In this paper, we present our solution to the Cross-View Isolated Sign Language Recognition (CV-ISLR) challenge held at WWW 2025. CV-ISLR addresses a critical issue in traditional Isolated Sign Language Recognition (ISLR), where existing datasets predominantly capture sign language videos from a frontal perspective, while real-world camera angles often vary. To accurately recognize sign language from different viewpoints, models must be capable of understanding gestures from multiple angles, making cross-view recognition challenging. To address this, we explore the advantages of ensemble learning, which enhances model robustness and generalization across diverse views. Our approach, built on a multi-dimensional Video Swin Transformer model, leverages this ensemble strategy to achieve competitive performance. Finally, our solution ranked 3rd in both the RGB-based ISLR and RGB-D-based ISLR tracks, demonstrating the effectiveness in handling the challenges of cross-view recognition. The code is available at: https://github.com/Jiafei127/CV_ISLR_WWW2025.
@article{arxiv.2502.02196,
title = {Exploiting Ensemble Learning for Cross-View Isolated Sign Language Recognition},
author = {Fei Wang and Kun Li and Yiqi Nie and Zhangling Duan and Peng Zou and Zhiliang Wu and Yuwei Wang and Yanyan Wei},
journal= {arXiv preprint arXiv:2502.02196},
year = {2025}
}
Comments
3rd Place in Cross-View Isolated Sign Language Recognition Challenge at WWW 2025