Collaborative Multilingual Continuous Sign Language Recognition: A Unified Framework

计算机科学 手语 自然语言处理 语言模型 人工智能 符号(数学) 嵌入 编码器 语音识别 语言学 数学分析 哲学 数学 操作系统
作者
Hezhen Hu,Junfu Pu,Wengang Zhou,Houqiang Li
出处
期刊:IEEE Transactions on Multimedia [Institute of Electrical and Electronics Engineers]
卷期号:25: 7559-7570 被引量:2
标识
DOI:10.1109/tmm.2022.3223260
摘要

Current continuous sign language recognition systems generally target on a single language. When it comes to the multilingual problem, existing solutions often build separate models based on the same network and then train them with their corresponding sign language corpora. Observing that different sign languages share some low-level visual patterns, we argue that it is beneficial to optimize the recognition model in a collaborative way. With this motivation, we propose the first unified framework for multilingual continuous sign language recognition. Our framework consists of a shared visual encoder for visual information encoding, multiple language-dependent sequential modules for long-range temporal dependency learning aimed at different languages, and a universal sequential module to learn the commonality of all languages. An additional language embedding is introduced to distinguish different languages within the shared temporal encoders. Further, we present a max-probability decoding method to obtain the alignment between sign videos and sign words for visual encoder refinement. We evaluate our approach on three continuous sign language recognition benchmarks, i.e., RWTH-PHOENIX-Weather, CSL and GSL-SD. The experimental results reveal that our method outperforms the individually trained recognition models. Our method also demonstrates better performance compared with state-of-the-art algorithms.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
2秒前
大海星辰完成签到,获得积分0
4秒前
叶子发布了新的文献求助30
4秒前
5秒前
6秒前
7秒前
8秒前
硕shuo发布了新的文献求助10
8秒前
9秒前
沉静雁凡完成签到,获得积分20
12秒前
12秒前
款姐关注了科研通微信公众号
13秒前
科研通AI2S应助Qiuqiu采纳,获得10
13秒前
13秒前
奶昔发布了新的文献求助10
13秒前
劲秉应助abbc采纳,获得30
14秒前
shyの煜完成签到 ,获得积分10
15秒前
orixero应助明亮随阴采纳,获得10
15秒前
16秒前
16秒前
16秒前
不配.应助EddyLalala采纳,获得10
16秒前
山水有重逢完成签到,获得积分10
19秒前
21秒前
22秒前
ziff应助L同学采纳,获得10
22秒前
22秒前
奶昔完成签到,获得积分10
23秒前
李盈盈完成签到,获得积分10
26秒前
27秒前
MissXia发布了新的文献求助50
28秒前
ding应助McbxM采纳,获得10
28秒前
小白菜加油开完成签到,获得积分20
29秒前
赘婿应助冷艳的孤晴采纳,获得10
29秒前
科研通AI2S应助动听锦程采纳,获得10
30秒前
小马甲应助QQQQQ采纳,获得10
30秒前
啊哟完成签到 ,获得积分10
31秒前
32秒前
32秒前
高分求助中
Spray / Wall-interaction Modelling by Dimensionless Data Analysis 2000
Evolution 3rd edition 1500
ALA生合成不全マウスでの糖代謝異常の分子機構解析 520
Mathematics and Finite Element Discretizations of Incompressible Navier—Stokes Flows 500
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
2-Acetyl-1-pyrroline: an important aroma component of cooked rice 500
Handbook on People's China (1957) 400
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3188878
求助须知:如何正确求助?哪些是违规求助? 2838335
关于积分的说明 8019519
捐赠科研通 2501171
什么是DOI,文献DOI怎么找? 1335362
科研通“疑难数据库(出版商)”最低求助积分说明 637508
邀请新用户注册赠送积分活动 605630