Zero-Shot Character Identification and Speaker Prediction in Comics via Iterative Multimodal Fusion

arXiv:2404.13993v1 Announce Type: cross
Abstract: Recognizing characters and predicting speakers of dialogue are critical for comic processing tasks, such as voice generation or translation. However, because characters vary by comic title, supervised learning approaches like training character classifiers which require specific annotations for each comic title are infeasible. This motivates us to propose a novel zero-shot approach, allowing machines to identify characters and predict speaker names based solely on unannotated comic images. In spite of their importance in real-world applications, …

abstract annotations arxiv characters classifiers comics cs.cv cs.mm dialogue fusion however identification iterative multimodal prediction processing speaker speakers supervised learning tasks training translation type via voice voice generation zero-shot