@inproceedings{zhang-etal-2025-dynamic,
title = "Dynamic Feature Fusion for Sign Language Translation Using {H}yper{N}etworks",
author = "Zhang, Ruiquan and
Zhao, Rui and
Wu, Zhicong and
Zhang, Liang and
Zhang, Haoqi and
Chen, Yidong",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.348/",
doi = "10.18653/v1/2025.findings-naacl.348",
pages = "6227--6239",
ISBN = "979-8-89176-195-7",
abstract = "This paper presents an efficient dual-stream early fusion method for sign language translation. Inspired by the brain{'}s ability to process color, shape, and motion simultaneously, the method explores complex dependencies between RGB and keypoint streams, improving speed and efficiency. A key challenge is extracting complementary features from both streams while ensuring global semantic consistency to avoid conflicts and improve generalization. To address this issue, we propose a hypernetwork-based fusion strategy that effectively extracts salient features from RGB and keypoint streams, alongside a partial shortcut connection training method to strengthen the complementary information between the dual streams. Additionally, we introduce self-distillation and SST contrastive learning to maintain feature advantages while aligning the global semantic space. Experiments show that our method achieves state-of-the-art performance on two public sign language datasets, reducing model parameters by about two-thirds."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-dynamic">
<titleInfo>
<title>Dynamic Feature Fusion for Sign Language Translation Using HyperNetworks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruiquan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhicong</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoqi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yidong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>This paper presents an efficient dual-stream early fusion method for sign language translation. Inspired by the brain’s ability to process color, shape, and motion simultaneously, the method explores complex dependencies between RGB and keypoint streams, improving speed and efficiency. A key challenge is extracting complementary features from both streams while ensuring global semantic consistency to avoid conflicts and improve generalization. To address this issue, we propose a hypernetwork-based fusion strategy that effectively extracts salient features from RGB and keypoint streams, alongside a partial shortcut connection training method to strengthen the complementary information between the dual streams. Additionally, we introduce self-distillation and SST contrastive learning to maintain feature advantages while aligning the global semantic space. Experiments show that our method achieves state-of-the-art performance on two public sign language datasets, reducing model parameters by about two-thirds.</abstract>
<identifier type="citekey">zhang-etal-2025-dynamic</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.348</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.348/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>6227</start>
<end>6239</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dynamic Feature Fusion for Sign Language Translation Using HyperNetworks
%A Zhang, Ruiquan
%A Zhao, Rui
%A Wu, Zhicong
%A Zhang, Liang
%A Zhang, Haoqi
%A Chen, Yidong
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F zhang-etal-2025-dynamic
%X This paper presents an efficient dual-stream early fusion method for sign language translation. Inspired by the brain’s ability to process color, shape, and motion simultaneously, the method explores complex dependencies between RGB and keypoint streams, improving speed and efficiency. A key challenge is extracting complementary features from both streams while ensuring global semantic consistency to avoid conflicts and improve generalization. To address this issue, we propose a hypernetwork-based fusion strategy that effectively extracts salient features from RGB and keypoint streams, alongside a partial shortcut connection training method to strengthen the complementary information between the dual streams. Additionally, we introduce self-distillation and SST contrastive learning to maintain feature advantages while aligning the global semantic space. Experiments show that our method achieves state-of-the-art performance on two public sign language datasets, reducing model parameters by about two-thirds.
%R 10.18653/v1/2025.findings-naacl.348
%U https://aclanthology.org/2025.findings-naacl.348/
%U https://doi.org/10.18653/v1/2025.findings-naacl.348
%P 6227-6239
Markdown (Informal)
[Dynamic Feature Fusion for Sign Language Translation Using HyperNetworks](https://aclanthology.org/2025.findings-naacl.348/) (Zhang et al., Findings 2025)
ACL