Concept Embedding through Canonical Forms: A Case Study on Zero-Shot ASL Recognition

Kamzin, Azamat; Amperayani, Venkata Naga Sai Apurupa; Sukhapalli, P.; Banerjee, Ayan; Gupta, Sandeep

doi:10.1109/icpr48806.2021.9412207

Cited by 3 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sign language vocabulary is so large that it is difficult to capture it all by building a dataset, so getting the models to learn the new sign language themselves will be one of the main solutions. Currently, some scholars [164][165][166] have carried out research on isolated sign language recognition based on fewshot learning or zero-shot learning. There is still a large room for improvement.…”

Section: No Ability To Recognize Sign Language Outside the Datasetmentioning

confidence: 99%

Sign Language Recognition: A Comprehensive Review of Traditional and Deep Learning Approaches, Datasets, and Challenges

Tao,

Zhao,

Liu

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The Deaf are a large social group in society. Their unique way of communicating through sign language is often confined within their community due to limited understanding by individuals outside of this demographic. This is where sign language recognition (SLR) comes in to help normal people understand the meaning of sign language. In recent years, new methods of sign language recognition have been developed and achieved good results, so it is necessary to make a summary. This review mainly focuses on the introduction of sign language recognition techniques based on algorithms especially in recent years, including the recognition models based on traditional methods and deep learning approaches, sign language datasets, challenges and future directions in SLR. To make the method structure clearer, this article explains and compares the basic principles of different methods from the perspectives of feature extraction and temporal modelling. We hope that this review will provide some reference and help for future research in sign language recognition.

show abstract

Section: No Ability To Recognize Sign Language Outside the Datasetmentioning

confidence: 99%

Sign Language Recognition: A Comprehensive Review of Traditional and Deep Learning Approaches, Datasets, and Challenges

Tao,

Zhao,

Liu

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Identification of sub-lexical properties is enhanced by utilizing this grammatical representation as discussed in [12].…”

Section: Asl Gesture Expression In Terms Of Sub-lexical Propertiesmentioning

confidence: 99%

EdGCon: Auto-assigner of Iconicity Ratings Grounded by Lexical Properties to Aid in Generation of Technical Gestures

Hossain

Kamboj

Maity

et al. 2023

Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing

View full text Add to dashboard Cite

Gestures that share similarities in their forms and are related in their meanings, should be easier for learners to recognize and incorporate into their existing lexicon. In that regard, to be more readily accepted as standard by the Deaf and Hard of Hearing community, technical gestures in American Sign Language (ASL) will optimally share similar in forms with their lexical neighbors. We utilize a lexical database of ASL, ASL-LEX, to identify lexical relations within a set of technical gestures. We use automated identification for 3 unique sub-lexical properties in ASL-location, handshape and movement. 𝐸𝑑𝐺𝐶𝑜𝑛 assigned an iconicity rating based on the lexical property similarities of the new gesture with an existing set of technical gestures and the relatedness of the meaning of the new technical word to that of the existing set of technical words. We collected 30 ad hoc crowdsourced technical gestures from different internet websites and tested them against 31 gestures from the DeafTEC technical corpus. We found that 𝐸𝑑𝐺𝐶𝑜𝑛 was able to correctly auto-assign the iconicity ratings 80.76% of the time. 1

show abstract

Engendering Trust in Automated Feedback: A Two Step Comparison of Feedbacks in Gesture Based Learning

Hossain

Kamzin

Amperayani

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Concept Embedding through Canonical Forms: A Case Study on Zero-Shot ASL Recognition

Cited by 3 publications

References 18 publications

Sign Language Recognition: A Comprehensive Review of Traditional and Deep Learning Approaches, Datasets, and Challenges

Sign Language Recognition: A Comprehensive Review of Traditional and Deep Learning Approaches, Datasets, and Challenges

EdGCon: Auto-assigner of Iconicity Ratings Grounded by Lexical Properties to Aid in Generation of Technical Gestures

Engendering Trust in Automated Feedback: A Two Step Comparison of Feedbacks in Gesture Based Learning

Contact Info

Product

Resources

About