HandReader: Advanced Techniques for Efficient Fingerspelling Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Korotaev, Pavel, Surovtsev, Petr, Kapitanov, Alexander, Kvanchiani, Karina, Nagaev, Aleksandr
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909611195367424
author Korotaev, Pavel
Surovtsev, Petr
Kapitanov, Alexander
Kvanchiani, Karina
Nagaev, Aleksandr
author_facet Korotaev, Pavel
Surovtsev, Petr
Kapitanov, Alexander
Kvanchiani, Karina
Nagaev, Aleksandr
contents Fingerspelling is a significant component of Sign Language (SL), allowing the interpretation of proper names, characterized by fast hand movements during signing. Although previous works on fingerspelling recognition have focused on processing the temporal dimension of videos, there remains room for improving the accuracy of these approaches. This paper introduces HandReader, a group of three architectures designed to address the fingerspelling recognition task. HandReader$_{RGB}$ employs the novel Temporal Shift-Adaptive Module (TSAM) to process RGB features from videos of varying lengths while preserving important sequential information. HandReader$_{KP}$ is built on the proposed Temporal Pose Encoder (TPE) operated on keypoints as tensors. Such keypoints composition in a batch allows the encoder to pass them through 2D and 3D convolution layers, utilizing temporal and spatial information and accumulating keypoints coordinates. We also introduce HandReader_RGB+KP - architecture with a joint encoder to benefit from RGB and keypoint modalities. Each HandReader model possesses distinct advantages and achieves state-of-the-art results on the ChicagoFSWild and ChicagoFSWild+ datasets. Moreover, the models demonstrate high performance on the first open dataset for Russian fingerspelling, Znaki, presented in this paper. The Znaki dataset and HandReader pre-trained models are publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2505_10267
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HandReader: Advanced Techniques for Efficient Fingerspelling Recognition
Korotaev, Pavel
Surovtsev, Petr
Kapitanov, Alexander
Kvanchiani, Karina
Nagaev, Aleksandr
Computer Vision and Pattern Recognition
Machine Learning
Fingerspelling is a significant component of Sign Language (SL), allowing the interpretation of proper names, characterized by fast hand movements during signing. Although previous works on fingerspelling recognition have focused on processing the temporal dimension of videos, there remains room for improving the accuracy of these approaches. This paper introduces HandReader, a group of three architectures designed to address the fingerspelling recognition task. HandReader$_{RGB}$ employs the novel Temporal Shift-Adaptive Module (TSAM) to process RGB features from videos of varying lengths while preserving important sequential information. HandReader$_{KP}$ is built on the proposed Temporal Pose Encoder (TPE) operated on keypoints as tensors. Such keypoints composition in a batch allows the encoder to pass them through 2D and 3D convolution layers, utilizing temporal and spatial information and accumulating keypoints coordinates. We also introduce HandReader_RGB+KP - architecture with a joint encoder to benefit from RGB and keypoint modalities. Each HandReader model possesses distinct advantages and achieves state-of-the-art results on the ChicagoFSWild and ChicagoFSWild+ datasets. Moreover, the models demonstrate high performance on the first open dataset for Russian fingerspelling, Znaki, presented in this paper. The Znaki dataset and HandReader pre-trained models are publicly available.
title HandReader: Advanced Techniques for Efficient Fingerspelling Recognition
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2505.10267