Identity-aware facial expression recognition in compressed video

Xiaofeng Liu, X Han, Jia You, L Kong, Jun Lu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

17 Citations (Scopus)


This paper targets to explore the inter-subject variations eliminated facial expression representation in the compressed video domain. Most of the previous methods process the RGB images of a sequence, while the off-the-shelf and valuable expression-related muscle movement already embedded in the compression format. In the up to two orders of magnitude compressed domain, we can explicitly infer the expression from the residual frames and possible to extract identity factors from the I frame with a pre-trained face recognition network. By enforcing the marginal independent of them, the expression feature is expected to be purer for the expression and be robust to identity shifts. We do not need the identity label or multiple expression samples from the same person for identity elimination. Moreover, when the apex frame is annotated in the dataset, the complementary constraint can be further added to regularize the feature-level game. In testing, only the compressed residual frames are required to achieve expression prediction. Our solution can achieve comparable or better performance than the recent decoded image based methods on the typical FER benchmarks with about 3× faster inference with compressed data.

Original languageEnglish
Title of host publicationProceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
Number of pages7
ISBN (Electronic)9781728188089
Publication statusPublished - 2020

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Identity-aware facial expression recognition in compressed video'. Together they form a unique fingerprint.

Cite this