Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts
This addresses the challenge of retrieving images with Chinese text in complex real-world layouts, which is a domain-specific problem for computer vision and text retrieval applications, representing a novel method for a known bottleneck.
The paper tackles the problem of Chinese scene text retrieval in diverse layouts by establishing a new benchmark (DL-CSVTR) and proposing a model (CSTR-CLIP) that integrates global visual information with multi-granularity alignment training, resulting in an 18.82% accuracy improvement over the previous state-of-the-art and faster inference speed.
Chinese scene text retrieval is a practical task that aims to search for images containing visual instances of a Chinese query text. This task is extremely challenging because Chinese text often features complex and diverse layouts in real-world scenes. Current efforts tend to inherit the solution for English scene text retrieval, failing to achieve satisfactory performance. In this paper, we establish a Diversified Layout benchmark for Chinese Street View Text Retrieval (DL-CSVTR), which is specifically designed to evaluate retrieval performance across various text layouts, including vertical, cross-line, and partial alignments. To address the limitations in existing methods, we propose Chinese Scene Text Retrieval CLIP (CSTR-CLIP), a novel model that integrates global visual information with multi-granularity alignment training. CSTR-CLIP applies a two-stage training process to overcome previous limitations, such as the exclusion of visual features outside the text region and reliance on single-granularity alignment, thereby enabling the model to effectively handle diverse text layouts. Experiments on existing benchmark show that CSTR-CLIP outperforms the previous state-of-the-art model by 18.82% accuracy and also provides faster inference speed. Further analysis on DL-CSVTR confirms the superior performance of CSTR-CLIP in handling various text layouts. The dataset and code will be publicly available to facilitate research in Chinese scene text retrieval.