1 |
Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Content4All Open Research Sign Language Translation Datasets ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Evaluating the Immediate Applicability of Pose Estimation for Sign Language Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Content4All Open Research Sign Language Translation Datasets ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Looking for the Signs: Identifying Isolated Sign Instances in Continuous Video Footage ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Evaluating the Immediate Applicability of Pose Estimation for Sign Language Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
AnonySIGN: Novel Human Appearance Synthesis for Sign Language Video Anonymisation ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Skeletal Graph Self-Attention: Embedding a Skeleton Inductive Bias into Sign Language Production ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
A Phonology-based Approach for Isolated Sign Production Assessment in Sign Language
|
|
|
|
In: http://infoscience.epfl.ch/record/285034 (2021)
|
|
BASE
|
|
Show details
|
|
12 |
Progressive Transformers for End-to-End Sign Language Production ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Everybody Sign Now: Translating Spoken Language to Photo Realistic Sign Language Video ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Adversarial Training for Multi-Channel Sign Language Production ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Multi-channel Transformers for Multi-articulatory Sign Language Translation ...
|
|
|
|
Abstract:
Sign languages use multiple asynchronous information channels (articulators), not just the hands but also the face and body, which computational approaches often ignore. In this paper we tackle the multi-articulatory sign language translation task and propose a novel multi-channel transformer architecture. The proposed architecture allows both the inter and intra contextual relationships between different sign articulators to be modelled within the transformer network itself, while also maintaining channel specific information. We evaluate our approach on the RWTH-PHOENIX-Weather-2014T dataset and report competitive translation performance. Importantly, we overcome the reliance on gloss annotations which underpin other state-of-the-art approaches, thereby removing future need for expensive curated datasets. ...
|
|
Keyword:
Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2009.00299 https://dx.doi.org/10.48550/arxiv.2009.00299
|
|
BASE
|
|
Hide details
|
|
17 |
Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Adversarial Training for Multi-Channel Sign Language Production
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Multi-channel Transformers for Multi-articulatory Sign Language Translation
|
|
|
|
BASE
|
|
Show details
|
|
|
|