GloTSFormer: Global Video Text Spotting Transformer
This work addresses video text spotting for computer vision applications, offering a novel global approach with significant performance gains.
The paper tackles video text spotting by proposing GloTSFormer, a Transformer-based method that models tracking as global associations and uses Gaussian Wasserstein distance for morphological correlation, achieving a 56.0 MOTA on ICDAR2015 with a 4.6-point improvement over prior SOTA.
Video Text Spotting (VTS) is a fundamental visual task that aims to predict the trajectories and content of texts in a video. Previous works usually conduct local associations and apply IoU-based distance and complex post-processing procedures to boost performance, ignoring the abundant temporal information and the morphological characteristics in VTS. In this paper, we propose a novel Global Video Text Spotting Transformer GloTSFormer to model the tracking problem as global associations and utilize the Gaussian Wasserstein distance to guide the morphological correlation between frames. Our main contributions can be summarized as three folds. 1). We propose a Transformer-based global tracking method GloTSFormer for VTS and associate multiple frames simultaneously. 2). We introduce a Wasserstein distance-based method to conduct positional associations between frames. 3). We conduct extensive experiments on public datasets. On the ICDAR2015 video dataset, GloTSFormer achieves 56.0 MOTA with 4.6 absolute improvement compared with the previous SOTA method and outperforms the previous Transformer-based method by a significant 8.3 MOTA.