Read and Attend: Temporal Localisation in Sign Language Videos

• URL: http://arxiv.org/abs/2103.16481v1
• Date: Tue, 30 Mar 2021 16:39:53 GMT
• Title: Read and Attend: Temporal Localisation in Sign Language Videos
• Authors: G\"ul Varol, Liliane Momeni, Samuel Albanie, Triantafyllos Afouras, Andrew Zisserman
• Abstract summary: We train a Transformer model to ingest a continuous signing stream and output a sequence of written tokens. We show that it acquires the ability to attend to a large vocabulary of sign instances in the input sequence, enabling their localisation.
• Score: 84.30262812057994
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• SignCLIP: Connecting Text and Sign Language by Contrastive Learning [39.72545568965546]
  SignCLIP is an efficient method of learning useful visual representations for sign language processing from large-scale, multilingual video-text pairs. We pretrain SignCLIP on Spreadthesign, a prominent sign language dictionary consisting of 500 thousand video clips in up to 44 sign languages. We analyze the latent space formed by the spoken language text and sign language poses, which provides additional linguistic insights.
  arXiv  Detail & Related papers  (2024-07-01T13:17:35Z)
• Learnt Contrastive Concept Embeddings for Sign Recognition [33.72708697077754]
  We focus on explicitly creating sign embeddings that bridge the gap between sign language and spoken language. We train a vocabulary of embeddings that are based on the linguistic labels for sign video. We develop a conceptual similarity loss which is able to utilise word embeddings from NLP methods to create sign embeddings that have better sign language to spoken language correspondence.
  arXiv  Detail & Related papers  (2023-08-18T12:47:18Z)
• Automatic dense annotation of large-vocabulary sign language videos [85.61513254261523]
  We propose a simple, scalable framework to vastly increase the density of automatic annotations. We make these annotations publicly available to support the sign language research community.
  arXiv  Detail & Related papers  (2022-08-04T17:55:09Z)
• Scaling up sign spotting through sign language dictionaries [99.50956498009094]
  The focus of this work is $textitsign spotting$ - given a video of an isolated sign, our task is to identify $textitwhether$ and $textitwhere$ it has been signed in a continuous, co-articulated sign language video. We train a model using multiple types of available supervision by: (1) $textitwatching$ existing footage which is sparsely labelled using mouthing cues; (2) $textitreading$ associated subtitles which provide additional translations of the signed content. We validate the effectiveness of our approach on low
  arXiv  Detail & Related papers  (2022-05-09T10:00:03Z)
• Aligning Subtitles in Sign Language Videos [80.20961722170655]
  We train on manually annotated alignments covering over 15K subtitles that span 17.7 hours of video. We use BERT subtitle embeddings and CNN video representations learned for sign recognition to encode the two signals. Our model outputs frame-level predictions, i.e., for each video frame, whether it belongs to the queried subtitle or not.
  arXiv  Detail & Related papers  (2021-05-06T17:59:36Z)
• Watch, read and lookup: learning to spot signs from multiple supervisors [99.50956498009094]
  Given a video of an isolated sign, our task is to identify whether and where it has been signed in a continuous, co-articulated sign language video. We train a model using multiple types of available supervision by: (1) watching existing sparsely labelled footage; (2) reading associated subtitles which provide additional weak-supervision; and (3) looking up words in visual sign language dictionaries. These three tasks are integrated into a unified learning framework using the principles of Noise Contrastive Estimation and Multiple Instance Learning.
  arXiv  Detail & Related papers  (2020-10-08T14:12:56Z)
• BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues [106.21067543021887]
  We show how to use mouthing cues from signers to obtain high-quality annotations from video data. The BSL-1K dataset is a collection of British Sign Language (BSL) signs of unprecedented scale.
  arXiv  Detail & Related papers  (2020-07-23T16:59:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.