Deep learning pathways for automatic sign language processing

M Toshpulatov, W Lee, J Jun, S Lee - Pattern Recognition, 2025 - Elsevier
This study provides a comprehensive review of the current state of the sign language
processing (SLP) field, encompassing sign language recognition (SLR), translation (SLT) …

Wilor: End-to-end 3d hand localization and reconstruction in-the-wild

RA Potamias, J Zhang, J Deng, S Zafeiriou - arxiv preprint arxiv …, 2024 - arxiv.org
In recent years, 3D hand pose estimation methods have garnered significant attention due to
their extensive applications in human-computer interaction, virtual reality, and robotics. In …

Animateme: 4d facial expressions via diffusion models

D Gerogiannis, FP Papantoniou, RA Potamias… - … on Computer Vision, 2024 - Springer
The field of photorealistic 3D avatar reconstruction and generation has garnered significant
attention in recent years; however, animating such avatars remains challenging. Recent …

A review of deep learning-based approaches to sign language processing

S Tan, N Khan, Z An, Y Ando, R Kawakami… - Advanced …, 2024 - Taylor & Francis
Technology to support human communication by sign language may address a growing
social need and is interesting from an engineering perspective, considering multimodal …

Sign-IDD: Iconicity Disentangled Diffusion for Sign Language Production

S Tang, J He, D Guo, Y Wei, F Li, R Hong - arxiv preprint arxiv …, 2024 - arxiv.org
Sign Language Production (SLP) aims to generate semantically consistent sign videos from
textual statements, where the conversion from textual glosses to sign poses (G2P) is a …

Pose-Guided Fine-Grained Sign Language Video Generation

T Shi, L Hu, F Shang, J Feng, P Liu, W Feng - European Conference on …, 2024 - Springer
Sign language videos are an important medium for spreading and learning sign language.
However, most existing human image synthesis methods produce sign language images …

Shapefusion: A 3d diffusion model for localized shape editing

RA Potamias, M Tarasiou, S Ploumpis… - European Conference on …, 2024 - Springer
In the realm of 3D computer vision, parametric models have emerged as a ground-breaking
methodology for the creation of realistic and expressive 3D avatars. Traditionally, they rely …

T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text

A Yin, H Li, K Shen, S Tang, Y Zhuang - arxiv preprint arxiv:2406.07119, 2024 - arxiv.org
In this work, we propose a two-stage sign language production (SLP) paradigm that first
encodes sign language sequences into discrete codes and then autoregressively generates …

Signs as Tokens: An Autoregressive Multilingual Sign Language Generator

R Zuo, RA Potamias, E Ververas, J Deng… - arxiv preprint arxiv …, 2024 - arxiv.org
Sign language is a visual language that encompasses all linguistic features of natural
languages and serves as the primary communication method for the deaf and hard-of …

[КНИГА][B] Computer Vision-ECCV 2024: 18th European Conference, Milan, Italy, September 29-October 4, 2024, Proceedings, Part XXIV.

A Leonardis, E Ricci, S Roth, O Russakovsky, T Sattler… - 2024 - books.google.com
The multi-volume set of LNCS books with volume numbers 15059 up to 15147 constitutes
the refereed proceedings of the 18th European Conference on Computer Vision, ECCV …