mlsanityData to 7 Oct 2026

Signformer is all you need: Towards Edge AI for Sign Language

arXiv 2411.12901 ↗First posted 19 Nov 2024cs.CL cs.CV cs.CYcited by 3

Not on the map. Why?

Abstract (arXiv)

Sign language translation, especially in gloss-free paradigm, is confronting a dilemma of impracticality and unsustainability due to growing resource-intensive methodologies. Contemporary state-of-the-arts (SOTAs) have significantly hinged on pretrained sophiscated backbones such as Large Language Models (LLMs), embedding sources, or extensive datasets, inducing considerable parametric and computational inefficiency for sustainable use in real-world scenario. Despite their success, following this research direction undermines the overarching mission of this domain to create substantial value to bridge hard-hearing and common populations. Committing to the prevailing trend of LLM and Natural Language Processing (NLP) studies, we pursue a profound essential change in architecture to achieve ground-up improvements without external aid from pretrained models, prior knowledge transfer, or any NLP strategies considered not-from-scratch. Introducing Signformer, a from-scratch Feather-Giant transforming the area towards Edge AI that redefines extremities of performance and efficiency with LLM-competence and edgy-deployable compactness. In this paper, we present nature analysis of sign languages to inform our algorithmic design and deliver a scalable transformer pipeline with convolution and attention novelty. We achieve new 2nd place on leaderboard with a parametric reduction of 467-1807x against the finests as of 2024 and outcompete almost every other methods in a lighter configuration of 0.57 million parameters.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 19 Nov 2024.

Builds on

25 of 40 references.

References · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  6. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  7. 2020GLU Variants Improve Transformercited by 1,724
  8. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  9. 2024ShortGPT: Layers in Large Language Models are More Redundant Than You Expectcited by 369
  10. 2018Efficient Attention: Attention with Linear Complexitiescited by 366
  11. 2023Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-trainingcited by 260
  12. 2019Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparisoncited by 217
13 more
  1. 2021Improving Sign Language Translation with Monolingual Data by Sign Back-Translationcited by 177
  2. 2023Gloss-free Sign Language Translation: Improving from Visual-Language Pretrainingcited by 104
  3. 2022A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translationcited by 80
  4. 2020Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognitioncited by 74
  5. 2024Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translationcited by 56
  6. 2024Contextual Position Encoding: Learning to Count What's Importantcited by 53
  7. 2017BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languagescited by 52
  8. 2019How Language-Neutral is Multilingual BERT?cited by 51
  9. 2023A Survey on Efficient Training of Transformerscited by 37
  10. 2021Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translationcited by 35
  11. 2018NetScore: Towards Universal Metrics for Large-scale Performance Analysis of Deep Neural Networks for Practical On-Device Edge Usagecited by 30
  12. 2020Neural Sign Language Translation by Learning Tokenizationcited by 19
  13. 2024Multi-Stream Keypoint Attention Network for Sign Language Recognition and Translationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026SignVLA: A Gloss-Free Vision-Language-Action Framework for Real-Time Sign Language-Guided Robotic Manipulationcited by 3
  2. 2026Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Modelscited by 0
  3. 2026SignVLA: Real-Time Sign Language-Guided Robotic Manipulation via Attention LSTM and Vision-Language-Action Modelscited by 0