Multi-Modal Zero-Shot Sign Language Recognition
arXiv:2109.00796
Abstract
Zero-Shot Learning (ZSL) has rapidly advanced in recent years. Towards overcoming the annotation bottleneck in the Sign Language Recognition (SLR), we explore the idea of Zero-Shot Sign Language Recognition (ZS-SLR) with no annotated visual examples, by leveraging their textual descriptions. In this way, we propose a multi-modal Zero-Shot Sign Language Recognition (ZS-SLR) model harnessing from the complementary capabilities of deep features fused with the skeleton-based ones. A Transformer-based model along with a C3D model is used for hand detection and deep features extraction, respectively. To make a trade-off between the dimensionality of the skeletonbased and deep features, we use an Auto-Encoder (AE) on top of the Long Short Term Memory (LSTM) network. Finally, a semantic space is used to map the visual features to the lingual embedding of the class labels, achieved via the Bidirectional Encoder Representations from Transformers (BERT) model. Results on four large-scale datasets, RKS-PERSIANSIGN, First-Person, ASLVID, and isoGD, show the superiority of the proposed model compared to state-of-the-art alternatives in ZS-SLR.
arXiv commentarXiv admin note: text overlap with arXiv:2108.10059
References in corpus (7)
- YOLOv3: An Incremental Improvement
- Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation
- TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation
- Action2Vec: A Crossmodal Embedding Approach to Action Learning
- TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition
- Semantic Embedding Space for Zero-Shot Action Recognition
- Towards Universal Representation for Unseen Action Recognition