The Impact of Low Vision on Touch-Gesture Articulation on Mobile Devices

Vatavu, Radu-Daniel; Gheran, Bogdan-Florin; Schipor, Maria Doina

doi:10.1109/mprv.2018.011591059

Cited by 19 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…4.1.10 Vision. Datasets under this group (a total of 11) typically include people who are blind [14,24] (6) or have low vision [165]. When datasets are collected with real-world assistive applications, where disability status as well as visual acuity or age of onset are not known, the umbrella term, "people with visual impairments" or "visually impaired" is used to describe those contributing data (e.g.…”

Section: Communities Of Focusmentioning

confidence: 99%

“…[92]). Datasets are typically collected in the context of accessibility such as navigation [65], object recognition [154], and accessibility of web or touchscreen interfaces [24,165]. There is one exception, where the context is clinical, focusing on screening of Proliferative Diabetic Retinopathy based on retina images [84].…”

Section: Communities Of Focusmentioning

confidence: 99%

“…The strategy of direct download was also common among datasets sourced from people who are blind or have low vision (7). They were similarly hosted on personal/project websites sharing their photos (e.g., [76]), touchscreen gestures (e.g., [165]), and walking patterns (e.g., [65]).…”

Section: Data Sharing Practicesmentioning

confidence: 99%

See 2 more Smart Citations

Sharing Practices for Datasets Related to Accessibility and Aging

Kamikubo

Dwivedi

Kacorri

2021

Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility

View full text Add to dashboard Cite

Datasets sourced from people with disabilities and older adults play an important role in innovation, benchmarking, and mitigating bias for both assistive and inclusive AI-infused applications. However, they are scarce. We conduct a systematic review of 137 accessibility datasets manually located across different disciplines over the last 35 years. Our analysis highlights how researchers navigate tensions between benefits and risks in data collection and sharing. We uncover patterns in data collection purpose, terminology, sample size, data types, and data sharing practices across communities of focus. We conclude by critically reflecting on challenges and opportunities related to locating and sharing accessibility datasets calling for technical, legal, and institutional privacy frameworks that are more attuned to concerns from these communities. CCS CONCEPTS• Human-centered computing → Human computer interaction (HCI); Accessibility; • Security and privacy → Human and societal aspects of security and privacy.

show abstract

Section: Communities Of Focusmentioning

confidence: 99%

Section: Communities Of Focusmentioning

confidence: 99%

See 1 more Smart Citation

Sharing Practices for Datasets Related to Accessibility and Aging

Kamikubo

Dwivedi

Kacorri

2021

Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility

View full text Add to dashboard Cite

show abstract

“…For example, letter "E" could present users with an edge-enhanced view of the physical reality, and letter "C" would activate color enhancement. However, it is known that people with low vision produce stroke gestures that exhibit larger variations in terms of the Length-Error and Bending-Error features [98] compared to people without visual impairments [102], which reflect negatively in the accuracy rates of gesture recognizers. Our practitioner would like to know how large this variation is for the particular symbols "E" and "C" chosen for implementation in their user interface and wearable prototype.…”

Section: Motivating Examplesmentioning

confidence: 99%

Omnis Prædictio: Estimating the full spectrum of human performance with stroke gestures

Leiva¹,

Vatavu²,

Martín-Albo³

et al. 2020

International Journal of Human-Computer Studies

Self Cite

View full text Add to dashboard Cite

Designing effective, usable, and widely adoptable stroke gesture commands for graphical user interfaces is a challenging task that traditionally involves multiple iterative rounds of prototyping, implementation, and follow-up user studies and controlled experiments for evaluation, verification, and validation. An alternative approach is to employ theoretical models of human performance, which can deliver practitioners with insightful information right from the earliest stages of user interface design. However, very few aspects of the large spectrum of human performance with stroke gesture input have been investigated and modeled so far, leaving researchers and practitioners of gesture-based user interface design with a very narrow range of predictable measures of human performance, mostly focused on estimating production time, of which extremely few cases delivered accompanying software tools to assist modeling. We address this problem by introducing "Omnis Praedictio" (Omnis for short), a generic technique and companion web tool that provides accurate user-independent estimations of any numerical stroke gesture feature, including custom features specified in code. Our experimental results on three public datasets show that our model estimations correlate on average r s > .9 with groundtruth data. Omnis also enables researchers and practitioners to understand human performance with stroke gestures on many levels and, consequently, raises the bar for human performance models and estimation techniques for stroke gesture input.

show abstract

“…Moreover, they lack consistent descriptions and require manual screening. We believe that this repository does not only contribute to transparency but also moves us a step Figure 1: Examples of datasets generated by people with disability including from left to right photos taken by blind people [11] sign language videos and annotations [4,19] stroke gestures by people with low vision [31], mobility app logs from people with visual impairments [17], audio recording from people with dysphonia [3], and text written by people with dyslexia [25].…”

mentioning

confidence: 99%

IncluSet: A Data Surfacing Repository for Accessibility Datasets

Kacorri

Dwivedi

Amancherla

et al. 2020

Proceedings of the 22nd International ACM SIGACCESS Conference on Computers and Accessibility

View full text Add to dashboard Cite

Datasets and data sharing play an important role for innovation, benchmarking, mitigating bias, and understanding the complexity of real world AI-infused applications. However, there is a scarcity of available data generated by people with disabilities with the potential for training or evaluating machine learning models. This is partially due to smaller populations, disparate characteristics, lack of expertise for data annotation, as well as privacy concerns. Even when data are collected and are publicly available, it is often difcult to locate them. We present a novel data surfacing repository, called IncluSet, that allows researchers and the disability community to discover and link accessibility datasets. The repository is pre-populated with information about 139 existing datasets: 65 made publicly available, 25 available upon request, and 49 not shared by the authors but described in their manuscripts. More importantly, IncluSet is designed to expose existing and new dataset contributions so they may be discoverable through Google Dataset Search.

show abstract

The Impact of Low Vision on Touch-Gesture Articulation on Mobile Devices

Cited by 19 publications

References 18 publications

Sharing Practices for Datasets Related to Accessibility and Aging

Sharing Practices for Datasets Related to Accessibility and Aging

Omnis Prædictio: Estimating the full spectrum of human performance with stroke gestures

IncluSet: A Data Surfacing Repository for Accessibility Datasets

Contact Info

Product

Resources

About