Privacy-Enhancing Face Obfuscation Guided by Semantic-Aware Attribution Maps

no code implementations • IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2023 • Jingzhi Li, Hua Zhang, Siyuan Liang, Pengwen Dai, Xiaochun Cao

Within this module, we introduce a pixel importance estimation model based on Shapley value to obtain a pixel-level attribution map, and then each pixel on the attribution map is aggregated into semantic facial parts, which are used to quantify the importance of different facial parts.

Face Recognition

Cognition Guided Human-Object Relationship Detection

no code implementations • journal 2023 • Zhitao Zeng, Pengwen Dai, Xuan Zhang, Lei Zhang, Xiaochun Cao

Human-object relationship detection reveals the fine-grained relationship between humans and objects, helping the comprehensive understanding of videos.

Human-Object Relationship Detection Object +1

Comprehensive Studies for Arbitrary-shape Scene Text Detection

no code implementations • 25 Jul 2021 • Pengwen Dai, Xiaochun Cao

In this paper, we carefully examine and analyze the inconsistent settings, and propose a unified framework for the bottom-up based scene text detection methods.

Scene Text Detection Text Detection

Progressive Contour Regression for Arbitrary-Shape Scene Text Detection

no code implementations • CVPR 2021 • Pengwen Dai, Sanyi Zhang, Hua Zhang, Xiaochun Cao

In the second stage, the contours of the oriented text proposals are iteratively regressed to arbitrarily shaped ones.

regression Scene Text Detection +1