论文标题
上下文文本块检测对场景文本理解
Contextual Text Block Detection towards Scene Text Understanding
论文作者
论文摘要
大多数现有场景文本检测器都集中于检测由于缺少上下文信息而仅捕获部分文本消息的字符或单词。为了更好地了解场景中的文本，更需要在自然阅读顺序中检测由一个或多个积分文本单元（例如字符，单词或短语）组成的上下文文本块（CTB）并传输某些完整的文本消息。本文介绍了上下文文本检测，这是一种检测CTB的新设置，以更好地理解场景中的文本。我们通过双重检测任务制定新设置，该任务首先检测到积分文本单元，然后将其分组为CTB。为此，我们设计了一种新颖的场景文本群集技术，将整体文本单元视为令牌，并将它们（属于同一CTB）分组为有序的令牌序列。此外，我们创建了两个数据集Scut-ctw-context和rects-context，以促进未来的研究，其中每个CTB都由有序的积分文本单元很好地注释。此外，我们介绍了三个指标，这些指标以局部准确性，连续性和全球准确性来衡量上下文文本检测。广泛的实验表明，我们的方法准确地检测到CTB，这些CTB有效地促进了下游任务，例如文本分类和翻译。该项目可在https://sg-vilab.github.io/publication/xue20222contextual/上获得。
Most existing scene text detectors focus on detecting characters or words that only capture partial text messages due to missing contextual information. For a better understanding of text in scenes, it is more desired to detect contextual text blocks (CTBs) which consist of one or multiple integral text units (e.g., characters, words, or phrases) in natural reading order and transmit certain complete text messages. This paper presents contextual text detection, a new setup that detects CTBs for better understanding of texts in scenes. We formulate the new setup by a dual detection task which first detects integral text units and then groups them into a CTB. To this end, we design a novel scene text clustering technique that treats integral text units as tokens and groups them (belonging to the same CTB) into an ordered token sequence. In addition, we create two datasets SCUT-CTW-Context and ReCTS-Context to facilitate future research, where each CTB is well annotated by an ordered sequence of integral text units. Further, we introduce three metrics that measure contextual text detection in local accuracy, continuity, and global accuracy. Extensive experiments show that our method accurately detects CTBs which effectively facilitates downstream tasks such as text classification and translation. The project is available at https://sg-vilab.github.io/publication/xue2022contextual/.
