• Home
  • Search
  • Read and Attend: Temporal Localisation in Sign Language Videos
  • Cite Icon34
  • https://doi.org/10.1109/cvpr46437.2021.01658Copy DOI Icon

Read and Attend: Temporal Localisation in Sign Language Videos

  • Jun 1, 2021
  • Gul Varol +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The objective of this work is to annotate sign instances across a broad vocabulary in continuous sign language. We train a Transformer model to ingest a continuous signing stream and output a sequence of written tokens on a large-scale collection of signing footage with weakly-aligned subtitles. We show that through this training it acquires the ability to attend to a large vocabulary of sign instances in the input sequence, enabling their localisation. Our contributions are as follows: (1) we demonstrate the ability to leverage large quantities of continuous signing videos with weakly-aligned subtitles to localise signs in continuous sign language; (2) we employ the learned attention to automatically generate hundreds of thousands of annotations for a large sign vocabulary; (3) we collect a set of 37K manually verified sign instances across a vocabulary of 950 sign classes to support our study of sign language recognition; (4) by training on the newly annotated data from our method, we outperform the prior state of the art on the BSL-1K sign language recognition benchmark.

Similar Papers
  • Conference Article
  • Citations89

Transition movement models for large vocabulary continuous sign language recognition

  • Jan 01, 2004
  • Wen Gao +3
  • Conference Article
  • Citations13

An encoding and identification approach for the static sign language recognition

  • Jul 01, 2012
  • Fu-Hua Chou +1
  • Video Transcripts

Recognizing American Sign Language Nonmanual Signal Grammar Errors in Continuous Videos

  • Dec 29, 2020
  • Underline Science Inc.
  • Elahe Vahdani
  • Research Article
  • Citations1

Znakovni jezici - nekad i sad

  • Jan 01, 2020
  • Зборник радова Филозофског факултета у Приштини
  • Ljubica Isaković +2
  • Research Article

Continuous Chinese Sign Language Recognition Using Millimeter-Wave Radar with DeepSeek Semantic Enhancement

  • Jan 01, 2025
  • IEEE Sensors Journal
  • Lei Zhang +5
  • Conference Article

A Continuous Sign Language Recognition Method Based on Temporal Modeling and Semantic Alignment

  • Nov 14, 2025
  • J Li +5
  • Research Article
  • Citations4

MyWSL: Malaysian words sign language dataset

  • Jun 22, 2023
  • Data in Brief
  • Rina Tasia Johari +3
  • Research Article
  • Citations7

A lightweight network-based sign language robot with facial mirroring and speech system

  • Oct 21, 2024
  • Expert Systems With Applications
  • Na Liu +8
  • Conference Article
  • Citations11

A Signer-Independent Sign Language Recognition System Based on the Weighted KNN/HMM

  • Aug 01, 2015
  • Siqi Liu +1
  • Research Article
  • Citations1

A STUDY OF WORLDWIDE PATTERNS IN ALPHABET SIGN LANGUAGE RECOGNITION USING CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS

  • Feb 12, 2025
  • Jurnal Teknik Informatika (Jutif)
  • Aris Rakhmadi +2
  • Conference Article
  • Citations6

Masked Batch Normalization to Improve Tracking-Based Sign Language Recognition Using Graph Convolutional Networks

  • Dec 15, 2021
  • Natsuki Takayama +2
  • Research Article
  • Citations12

Language policies, language rights, and sign languages: A critique of disability-based approaches

  • Feb 14, 2019
  • Critical Inquiry in Language Studies
  • Timothy Reagan
  • Conference Article
  • Citations26

Continuous gesture recognition system for Korean sign language based on fuzzy logic and hidden Markov model

  • Aug 07, 2002
  • Jung-Bae Kim +3
  • Research Article
  • Citations23

Sign Language Recognition by using Spatio-Temporal Features

  • Jan 01, 2024
  • Procedia Computer Science
  • Renjith S +2
  • Research Article
  • Citations24

A survey on recent advances in Sign Language Production

  • Dec 09, 2023
  • Expert Systems with Applications
  • Razieh Rastgoo +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.