FSboard: Over 3 million characters of ASL fingerspelling collected via smartphones Article Swipe
Manfred Georg
,
Garrett Tanzer
,
Saad S. M. Hassan
,
Maximus Shengelia
,
Esha Uboweja
,
Sam Sepah
,
S. M. Forbes
,
Thad Starner
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2407.15806
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2407.15806
Progress in machine understanding of sign languages has been slow and hampered by limited data. In this paper, we present FSboard, an American Sign Language fingerspelling dataset situated in a mobile text entry use case, collected from 147 paid and consenting Deaf signers using Pixel 4A selfie cameras in a variety of environments. Fingerspelling recognition is an incomplete solution that is only one small part of sign language translation, but it could provide some immediate benefit to Deaf/Hard of Hearing signers as more broadly capable technology develops. At >3 million characters in length and >250 hours in duration, FSboard is the largest fingerspelling recognition dataset to date by a factor of >10x. As a simple baseline, we finetune 30 Hz MediaPipe Holistic landmark inputs into ByT5-Small and achieve 11.1% Character Error Rate (CER) on a test set with unique phrases and signers. This quality degrades gracefully when decreasing frame rate and excluding face/body landmarks: plausible optimizations to help models run on device in real time.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2407.15806
- https://arxiv.org/pdf/2407.15806
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4406073424
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4406073424Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2407.15806Digital Object Identifier
- Title
-
FSboard: Over 3 million characters of ASL fingerspelling collected via smartphonesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-07-22Full publication date if available
- Authors
-
Manfred Georg, Garrett Tanzer, Saad S. M. Hassan, Maximus Shengelia, Esha Uboweja, Sam Sepah, S. M. Forbes, Thad StarnerList of authors in order
- Landing page
-
https://arxiv.org/abs/2407.15806Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2407.15806Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2407.15806Direct OA link when available
- Concepts
-
American Sign Language, Computer science, Natural language processing, Sign language, Linguistics, PhilosophyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4406073424 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2407.15806 |
| ids.doi | https://doi.org/10.48550/arxiv.2407.15806 |
| ids.openalex | https://openalex.org/W4406073424 |
| fwci | |
| type | preprint |
| title | FSboard: Over 3 million characters of ASL fingerspelling collected via smartphones |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11285 |
| topics[0].field.id | https://openalex.org/fields/32 |
| topics[0].field.display_name | Psychology |
| topics[0].score | 0.9821000099182129 |
| topics[0].domain.id | https://openalex.org/domains/2 |
| topics[0].domain.display_name | Social Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3204 |
| topics[0].subfield.display_name | Developmental and Educational Psychology |
| topics[0].display_name | Hearing Impairment and Communication |
| topics[1].id | https://openalex.org/T12151 |
| topics[1].field.id | https://openalex.org/fields/36 |
| topics[1].field.display_name | Health Professions |
| topics[1].score | 0.9327999949455261 |
| topics[1].domain.id | https://openalex.org/domains/4 |
| topics[1].domain.display_name | Health Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/3600 |
| topics[1].subfield.display_name | General Health Professions |
| topics[1].display_name | Interpreting and Communication in Healthcare |
| topics[2].id | https://openalex.org/T13310 |
| topics[2].field.id | https://openalex.org/fields/12 |
| topics[2].field.display_name | Arts and Humanities |
| topics[2].score | 0.9054999947547913 |
| topics[2].domain.id | https://openalex.org/domains/2 |
| topics[2].domain.display_name | Social Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1203 |
| topics[2].subfield.display_name | Language and Linguistics |
| topics[2].display_name | Subtitles and Audiovisual Media |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2776737515 |
| concepts[0].level | 3 |
| concepts[0].score | 0.606157660484314 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q14759 |
| concepts[0].display_name | American Sign Language |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.5455753803253174 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C204321447 |
| concepts[2].level | 1 |
| concepts[2].score | 0.3414493501186371 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[2].display_name | Natural language processing |
| concepts[3].id | https://openalex.org/C522192633 |
| concepts[3].level | 2 |
| concepts[3].score | 0.2501937747001648 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q34228 |
| concepts[3].display_name | Sign language |
| concepts[4].id | https://openalex.org/C41895202 |
