HAKA: HierArchical Knowledge Acquisition in a sign language tutor

Proceedings Paper Computer Science, Artificial Intelligence

Sign Pose-based Transformer for Word-level Sign Language Recognition

Matyas Bohacek et al.

Summary: This paper presents a word-level sign language recognition system based on the Transformer model. The system aims to be computationally efficient for usage on handheld devices. The recognition is based on estimating the pose of the human body using 2D landmark locations. The proposed system achieves state of the art results on WLASL and LSA64 datasets, with significant improvements in accuracy through pose normalization and augmentation techniques.

2022 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW 2022) (2022)

Add to Collection

Review Education & Educational Research

Types, purposes, and effectiveness of state-of-the-art technologies for second and foreign language learning

Ruofei Zhang et al.

Summary: Digital technologies have been widely used in language learning, with the most advanced ones including mobile learning, multimedia learning and socialization technologies, speech-to-text and text-to-speech recognition, and digital-game-based learning. The purposes and benefits of these technologies include promoting practices, delivering instructional content, facilitating interactions, and restructuring teaching approaches. Overall, these state-of-the-art technologies have a positive impact on language teaching and learning.

COMPUTER ASSISTED LANGUAGE LEARNING (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Benchmarking deep neural network approaches for Indian Sign Language recognition

Ashish Sharma et al.

Summary: This paper discusses a comparative analysis of gesture recognition techniques, testing three models on an Indian Sign Language dataset. The hierarchical model outperformed the other two, achieving 98.52% accuracy for one-hand gestures and 97% for two-hand gestures.

NEURAL COMPUTING & APPLICATIONS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Quantitative analysis of robot gesticulation behavior

Unai Zabala et al.

Summary: This paper conducts a quantitative analysis on generated gestures using Principal Coordinate Analysis, procrustes statistics, and a new Frechet Gesture Distance method, aiming to assess the fidelity and originality of the generated gestures.

AUTONOMOUS ROBOTS (2021)

Add to Collection

Review Computer Science, Artificial Intelligence

Sign Language Recognition: A Deep Survey

Razieh Rastgoo et al.

Summary: Sign language, as a different form of communication language, is crucial for large groups in society, and visual sign language recognition using deep learning approaches has shown significant improvement in recent years. Despite the overall trend indicating increased accuracy, there are still some challenges that need to be addressed in the field of sign language recognition.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

RNN-Transducer based Chinese Sign Language Recognition

Liqing Gao et al.

Summary: This paper proposes a new RNN-Transducer based SLR framework, named H2SNet, which addresses the issues of CTC-based SLR methods by utilizing visual hierarchy transcription network and lexical prediction network. Extensive experiments validate the effectiveness and superiority of the proposed approach over state-of-the-art methods.

NEUROCOMPUTING (2021)

Add to Collection

Article Cultural Studies

Beyond Human: Deep Learning, Explainability and Representation

M. Beatrice Fazi

Summary: This article discusses the opacity of deep learning and artificial intelligence technologies, challenges related abstract operations, and reconsiders the explainability of these technologies. The author analyzes how technoscience and technoculture re-present algorithmic procedures, and addresses explainability using philosophical concepts.

THEORY CULTURE & SOCIETY (2021)

Add to Collection

Article Computer Science, Artificial Intelligence