Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books

TL;DR

This paper introduces a method to align movies with their corresponding books using neural embeddings, enabling richer visual explanations that incorporate detailed semantic information from literature.

Contribution

It presents a novel approach combining unsupervised sentence embeddings and video-text neural embeddings for accurate movie-book alignment.

Findings

Good quantitative alignment performance

Qualitative examples show diverse application potential

Effective combination of multiple information sources

Abstract

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.