paper-with-me

Papers

Spatio-temporal Sign Language Representation and Translation

2022-12-10 · Proceedings of the Seventh Conference on Machine Translation (WMT) 2022 12 · Yasser Hamidullah, Josef van Genabith, Cristina España-Bonet

This paper describes the DFKI-MLT submission to the WMT-SLT 2022 sign language translation (SLT) task from Swiss German Sign Language (video) into German (text). State-of-the-art techniques for SLT use a generic seq2seq architecture with customized input embeddings. Instead of word embeddings as used in textual machine translation, SLT systems use features extracted from video frames. Standard approaches often do not benefit from temporal features. In our participation, we present a system that learns spatio-temporal feature representations and translation in a single model, resulting in a real end-to-end architecture expected to better generalize to new data sets. Our best system achieved 5 ± 1 BLEU points on the development set, but the performance on the test dropped to 0.11 ± 0.06 BLEU points.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationSign Language TranslationTranslationWord Embeddings

Similar Papers 제목 키워드 기반

Spatio-temporal Sign Language Representation and Translation

2025-10-22 · Yasser Hamidullah, Josef van Genabith, Cristina España-Bonet arxiv

This paper describes the DFKI-MLT submission to the WMT-SLT 2022 sign language translation (SLT) task from Swiss German Sign Language (video) into German (text). State-of-the-art techniques for SLT use a generic seq2seq …

Sign Language TranslationMachine Translation

A Spatio-Temporal Representation Learning as an Alternative to Traditional Glosses in Sign Language Translation and Production

2024-07-03 · Eui Jun Hwang, Sukmin Cho, Huije Lee, Youngwoo Yoon 외

This work addresses the challenges associated with the use of glosses in both Sign Language Translation (SLT) and Sign Language Production (SLP). While glosses have long been used as a bridge between sign language and sp…

Gloss-free Sign Language TranslationRepresentation LearningSelf-Supervised LearningSign Language Production+3

Sign Language Translation with Hierarchical Spatio-TemporalGraph Neural Network

2021-11-14 · Jichao Kan, Kun Hu, Markus Hagenbuchner, Ah Chung Tsoi 외

Sign language translation (SLT), which generates text in a spoken language from visual content in a sign language, is important to assist the hard-of-hearing community for their communications. Inspired by neural machine…

Graph Neural NetworkMachine TranslationNMTSign Language Translation+1

A multitask transformer to sign language translation using motion gesture primitives

2025-03-25 · Fredy Alejandro Mendoza López, Jefferson Rodriguez, Fabio Martínez

The absence of effective communication the deaf population represents the main social gap in this community. Furthermore, the sign language, main deaf communication tool, is unlettered, i.e., there is no formal written r…

Sign Language Translation

SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition

2026-01-24 · Rui Fan, Weidong Hao arxiv

Event cameras action recognition (EAR) offers compelling privacy-protecting and efficiency advantages, where temporal motion dynamics is of great importance. Existing spatiotemporal multi-view representation learning (SM…

Representation LearningAction RecognitionObject Recognition