Re:Cognize -- 开放集漫画角色再识别
Re:Cognize -- Open-Set Comic Character Re-Identification
- University of Central Florida（中佛罗里达大学）
- Institute of Artificial Intelligence, University of Central Florida（中佛罗里达大学人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出Re:Cognize基准，以开放集顺序方式评估漫画角色再识别，发现识别已解决但接受度是瓶颈，并推出无需数据拟合的ReCast方法，能恢复完美标签三分之二性能。
AI中文摘要：
漫画读者在一页上遇到一个角色，一百页后一眼就能认出他们，而无需事先获得角色名单。漫画角色的再识别同样要求开放集和顺序性：页面按阅读顺序以流的形式到达，新面孔在任何人命名之前出现，角色阵容随着故事的阅读而逐步构建。Re:Cognize 评估的是在阅读故事过程中的识别，而不是针对预先提供的角色名单：在单一查询流上设置四种协议，从封闭集检索到模型必须自行构建和扩展的角色阵容。令人惊讶的是模型失败的地方。识别几乎已解决：每个角色一张参考图像的性能已经与预先构建的图库相当。而知道该相信什么则不然：一个自行添加匹配项的模型会使角色阵容变差，而同样的扩展若带有正确标签，则会使 top-1 准确率提高超过二十个百分点。瓶颈在于接受度，而非视觉能力，一次比较即可决定：当且仅当新增项在其接管的查询上比现有阵容更正确时，添加才是有益的。该比较无需拟合任何参数，并且在一个新语料库的一半上测量，能正确预测另一半。ReCast 在无数据拟合的情况下将其付诸实践：每个角色一个运行平均值的角色表，仅在页面本身为裁剪图像背书时才进行扩展。它恢复了完美标签所能达到的三分之一到三分之二的性能，具体取决于角色阵容是从随机示例开始还是从首次出现开始。Re:Cognize 衡量模型是否能随读随认；ReCast 是一个能做到这一点的角色阵容。我们的主张涉及身份维护，即识别已遇到的角色；新角色的出现是在固定参考规则下作为诊断指标进行测量的，我们对此不提出任何方法。
英文摘要：
A manga reader meets a character on one page and knows them on sight a hundred pages later, without ever being handed a cast list. Re-identifying comic characters demands the same, open-set and sequential: pages arrive as a stream in reading order, new faces appear before anyone names them, and the cast is assembled as the story is read. $\textbf{Re:Cognize}$ evaluates recognition as the story is read, not against a cast handed over in advance: four protocols on one query stream, from closed-set retrieval to a cast the model must build and grow itself. The surprise is where models fail. Recognising is close to solved: one reference image per character already ranks as well as a gallery built in advance. Knowing what to believe is not: a model that adds its own matches makes its cast worse, while the same growth with correct labels would gain over twenty points of top-1 accuracy. The bottleneck is acceptance, not vision, and one comparison decides it: an addition pays exactly when it is right more often than the cast already was on the queries it takes over. The comparison has nothing to fit, and measured on half of a new corpus it calls the other half correctly. $\textbf{ReCast}$ puts it to work with nothing fitted on data: a cast sheet of one running average per character, grown only where the page itself vouches for a crop. It recovers a third to two thirds of what perfect labels would, depending on whether the cast starts from random examples or from first appearances. Re:Cognize measures whether a model can read along; ReCast is a cast that does. Our claims are on identity maintenance, recognising characters already met; the emergence of new ones is measured as a diagnostic under a fixed reference rule, and we propose no method for it.
