ICASSP 2023accepted0 citations

Lightweight Fisher Vector Transfer Learning for Video Deduplication

Chris Henry, Rijun Liao, Ruiyuan Lin, Zhebin Zhang, Hongyu Sun, Zhu Li

Abstract

Video deduplication in cloud and on devices is a key challenge for storage and communication efficiency. The lifetime of video content creation, communication/sharing, and consumption can generate multiple versions of the same content with variations in coding and editing effects. In this work, we develop a lightweight and robust deduplication feature based on the fisher vector aggregation of Scale-Invariant Feature Transform (SIFT) keypoints. The fisher vector representation is used for a deduplication transfer learning process that utilizes a lightweight Multilayer Perceptron (MLP) network with center loss to learn a compact and distinctive feature. Simulation on the CC_WEB_VIDEO dataset demonstrated that the proposed feature is extremely robust in deduplication with respect to typical editing effects and coding/transcoding degenerations while being computationally very lightweight compared to other solutions.

BibTeX
@inproceedings{icassp2023_lightweightfishe,
  title = {Lightweight Fisher Vector Transfer Learning for Video Deduplication},
  author = {Chris Henry and Rijun Liao and Ruiyuan Lin and Zhebin Zhang and Hongyu Sun and Zhu Li},
  booktitle = {ICASSP 2023},
  year = {2023}
}
Lightweight Fisher Vector Transfer Learning for Video Deduplication · ICASSP 2023