# Hands-On: Segmenting Individual Signs from Continuous Sequences

arXiv: https://arxiv.org/abs/2504.08593 · HTML: https://mlsanity.com/paper/2504.08593/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 11 Apr 2025.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [Two-Stream Network for Sign Language Recognition and Translation](https://mlsanity.com/paper/2211.01367/) (2022)
- [Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining](https://mlsanity.com/paper/2307.14768/) (2023)
- [Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production](https://mlsanity.com/paper/2203.15354/) (2022)
- [Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation](https://mlsanity.com/paper/2405.04164/) (2024)
- [SLTUNET: A Simple Unified Model for Sign Language Translation](https://mlsanity.com/paper/2305.01778/) (2023)
- [Aligning Subtitles in Sign Language Videos](https://mlsanity.com/paper/2105.02877/) (2021)
- [Improving 3D Pose Estimation for Sign Language](https://mlsanity.com/paper/2308.09525/) (2023)
- [Sign language segmentation with temporal convolutional networks](https://mlsanity.com/paper/2011.12986/) (2020)
- [Linguistically Motivated Sign Language Segmentation](https://mlsanity.com/paper/2310.13960/) (2023)
- [Sign Segmentation with Changepoint-Modulated Pseudo-Labelling](https://mlsanity.com/paper/2104.13817/) (2021)
- [Multi-Stream Keypoint Attention Network for Sign Language Recognition and Translation](https://mlsanity.com/paper/2405.05672/) (2024)

## Built on by (most cited first, 10 of 10)

- [Beyond Gloss: A Hand-Centric Framework for Gloss-Free Sign Language Translation](https://mlsanity.com/paper/2507.23575/) (2025)
- [Segment, Embed, and Align: A Universal Recipe for Aligning Subtitles to Signing](https://mlsanity.com/paper/2512.08094/) (2025)
- [SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning](https://mlsanity.com/paper/2603.10446/) (2026)
- [Sign Spotting Disambiguation using Large Language Models](https://mlsanity.com/paper/2507.03703/) (2025)
- [SAGE: Segment-Aware Gloss-Free Encoding for Token-Efficient Sign Language Translation](https://mlsanity.com/paper/2507.09266/) (2025)
- [SignAgent: Agentic LLMs for Linguistically-Grounded Sign Language Annotation and Dataset Curation](https://mlsanity.com/paper/2603.19059/) (2026)
- [BackTranslation2.0 -- A Linguistically Motivated Metric to Assess Sign Language Production](https://mlsanity.com/paper/2606.28673/) (2026)
- [Recognising BSL Fingerspelling in Continuous Signing Sequences](https://mlsanity.com/paper/2603.19523/) (2026)
- [Gloss-Free Representation Learning for Cross-Dataset Sign Spotting](https://mlsanity.com/paper/2608.11332/) (2026)
- [Machine Translation for Sign Languages](https://mlsanity.com/paper/2610.00881/) (2026)

## Abstract (arXiv)

This work tackles the challenge of continuous sign language segmentation, a key task with huge implications for sign language translation and data annotation. We propose a transformer-based architecture that models the temporal dynamics of signing and frames segmentation as a sequence labeling problem using the Begin-In-Out (BIO) tagging scheme. Our method leverages the HaMeR hand features, and is complemented with 3D Angles. Extensive experiments show that our model achieves state-of-the-art results on the DGS Corpus, while our features surpass prior benchmarks on BSLCorpus.