Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books
This addresses the challenge of creating semantically detailed visual explanations for multimedia content, though it appears incremental in combining existing embedding techniques.
This paper tackles the problem of aligning movies with their corresponding books to generate rich visual explanations that go beyond standard captions, achieving good quantitative performance on movie/book alignment tasks.
Books are a rich source of both fine-grained information, how a character, an object or a scene looks like, as well as high-level semantics, what someone is thinking, feeling and how these states evolve through a story. This paper aims to align books to their movie releases in order to provide rich descriptive explanations for visual content that go semantically far beyond the captions available in current datasets. To align movies and books we exploit a neural sentence embedding that is trained in an unsupervised way from a large corpus of books, as well as a video-text neural embedding for computing similarities between movie clips and sentences in the book. We propose a context-aware CNN to combine information from multiple sources. We demonstrate good quantitative performance for movie/book alignment and show several qualitative examples that showcase the diversity of tasks our model can be used for.