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.
| Original language | English |
|---|---|
| Title of host publication | PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022 |
| Publisher | Association for Computing Machinery, Inc |
| Pages | 6618-6626 |
| Number of pages | 9 |
| ISBN (Electronic) | 978-1-4503-9203-7 |
| ISBN (Print) | 978-145039203-7 |
| DOIs | |
| State | Published - 10 Oct 2022 |
Publication series
| Name | Towards Causality Inference for Very Important Person Localization |
|---|
Funding
This work was supported by National Key R&D Project (2021YFC3320301), National Natural Science Foundation of China (62171325,U1803262), Key Project of Scientic Research Plan of Hubei Provincial Department of Education(No.D20211106), and Opening Foundation of National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University (No.2021SCUVS003). The numerical calculations in this paper have been done on the supercomputing system in the Supercomputing Center of Wuhan University.
Indexed by
- Scopus
- CPCI-S
Fingerprint
Dive into the research topics of 'Towards Causality Inference for Very Important Person Localization'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver