scenes without considering the texts in images.…”

Section: Introductionmentioning

confidence: 99%

Towards Accurate Text-based Image Captioning with Content Diversity Exploration

Niu

Tan

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Text-based image captioning (TextCap) which aims to read and reason images with texts is crucial for a machine to understand a detailed and complex scene environment, considering that texts are omnipresent in daily life. This task, however, is very challenging because an image often contains complex texts and visual information that is hard to be described comprehensively. Existing methods attempt to extend the traditional image captioning methods to solve this task, which focus on describing the overall scene of images by one global caption. This is infeasible because the complex text and visual information cannot be described well within one caption. To resolve this difficulty, we seek to generate multiple captions that accurately describe different parts of an image in detail. To achieve this purpose, there are three key challenges: 1) it is hard to decide which parts of the texts of images to copy or paraphrase; 2) it is non-trivial to capture the complex relationship between diverse texts in an image; 3) how to generate multiple captions with diverse content is still an open problem. To conquer these, we propose a novel Anchor-Captioner method. Specifically, we first find the important tokens which are supposed to be paid more attention to and consider them as anchors. Then, for each chosen anchor, we group its relevant texts to construct the corresponding anchor-centred graph (ACG). Last, based on different ACGs, we conduct the multi-view caption generation to improve the content diversity of generated captions. Experimental results show that our method not only achieves SOTA performance but also generates diverse captions to describe images.

show abstract

Do you hear what I see?

Abstract: Researchers have found evidence that the representation of auditory and tactile information in the brains of blind people shows strong similarities to the way in which visual information is represented in sighted people.

Cited by 6 publications

References 9 publications

Blindness and Human Brain Plasticity

Blindness and Human Brain Plasticity

Face transplantation for the blind: more than being blind in a sighted world

Towards Accurate Text-based Image Captioning with Content Diversity Exploration

Contact Info

Product

Resources

About