Read and Attend: Temporal Localisation in Sign Language Videos
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Bukva: Russian Sign Language Alphabet
HandReader: Advanced Techniques for Efficient Fingerspelling Recognition
Hierarchical Sub-action Tree for Continuous Sign Language Recognition
SignBart -- New approach with the skeleton sequence for Isolated Sign language Recognition
SLRNet: A Real-Time LSTM-Based Sign Language Recognition System
Transfer Learning from Visual Speech Recognition to Mouthing Recognition in German Sign Language
토론
이 논문과 연결된 포럼 글이 아직 없습니다.