# Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment

arXiv: https://arxiv.org/abs/2512.08040 · HTML: https://mlsanity.com/paper/2512.08040/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 93 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Builds on (most cited first, 30 of 61)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [LRS3-TED: a large-scale dataset for visual speech recognition](https://mlsanity.com/paper/1809.00496/) (2018)
- [Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation](https://mlsanity.com/paper/2003.13830/) (2020)
- [Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison](https://mlsanity.com/paper/1910.11006/) (2019)
- [Improving Sign Language Translation with Monolingual Data by Sign Back-Translation](https://mlsanity.com/paper/2105.12397/) (2021)
- [How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language](https://mlsanity.com/paper/2008.08143/) (2020)
- [Adaptive Graph Convolutional Neural Networks](https://mlsanity.com/paper/1801.03226/) (2018)
- [Two-Stream Network for Sign Language Recognition and Translation](https://mlsanity.com/paper/2211.01367/) (2022)
- [MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language](https://mlsanity.com/paper/1812.01053/) (2018)
- [Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels](https://mlsanity.com/paper/2303.14307/) (2023)
- [BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues](https://mlsanity.com/paper/2007.12131/) (2020)
- [TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning](https://mlsanity.com/paper/2410.19702/) (2024)
- [Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining](https://mlsanity.com/paper/2307.14768/) (2023)
- [Visual Alignment Constraint for Continuous Sign Language Recognition](https://mlsanity.com/paper/2104.02330/) (2021)

## Built on by (most cited first, 6 of 6)

- [M3T: Discrete Multi-Modal Motion Tokens for Sign Language Production](https://mlsanity.com/paper/2603.23617/) (2026)
- [Sign Language Recognition in the Age of LLMs](https://mlsanity.com/paper/2604.11225/) (2026)
- [ViPo-MLLM: Visual-Pose Multimodal LLM for Gloss-Free Sign Language Translation](https://mlsanity.com/paper/2607.03657/) (2026)
- [ODE-Based Transformer Decoders for Iterative Sign Language Translation](https://mlsanity.com/paper/2608.11352/) (2026)
- [SignMatch: Matching Dictionary Signs to Continuous Sign Language Video](https://mlsanity.com/paper/2609.01886/) (2026)
- [SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation](https://mlsanity.com/paper/2610.11371/) (2026)

## Abstract (arXiv)

Our aim is to develop a unified model for sign language understanding, that performs sign language translation (SLT) and sign-subtitle alignment (SSA). Together, these two tasks enable the conversion of continuous signing videos into spoken language text and also the temporal alignment of signing with subtitles -- both essential for practical communication, large-scale corpus construction, and educational applications. To achieve this, our approach is built upon three components: (i) a lightweight visual backbone that captures manual and non-manual cues from human keypoints and lip-region images while preserving signer privacy; (ii) a Sliding Perceiver mapping network that aggregates consecutive visual features into word-level embeddings to bridge the vision-text gap; and (iii) a multi-task scalable training strategy that jointly optimises SLT and SSA, reinforcing both linguistic and temporal alignment. To promote cross-linguistic generalisation, we pretrain our model on large-scale sign-text corpora covering British Sign Language (BSL) and American Sign Language (ASL) from the BOBSL and YouTube-SL-25 datasets. With this multilingual pretraining and strong model design, we achieve state-of-the-art results on the challenging BOBSL (BSL) dataset for both SLT and SSA. Our model also demonstrates robust zero-shot generalisation and finetuned SLT performance on How2Sign (ASL), highlighting the potential of scalable translation across different sign languages.