| concepts[4].level | 1 |
| concepts[4].score | 0.21048930287361145 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[4].display_name | Linguistics |
| concepts[5].id | https://openalex.org/C138885662 |
| concepts[5].level | 0 |
| concepts[5].score | 0.0 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[5].display_name | Philosophy |
| keywords[0].id | https://openalex.org/keywords/american-sign-language |
| keywords[0].score | 0.606157660484314 |
| keywords[0].display_name | American Sign Language |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.5455753803253174 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/natural-language-processing |
| keywords[2].score | 0.3414493501186371 |
| keywords[2].display_name | Natural language processing |
| keywords[3].id | https://openalex.org/keywords/sign-language |
| keywords[3].score | 0.2501937747001648 |
| keywords[3].display_name | Sign language |
| keywords[4].id | https://openalex.org/keywords/linguistics |
| keywords[4].score | 0.21048930287361145 |
| keywords[4].display_name | Linguistics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2407.15806 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2407.15806 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2407.15806 |
| locations[1].id | doi:10.48550/arxiv.2407.15806 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2407.15806 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5040607597 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Manfred Georg |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Georg, Manfred |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5004101107 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Garrett Tanzer |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Tanzer, Garrett |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5060564303 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-6663-4565 |
| authorships[2].author.display_name | Saad S. M. Hassan |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Hassan, Saad |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5113257043 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Maximus Shengelia |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Shengelia, Maximus |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5059951406 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Esha Uboweja |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Uboweja, Esha |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5092862292 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-8689-4804 |
| authorships[5].author.display_name | Sam Sepah |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Sepah, Sam |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5070299751 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-0900-2507 |
| authorships[6].author.display_name | S. M. Forbes |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Forbes, Sean |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5045801671 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-8442-7842 |
| authorships[7].author.display_name | Thad Starner |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Starner, Thad |
| authorships[7].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2407.15806 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-01-05T00:00:00 |
| display_name | FSboard: Over 3 million characters of ASL fingerspelling collected via smartphones |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11285 |
| primary_topic.field.id | https://openalex.org/fields/32 |
| primary_topic.field.display_name | Psychology |
| primary_topic.score | 0.9821000099182129 |
| primary_topic.domain.id | https://openalex.org/domains/2 |
| primary_topic.domain.display_name | Social Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3204 |
| primary_topic.subfield.display_name | Developmental and Educational Psychology |
| primary_topic.display_name | Hearing Impairment and Communication |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W3157102744, https://openalex.org/W2001405890 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2407.15806 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2407.15806 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2407.15806 |
| primary_location.id | pmh:oai:arXiv.org:2407.15806 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2407.15806 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2407.15806 |
| publication_date | 2024-07-22 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 29, 49, 108, 113, 134 |
| abstract_inverted_index.30 | 118 |
| abstract_inverted_index.4A | 45 |
| abstract_inverted_index.As | 112 |
| abstract_inverted_index.At | 87 |
| abstract_inverted_index.Hz | 119 |
| abstract_inverted_index.In | 15 |
| abstract_inverted_index.an | 21, 56 |
| abstract_inverted_index.as | 81 |
| abstract_inverted_index.by | 12, 107 |
| abstract_inverted_index.in | 1, 28, 48, 91, 96, 162 |
| abstract_inverted_index.is | 55, 60, 99 |
| abstract_inverted_index.it | 70 |
