Towards Causality Inference for Very Important Person Localization
Lists
Only you see this
Abstract
Very Important Person Localization (VIPLoc) aims at detecting certain individuals in a given image, who are more attractive than others in the image. Existing uncontrolled VIPLoc benchmark assumes that the image has one single VIP, which is not suitable for actual application scenarios when multiple VIPs or no VIPs appear in the image. In this paper, we re-built a complex uncontrolled conditions (CUC) dataset to make the VIPLoc closer to the actual situation, containing no, single, and multiple VIPs. Existing methods use the hand-designed and deep learning strategies to extract the features of persons and analyze the differences between VIPs and other persons from the perspective of statistics. They are not explainable as to why the VIP located this output for that input. Thus, there exist the severe performance degradation when we use these models in real-world VIPLoc. Specifically, we establish a causal inference framework that unpacks the causes of previous methods and derives a new principled solution for VIPLoc. It treats the scene as confounding factor, allowing the ever-elusive confounding effects to be eliminated and the essential determinants to be uncovered. Through extensive experiments, our method outperforms the state-of-the-art methods on public VIPLoc datasets and the re-built CUC dataset.
BibTeX
@inproceedings{wang2022towards,
author = {Xiao Wang and Zheng Wang and Wu Liu and Xin Xu and Qijun Zhao and Shin'ichi Satoh},
title = {{Towards Causality Inference for Very Important Person Localization}},
booktitle = {ACM Multimedia},
year = {2022},
doi = {10.1145/3503161.3548014},
}Loading related content...