Summary of Scope: Sign Language Contextual Processing with Embedding From Llms, by Yuqi Liu et al.
SCOPE: Sign Language Contextual Processing with Embedding from LLMs
by Yuqi Liu, Wenqian Zhang, Sihan Ren, Chengyu Huang, Jingyi Yu, Lan Xu
First submitted to arxiv on: 2 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces a novel context-aware vision-based sign language recognition (SLR) and translation (SLT) framework, SCOPE, which leverages multi-modal encoders for dialogue contexts and Large Language Models (LLMs) for fine-tuning. The authors address the limitations of current SLR and SLT methods by introducing a new sign language dataset containing 72 hours of Chinese sign language videos in contextual dialogues. The SCOPE framework achieves state-of-the-art performance on multiple datasets, including Phoenix-2014T, CSL-Daily, and the SCOPE dataset itself. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary SCOPE is a new way to recognize and translate sign languages like those used by Deaf people all around the world. Right now, computers can only understand simple signs, but they struggle with longer conversations because they don’t take into account what’s happening in the scene. The authors created a special framework that uses computer vision and language models to better understand these conversations. They also made a huge dataset of sign language videos that includes different scenarios like shopping or dining. This helps computers learn to recognize signs more accurately. |
Keywords
» Artificial intelligence » Fine tuning » Multi modal » Translation
