Recent advances in sign language understanding have achieved impressive success on short, single-sentence videos, yet their performance drops sharply when applied to long, continuous sign language videos. To bridge this gap, we focus on a challenging and realistic setting: Visual-only Sentence-level Sign Language Segme...
Bo-Wen Guo, Shi-Wei Gan, Ya-Feng Yin et al.· 0 citations
Uni-SLTP is proposed, a unified framework for SLT and SLP with two key components: a shared sign tokenizer that converts sign sequences into discrete tokens and latent representations, capturing both semantic and reconstructive information.
Xiao Liu, Shi-Wei Gan, Ya-Feng Yin et al.· 0 citations
This work proposes an inference-time, plug-and-play Self-Contrastive Steering (SCS) method that constructs unconditional general text embeddings and uses them to refine conditional text embeddings, making them more focused on the target condition.
Zi-Feng Cheng, Ling-Yun Qian, Zhi-Wei Jiang et al.· Annual Meeting of the Associ...· 1 citation
Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks. However, fine-tuning LLMs for Gloss-Free Sign Language Translation (GFSLT) remains a challenge. In this paper, we investigate how to effectively adapt LLMs to the GFSLT task. We show that there are two key issues that need to be...
Shi-Wei Gan, Xiao Liu, Ya-Feng Yin et al.· 1 citation
SignDINO is introduced, a simple yet effective sign-aware DINO training strategy that learns effective and semantically meaningful sign-aware DINO training strategy, and only global frames are required during inference for simplicity.
Shi-Wei Gan, Xiao Liu, Ya-Feng Yin et al.· Computer Vision and Pattern...· 2 citations
Class-wise Covariance Regularization is proposed, which aligns the predicted covariance structure of class confidences with the semantic correlations encoded in pretrained text embed-dings with the geometric consistency of the class space throughout fine-tuning, resulting in more stable and interpretable confidence dis...
Ao Zhou, Zhi-Wei Jiang, Zi-Feng Cheng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.