-
How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language
Sign Language is the primary means of communication for the majority of ...
read it
-
Towards Large-Scale Data Mining for Data-Driven Analysis of Sign Languages
Access to sign language data is far from adequate. We show that it is po...
read it
-
ASL Recognition with Metric-Learning based Lightweight Network
In the past decades the set of human tasks that are solved by machines w...
read it
-
Quantitative Survey of the State of the Art in Sign Language Recognition
This work presents a meta study covering around 300 published sign langu...
read it
-
Exploiting the Logits: Joint Sign Language Recognition and Spell-Correction
Machine learning techniques have excelled in the automatic semantic anal...
read it
-
BosphorusSign22k Sign Language Recognition Dataset
Sign Language Recognition is a challenging research domain. It has recen...
read it
-
Improving American Sign Language Recognition with Synthetic Data
There is a need for real-time communication between the deaf and hearing...
read it
BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues
Recent progress in fine-grained gesture and action classification, and machine translation, point to the possibility of automated sign language recognition becoming a reality. A key stumbling block in making progress towards this goal is a lack of appropriate training data, stemming from the high complexity of sign annotation and a limited supply of qualified annotators. In this work, we introduce a new scalable approach to data collection for sign recognition in continuous videos. We make use of weakly-aligned subtitles for broadcast footage together with a keyword spotting method to automatically localise sign-instances for a vocabulary of 1,000 signs in 1,000 hours of video. We make the following contributions: (1) We show how to use mouthing cues from signers to obtain high-quality annotations from video data - the result is the BSL-1K dataset, a collection of British Sign Language (BSL) signs of unprecedented scale; (2) We show that we can use BSL-1K to train strong sign recognition models for co-articulated signs in BSL and that these models additionally form excellent pretraining for other sign languages and benchmarks - we exceed the state of the art on both the MSASL and WLASL benchmarks. Finally, (3) we propose new large-scale evaluation sets for the tasks of sign recognition and sign spotting and provide baselines which we hope will serve to stimulate research in this area.
READ FULL TEXT
Comments
There are no comments yet.