Unambiguous Scene Text Segmentation with Referring Expression Comprehension

Text instance provides valuable information for the understanding and interpretation of natural scenes. The rich, precise high-level semantics embodied in the text could be beneficial for understanding the world around us, and empower a wide range of real-world applications. While most recent visual phrase grounding approaches focus on general objects, this paper explores extracting designated texts and predicting unambiguous scene text segmentation mask, i.e. scene text segmentation from natural language descriptions (referring expressions) like orange text on a little boy in black swinging a bat. The solution of this novel problem enables accurate segmentation of scene text instances from the complex background. In our proposed framework, a unified deep network jointly models visual and linguistic information by encoding both region-level and pixel-level visual features of natural scene images into spatial feature maps, and then decode them into saliency response map of text instances. To conduct quantitative evaluations, we establish a new scene text referring expression segmentation dataset: COCO-CharRef. Experimental results demonstrate the effectiveness of the proposed framework on the text instance segmentation task. By combining image-based visual features with language-based textual explanations, our framework outperforms baselines that are derived from state-of-the-art text localization and natural language object retrieval methods on COCO-CharRef dataset.