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 ...
|
|
Moryossef, Amit; Tsochantaridis, Ioannis; Dinn, Joe; Camgöz, Necati Cihan; Bowden, Richard; Jiang, Tao; Rios, Annette; Müller, Mathias; Ebling, Sarah. - : arXiv, 2021
|
|
Abstract:
Signed languages are visual languages produced by the movement of the hands, face, and body. In this paper, we evaluate representations based on skeleton poses, as these are explainable, person-independent, privacy-preserving, low-dimensional representations. Basically, skeletal representations generalize over an individual's appearance and background, allowing us to focus on the recognition of motion. But how much information is lost by the skeletal representation? We perform two independent studies using two state-of-the-art pose estimation systems. We analyze the applicability of the pose estimation systems to sign language recognition by evaluating the failure cases of the recognition models. Importantly, this allows us to characterize the current limitations of skeletal pose estimation approaches in sign language recognition. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2104.10166 https://arxiv.org/abs/2104.10166
|
|
BASE
|
|
Hide 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 ...
|
|
|
|
BASE
|
|
Show 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
|
|
|
|