Search Results for author: Linzhi Huang

Found 6 papers, 3 papers with code

MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs

no code implementations13 Jun 2024 Xuannan Liu, Zekun Li, Peipei Li, Shuhan Xia, Xing Cui, Linzhi Huang, Huaibo Huang, Weihong Deng, Zhaofeng He

Current multimodal misinformation detection (MMD) methods often assume a single source and type of forgery for each sample, which is insufficient for real-world scenarios where multiple forgery sources coexist.

Misinformation

CornerFormer: Boosting Corner Representation for Fine-Grained Structured Reconstruction

no code implementations14 Apr 2023 Hongbo Tian, Yulong Li, Linzhi Huang, Xu Ling, Yue Yang, Jiani Hu

Current transformer-based approaches tackle this challenging problem in a two-stage manner, which detect corners in the first model and classify the proposed edges (corner-pairs) in the second model.

Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attention

no code implementations5 Apr 2023 Linzhi Huang, Mei Wang, Jiahao Liang, Weihong Deng, Hongzhi Shi, Dongchao Wen, Yingjie Zhang, Jian Zhao

Specifically, we use the gradient attention map (GAM) of the face recognition network to track the sensitive facial regions and make the GAMs of different races tend to be consistent through adversarial learning.

Face Recognition

Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module

1 code implementation CVPR 2023 Linzhi Huang, Yulong Li, Hongbo Tian, Yue Yang, Xiangang Li, Weihong Deng, Jieping Ye

The previous method ignored two problems: (i) When conducting interactive training between large model and lightweight model, the pseudo label of lightweight model will be used to guide large models.

2D Human Pose Estimation Pose Estimation +2

DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose Estimation

1 code implementation19 Jul 2022 Linzhi Huang, Jiahao Liang, Weihong Deng

To solve this problem, we propose a pose augmentation solution via DH forward kinematics model, which we call DH-AUG. We observe that the previous work is all based on single-frame pose augmentation, if it is directly applied to video pose estimator, there will be several previously ignored problems: (i) angle ambiguity in bone rotation (multiple solutions); (ii) the generated skeleton video lacks movement continuity.

3D Human Pose Estimation Diversity

Cannot find the paper you are looking for? You can Submit a new open access paper.