LLaVA-SLT: Visual Language Tuning for Sign Language Translation

• URL: http://arxiv.org/abs/2412.16524v1
• Date: Sat, 21 Dec 2024 08:01:08 GMT
• Title: LLaVA-SLT: Visual Language Tuning for Sign Language Translation
• Authors: Han Liang, Chengyu Huang, Yuecheng Xu, Cheng Tang, Weicai Ye, Juze Zhang, Xin Chen, Jingyi Yu, Lan Xu,
• Abstract summary: Recent advancements in Sign Language Translation (SLT) have shown promise, yet they often largely lag behind gloss-based approaches in terms of accuracy. 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 comprehensive experiments demonstrate that LLaVA-SLT outperforms the state-of-the-art methods.
• Score: 42.20090162339927
• License:
• Abstract: 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.

Related papers

• Leveraging the Power of MLLMs for Gloss-Free Sign Language Translation [6.688680877428467]
  We propose a novel gloss-free Multimodal Sign Language Translation framework. We generate detailed textual descriptions of sign language components using multimodal large language models. Our approach achieves state-of-the-art performance on benchmark datasets PHOENIX14T and CSL-Daily.
  arXiv  Detail & Related papers  (2024-11-25T09:01:41Z)
• An Efficient Sign Language Translation Using Spatial Configuration and Motion Dynamics with LLMs [7.630967411418269]
  Gloss-free Sign Language Translation (SLT) converts sign videos directly into spoken language sentences without relying on glosses. This paper emphasizes the importance of capturing the spatial configurations and motion dynamics inherent in sign language. We introduce Spatial and Motion-based Sign Language Translation (SpaMo), a novel LLM-based SLT framework.
  arXiv  Detail & Related papers  (2024-08-20T07:10:40Z)
• Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation [30.008980708977095]
  We introduce Sign2GPT, a novel framework for sign language translation. We propose a novel pretraining strategy that directs our encoder to learn sign representations from automatically extracted pseudo-glosses. We evaluate our approach on two public benchmark sign language translation datasets.
  arXiv  Detail & Related papers  (2024-05-07T10:00:38Z)
• Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation [28.648494997132925]
  We propose Factorized Learning assisted with Large Language Model (FLa-LLM) for gloss-free Sign Language Translation (SLT) We factorize the training process into two stages. In the visual initialing stage, we employ a lightweight translation model after the visual encoder to pre-train the visual encoder. In the LLM fine-tuning stage, we freeze the acquired knowledge in the visual encoder and integrate it with a pre-trained LLM to inspire the LLM's translation potential.
  arXiv  Detail & Related papers  (2024-03-19T09:00:23Z)
• Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining [56.26550923909137]
  Gloss-Free Sign Language Translation (SLT) is a challenging task due to its cross-domain nature. We propose a novel Gloss-Free SLT based on Visual-Language Pretraining (GFSLT-) Our approach involves two stages: (i) integrating Contrastive Language-Image Pre-training with masked self-supervised learning to create pre-tasks that bridge the semantic gap between visual and textual representations and restore masked sentences, and (ii) constructing an end-to-end architecture with an encoder-decoder-like structure that inherits the parameters of the pre-trained Visual and Text Decoder from
  arXiv  Detail & Related papers  (2023-07-27T10:59:18Z)
• mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs [50.17767479660832]
  Vision-language models (Vision-LLMs) align pretrained image encoders with (frozen) large language models (LLMs) and post-hoc condition LLMs to understand' the image input. We present mBLIP, the first Vision-LLM leveraging multilingual LLMs, which we obtain in a computationally efficient manner on consumer-level hardware.
  arXiv  Detail & Related papers  (2023-07-13T17:51:58Z)
• Chain-of-Dictionary Prompting Elicits Translation in Large Language Models [100.47154959254937]
  Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation (MNMT) We present a novel method, CoD, which augments LLMs with prior knowledge with the chains of multilingual dictionaries for a subset of input words to elicit translation abilities.
  arXiv  Detail & Related papers  (2023-05-11T05:19:47Z)
• Translate to Disambiguate: Zero-shot Multilingual Word Sense Disambiguation with Pretrained Language Models [67.19567060894563]
  Pretrained Language Models (PLMs) learn rich cross-lingual knowledge and can be finetuned to perform well on diverse tasks. We present a new study investigating how well PLMs capture cross-lingual word sense with Contextual Word-Level Translation (C-WLT) We find that as the model size increases, PLMs encode more cross-lingual word sense knowledge and better use context to improve WLT performance.
  arXiv  Detail & Related papers  (2023-04-26T19:55:52Z)
• Improving Sign Language Translation with Monolingual Data by Sign Back-Translation [105.83166521438463]
  We propose a sign back-translation (SignBT) approach, which incorporates massive spoken language texts into sign training. With a text-to-gloss translation model, we first back-translate the monolingual text to its gloss sequence. Then, the paired sign sequence is generated by splicing pieces from an estimated gloss-to-sign bank at the feature level.
  arXiv  Detail & Related papers  (2021-05-26T08:49:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.