SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.14768 · ICCV · 2023

Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining

Sergio Escalera, Jun Wan, Yanyan Liang, Zhen Lei, Zhigang Chen, Benjia Zhou, Du Zhang, Albert Clapés

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
zhoubenjia/gfslt-vlp canonical 6 of 7
FunctionStatusWhere it lives
cosine_scheduler Ran zhoubenjia/gfslt-vlp/utils.py
code served (permissive licence) · get_code("04805aa3e54efe47")
make_head Ran zhoubenjia/gfslt-vlp/models.py
code served (permissive licence) · get_code("dd6acfc78ad9755a")
sampler_func Ran zhoubenjia/gfslt-vlp/utils.py
code served (permissive licence) · get_code("3ecbe9910f3ee824")
tokenize_13a Ran zhoubenjia/gfslt-vlp/metrics.py
code served (permissive licence) · get_code("b5ec86d615fa1553")
tokenize_v14_international Ran zhoubenjia/gfslt-vlp/metrics.py
code served (permissive licence) · get_code("7863c21b724029ba")
tokenize_zh Ran zhoubenjia/gfslt-vlp/metrics.py
code served (permissive licence) · get_code("803bc06bd832fbfe")
count_parameters_in_MB Not yet run zhoubenjia/gfslt-vlp/utils.py
code served (permissive licence) · get_code("0fee20319bd8425a")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Sign Language Translation (SLT) is a challenging task due to its cross-domain nature, involving the translation of visual-gestural language to text. Many previous methods employ an intermediate representation, i.e., gloss sequences, to facilitate SLT, thus transforming it into a twostage task of sign language recognition (SLR) followed by sign language translation (SLT). However, the scarcity of gloss-annotated sign language data, combined with the information bottleneck in the mid-level gloss representation, has hindered the further development of the SLT task. To address this challenge, we propose a novel Gloss-Free SLT based on Visual-Language Pretraining (GFSLT-VLP), which improves SLT by inheriting language-oriented prior knowledge from pre-trained models, without any gloss annotation assistance. Our approach involves two stages: (i) integrating Contrastive Language-Image Pretraining (CLIP) 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 Encoder and Text Decoder from the first stage. The seamless combination of these novel designs forms a robust sign language representation and significantly improves gloss-free sign language translation. In particular, we have achieved unprecedented improvements in terms of BLEU-4 score on the PHOENIX14T dataset (≥+5) and the CSL-Daily dataset (≥+3) compared to state-of-the-art gloss-free SLT methods. Furthermore, our approach also achieves competitive results on the PHOENIX14T dataset when compared with most of the gloss-based methods 1 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2307.14768")
get_code_for_paper("2307.14768")
have("2307.14768")

Connect an agent — have() is free.