A Fast Partial Video Copy Detection Using KNN and Global Feature Database
This work addresses the need for efficient detection of copied video segments, which is crucial for content moderation and copyright enforcement, representing a strong specific gain in this domain.
The authors tackled the problem of partial video copy detection by proposing a framework that uses a KNN-searchable global feature database to quickly identify candidate videos and a modified temporal network for localization, achieving a benchmark F1 score that significantly exceeds the state of the art on the VCDB dataset.
We propose a fast partial video copy detection framework in this paper. In this framework all frame features of the reference videos are organized in a KNN searchable database. Instead of scanning all reference videos, the query video segment does a fast KNN search in the global feature database. The returned results are used to generate a short list of candidate videos. A modified temporal network is then used to localize the copy segment in the candidate videos. We evaluate different choice of CNN features on the VCDB dataset. Our benchmark F1 score exceeds the state of the art by a big margin.