Knowledge Graph Extraction from Videos

TL;DR

This paper introduces the novel task of extracting knowledge graphs directly from videos, aiming to improve data processing and evaluation over traditional natural language annotations, and proposes a method to generate datasets for this task.

Contribution

It defines the new task of knowledge graph extraction from videos, creates datasets for it, and presents an initial deep-learning model for this purpose.

Findings

Successful dataset generation from existing video annotations

Initial model demonstrates feasibility of knowledge graph extraction

Results on MSVD* and MSR-VTT* datasets show promising performance

Abstract

Nearly all existing techniques for automated video annotation (or captioning) describe videos using natural language sentences. However, this has several shortcomings: (i) it is very hard to then further use the generated natural language annotations in automated data processing, (ii) generating natural language annotations requires to solve the hard subtask of generating semantically precise and syntactically correct natural language sentences, which is actually unrelated to the task of video annotation, (iii) it is difficult to quantitatively measure performance, as standard metrics (e.g., accuracy and F1-score) are inapplicable, and (iv) annotations are language-specific. In this paper, we propose the new task of knowledge graph extraction from videos, i.e., producing a description in the form of a knowledge graph of the contents of a given video. Since no datasets exist for this task, we also include a method to automatically generate them, starting from datasets where videos are annotated with natural language. We then describe an initial deep-learning model for knowledge graph extraction from videos, and report results on MSVD* and MSR-VTT*, two datasets obtained from MSVD and MSR-VTT using our method.