Maxim Arap — accepted AI-conference papers

2023

LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization

Sheng Liu, Cong Phuoc Huynh, Cong Chen, Maxim Arap, Raffay Hamid

CVPR 2023poster

We present a simple yet effective self-supervised pretraining method for image harmonization which can leverage large-scale unannotated image datasets. To achieve this goal, we first generate pre-training data online with our Label-Efficient Masked Region Transform (LEMaRT) pipeline. Given an image,…

Cited by 23 Source ↗PDF ↗Scholar ↗

2023

Movies2Scenes: Using Movie Metadata To Learn Scene Representation

Shixing Chen, Chun-Hao Liu, Xiang Hao, Xiaohan Nie, Maxim Arap, Raffay Hamid

CVPR 2023poster

Understanding scenes in movies is crucial for a variety of applications such as video moderation, search, and recommendation. However, labeling individual scenes is a time-consuming process. In contrast, movie level metadata (e.g., genre, synopsis, etc.) regularly gets produced as part of the film p…

Cited by 19 Source ↗PDF ↗Scholar ↗