LLaVA-SLT: Visual Language Tuning for Sign Language Translation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916537944768512 |
|---|---|
| author | Liang, Han Huang, Chengyu Xu, Yuecheng Tang, Cheng Ye, Weicai Zhang, Juze Chen, Xin Yu, Jingyi Xu, Lan |
| author_facet | Liang, Han Huang, Chengyu Xu, Yuecheng Tang, Cheng Ye, Weicai Zhang, Juze Chen, Xin Yu, Jingyi Xu, Lan |
| contents | In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have shown promise, yet they often largely lag behind gloss-based approaches in terms of translation accuracy. To narrow this performance gap, we introduce LLaVA-SLT, a pioneering Large Multimodal Model (LMM) framework designed to leverage the power of Large Language Models (LLMs) through effectively learned visual language embeddings. Our model is trained through a trilogy. First, we propose linguistic continued pretraining. We scale up the LLM and adapt it to the sign language domain using an extensive corpus dataset, effectively enhancing its textual linguistic knowledge about sign language. Then, we adopt visual contrastive pretraining to align the visual encoder with a large-scale pretrained text encoder. We propose hierarchical visual encoder that learns a robust word-level intermediate representation that is compatible with LLM token embeddings. Finally, we propose visual language tuning. We freeze pretrained models and employ a lightweight trainable MLP connector. It efficiently maps the pretrained visual language embeddings into the LLM token embedding space, enabling downstream SLT task. Our comprehensive experiments demonstrate that LLaVA-SLT outperforms the state-of-the-art methods. By using extra annotation-free data, it even closes to the gloss-based accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16524 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLaVA-SLT: Visual Language Tuning for Sign Language Translation Liang, Han Huang, Chengyu Xu, Yuecheng Tang, Cheng Ye, Weicai Zhang, Juze Chen, Xin Yu, Jingyi Xu, Lan Computer Vision and Pattern Recognition In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have shown promise, yet they often largely lag behind gloss-based approaches in terms of translation accuracy. To narrow this performance gap, we introduce LLaVA-SLT, a pioneering Large Multimodal Model (LMM) framework designed to leverage the power of Large Language Models (LLMs) through effectively learned visual language embeddings. Our model is trained through a trilogy. First, we propose linguistic continued pretraining. We scale up the LLM and adapt it to the sign language domain using an extensive corpus dataset, effectively enhancing its textual linguistic knowledge about sign language. Then, we adopt visual contrastive pretraining to align the visual encoder with a large-scale pretrained text encoder. We propose hierarchical visual encoder that learns a robust word-level intermediate representation that is compatible with LLM token embeddings. Finally, we propose visual language tuning. We freeze pretrained models and employ a lightweight trainable MLP connector. It efficiently maps the pretrained visual language embeddings into the LLM token embedding space, enabling downstream SLT task. Our comprehensive experiments demonstrate that LLaVA-SLT outperforms the state-of-the-art methods. By using extra annotation-free data, it even closes to the gloss-based accuracy. |
| title | LLaVA-SLT: Visual Language Tuning for Sign Language Translation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.16524 |