Read and Attend: Temporal Localisation in Sign Language Videos

by   Gul Varol, et al.
University of Oxford

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.


page 3

page 8


BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues

Recent progress in fine-grained gesture and action classification, and m...

Quantitative Survey of the State of the Art in Sign Language Recognition

This work presents a meta study covering around 300 published sign langu...

SF-Net: Structured Feature Network for Continuous Sign Language Recognition

Continuous sign language recognition (SLR) aims to translate a signing s...

Signing Outside the Studio: Benchmarking Background Robustness for Continuous Sign Language Recognition

The goal of this work is background-robust continuous sign language reco...

Sign language segmentation with temporal convolutional networks

The objective of this work is to determine the location of temporal boun...

Towards Automatic Speech to Sign Language Generation

We aim to solve the highly challenging task of generating continuous sig...

Weakly-supervised Fingerspelling Recognition in British Sign Language Videos

The goal of this work is to detect and recognize sequences of letters si...

Please sign up or login with your details

Forgot password? Click here to reset