| abstract_inverted_index.of | 4, 51, 65, 78, 110 |
| abstract_inverted_index.on | 133, 160 |
| abstract_inverted_index.to | 76, 105, 156 |
| abstract_inverted_index.we | 18, 116 |
| abstract_inverted_index.147 | 37 |
| abstract_inverted_index.and | 10, 39, 93, 126, 140, 150 |
| abstract_inverted_index.but | 69 |
| abstract_inverted_index.has | 7 |
| abstract_inverted_index.one | 62 |
| abstract_inverted_index.run | 159 |
| abstract_inverted_index.set | 136 |
| abstract_inverted_index.the | 100 |
| abstract_inverted_index.use | 33 |
| abstract_inverted_index.Deaf | 41 |
| abstract_inverted_index.Rate | 131 |
| abstract_inverted_index.Sign | 23 |
| abstract_inverted_index.This | 142 |
| abstract_inverted_index.been | 8 |
| abstract_inverted_index.date | 106 |
| abstract_inverted_index.from | 36 |
| abstract_inverted_index.help | 157 |
| abstract_inverted_index.into | 124 |
| abstract_inverted_index.more | 82 |
| abstract_inverted_index.only | 61 |
| abstract_inverted_index.paid | 38 |
| abstract_inverted_index.part | 64 |
| abstract_inverted_index.rate | 149 |
| abstract_inverted_index.real | 163 |
| abstract_inverted_index.sign | 5, 66 |
| abstract_inverted_index.slow | 9 |
| abstract_inverted_index.some | 73 |
| abstract_inverted_index.test | 135 |
| abstract_inverted_index.text | 31 |
| abstract_inverted_index.that | 59 |
| abstract_inverted_index.this | 16 |
| abstract_inverted_index.when | 146 |
| abstract_inverted_index.with | 137 |
| abstract_inverted_index.>3 | 88 |
| abstract_inverted_index.(CER) | 132 |
| abstract_inverted_index.11.1% | 128 |
| abstract_inverted_index.Error | 130 |
| abstract_inverted_index.Pixel | 44 |
| abstract_inverted_index.case, | 34 |
| abstract_inverted_index.could | 71 |
| abstract_inverted_index.data. | 14 |
| abstract_inverted_index.entry | 32 |
| abstract_inverted_index.frame | 148 |
| abstract_inverted_index.hours | 95 |
| abstract_inverted_index.small | 63 |
| abstract_inverted_index.time. | 164 |
| abstract_inverted_index.using | 43 |
| abstract_inverted_index.device | 161 |
| abstract_inverted_index.factor | 109 |
| abstract_inverted_index.inputs | 123 |
| abstract_inverted_index.length | 92 |
| abstract_inverted_index.mobile | 30 |
| abstract_inverted_index.models | 158 |
| abstract_inverted_index.paper, | 17 |
| abstract_inverted_index.selfie | 46 |
| abstract_inverted_index.simple | 114 |
| abstract_inverted_index.unique | 138 |
| abstract_inverted_index.>250 | 94 |
| abstract_inverted_index.FSboard | 98 |
| abstract_inverted_index.Hearing | 79 |
| abstract_inverted_index.achieve | 127 |
| abstract_inverted_index.benefit | 75 |
| abstract_inverted_index.broadly | 83 |
| abstract_inverted_index.cameras | 47 |
| abstract_inverted_index.capable | 84 |
| abstract_inverted_index.dataset | 26, 104 |
| abstract_inverted_index.largest | 101 |
| abstract_inverted_index.limited | 13 |
| abstract_inverted_index.machine | 2 |
| abstract_inverted_index.million | 89 |
| abstract_inverted_index.phrases | 139 |
| abstract_inverted_index.present | 19 |
| abstract_inverted_index.provide | 72 |
| abstract_inverted_index.quality | 143 |
| abstract_inverted_index.signers | 42, 80 |
| abstract_inverted_index.variety | 50 |
| abstract_inverted_index.>10x. | 111 |
| abstract_inverted_index.American | 22 |
| abstract_inverted_index.FSboard, | 20 |
| abstract_inverted_index.Holistic | 121 |
| abstract_inverted_index.Language | 24 |
| abstract_inverted_index.Progress | 0 |
| abstract_inverted_index.degrades | 144 |
| abstract_inverted_index.finetune | 117 |
| abstract_inverted_index.hampered | 11 |
| abstract_inverted_index.landmark | 122 |
| abstract_inverted_index.language | 67 |
| abstract_inverted_index.signers. | 141 |
| abstract_inverted_index.situated | 27 |
| abstract_inverted_index.solution | 58 |
| abstract_inverted_index.Character | 129 |
| abstract_inverted_index.Deaf/Hard | 77 |
| abstract_inverted_index.MediaPipe | 120 |
| abstract_inverted_index.baseline, | 115 |
| abstract_inverted_index.collected | 35 |
| abstract_inverted_index.develops. | 86 |
| abstract_inverted_index.duration, | 97 |
| abstract_inverted_index.excluding | 151 |
| abstract_inverted_index.face/body | 152 |
| abstract_inverted_index.immediate | 74 |
| abstract_inverted_index.languages | 6 |
| abstract_inverted_index.plausible | 154 |
| abstract_inverted_index.ByT5-Small | 125 |
| abstract_inverted_index.characters | 90 |
| abstract_inverted_index.consenting | 40 |
| abstract_inverted_index.decreasing | 147 |
| abstract_inverted_index.gracefully | 145 |
| abstract_inverted_index.incomplete | 57 |
| abstract_inverted_index.landmarks: | 153 |
| abstract_inverted_index.technology | 85 |
| abstract_inverted_index.recognition | 54, 103 |
| abstract_inverted_index.translation, | 68 |
| abstract_inverted_index.environments. | 52 |
| abstract_inverted_index.optimizations | 155 |
| abstract_inverted_index.understanding | 3 |
| abstract_inverted_index.Fingerspelling | 53 |
| abstract_inverted_index.fingerspelling | 25, 102 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile |