The NGT200 Dataset: Geometric Multi-View Isolated Sign Recognition
Not on the map. Why?
Abstract (arXiv)
Sign Language Processing (SLP) provides a foundation for a more inclusive future in language technology; however, the field faces several significant challenges that must be addressed to achieve practical, real-world applications. This work addresses multi-view isolated sign recognition (MV-ISR), and highlights the essential role of 3D awareness and geometry in SLP systems. We introduce the NGT200 dataset, a novel spatio-temporal multi-view benchmark, establishing MV-ISR as distinct from single-view ISR (SV-ISR). We demonstrate the benefits of synthetic data and propose conditioning sign representations on spatial symmetries inherent in sign language. Leveraging an SE(2) equivariant model improves MV-ISR performance by 8%-22% over the baseline.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 19 of its 49 references that are in the map. First posted on arXiv 3 Sep 2024.
Builds on
19 of 49 references.
References · 19
- 2019MediaPipe: A Framework for Building Perception Pipelinescited by 583
- 2019Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparisoncited by 218
- 2020How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Languagecited by 173
- 2018MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Languagecited by 118
- 2021Skeleton Aware Multi-modal Sign Language Recognitioncited by 101
- 2019Sign Language Recognition, Generation, and Translation: An Interdisciplinary Perspectivecited by 87
- 2020AUTSL: A Large Scale Multi-modal Turkish Sign Language Dataset and Baseline Methodscited by 75
- 2021Including Signed Languages in Natural Language Processingcited by 68
- 2020Quantitative Survey of the State of the Art in Sign Language Recognitioncited by 50
- 2023Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Spacecited by 41
- 2023ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognitioncited by 34
- 2021OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languagescited by 31
7 more
- 2021Sign Language Production: A Reviewcited by 26
- 2021Evaluating the Immediate Applicability of Pose Estimation for Sign Language Recognitioncited by 25
- 2024Systemic Biases in Sign Language AI Research: A Deaf-Led Call to Reevaluate Research Agendascited by 19
- 2024Grounding Continuous Representations in Geometry: Equivariant Neural Fieldscited by 19
- 2023The Sem-Lex Benchmark: Modeling ASL Signs and Their Phonemescited by 17
- 2021Skeletal Graph Self-Attention: Embedding a Skeleton Inductive Bias into Sign Language Productioncited by 11
- 2023Exploring Strategies for Modeling Sign Language Phonologycited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.