no code implementations • 15 May 2024 • Haomiao Sun, Mingjie He, Shiguang Shan, Hu Han, Xilin Chen
Although face analysis has achieved remarkable improvements in the past few years, designing a multi-task face analysis model is still challenging.
1 code implementation • 19 Dec 2023 • Yufei Cai, Yuxiang Wei, Zhilong Ji, Jinfeng Bai, Hu Han, WangMeng Zuo
To decouple irrelevant attributes (i. e., background and pose) from the subject embedding, we further present several attribute mappers that encode each image as several image-specific subject-unrelated embeddings.
no code implementations • 9 Feb 2023 • Han Li, Hu Han, S. Kevin Zhou
Most SCL methods commonly adopt a loss-based strategy of estimating data difficulty and deweighting the `hard' samples in the early training stage.
1 code implementation • ICCV 2023 • Yisheng Zhu, Hu Han, Zhengtao Yu, Guangcan Liu
Specifically, we design a Relative Visual Tempo Learning (RVTL) task to explore the motion information in intra-video clips, and an Appearance-Consistency (AC) task to learn appearance information simultaneously, resulting in more representative spatiotemporal features.
1 code implementation • CVPR 2023 • YiFan Li, Hu Han, Shiguang Shan, Xilin Chen
Then we propose a dynamic threshold strategy for each instance, based on the momentum of each instance's memorization strength in previous epochs to select and correct noisy labeled data.
1 code implementation • CVPR 2023 • Shikang Yu, Jiachen Chen, Hu Han, Shuqiang Jiang
Therefore, we propose mSARC to assure the student network can imitate not only the logit output but also the spatial activation region of the teacher network in order to alleviate the influence of unwanted noises in diverse synthetic images on distillation learning.
1 code implementation • 24 Jul 2022 • YiFan Li, Haomiao Sun, Zhaori Liu, Hu Han
As a result, we utilize AffectNet pretrained CNN to extract expression scores concatenating with expression and AU scores from ViT to obtain the final VA features.
no code implementations • 4 Apr 2022 • Xuri Ge, Joemon M. Jose, Songpei Xu, Xiao Liu, Hu Han
While the region-level feature learning from local face patches features via graph neural network can encode the correlation across different AUs, the pixel-wise and channel-wise feature learning via graph attention network can enhance the discrimination ability of AU features from global face features.
no code implementations • 13 Mar 2022 • Han Li, Long Chen, Hu Han, S. Kevin Zhou
Universal Lesion Detection (ULD) in computed tomography plays an essential role in computer-aided diagnosis.
no code implementations • 3 Mar 2022 • Xuri Ge, Joemon M. Jose, Pengcheng Wang, Arunachalam Iyer, Xiao Liu, Hu Han
In this paper, we propose a novel Adaptive Local-Global Relational Network (ALGRNet) for facial AU detection and use it to classify facial paralysis severity.
no code implementations • 24 Jun 2021 • Yuanqi Du, Quan Quan, Hu Han, S. Kevin Zhou
Pseudo-normality synthesis, which computationally generates a pseudo-normal image from an abnormal one (e. g., with lesions), is critical in many perspectives, from lesion detection, data augmentation to clinical surgery suggestion.
no code implementations • CVPR 2021 • Hao Lu, Hu Han, S. Kevin Zhou
Remote photoplethysmography (rPPG) based physiological measurement has great application values in health monitoring, emotion analysis, etc.
no code implementations • 23 Mar 2021 • Han Li, Long Chen, Hu Han, S. Kevin Zhou
Universal Lesion Detection (ULD) in computed tomography plays an essential role in computer-aided diagnosis.
Ranked #3 on Medical Object Detection on DeepLesion
1 code implementation • 16 Dec 2020 • Pengbo Liu, Hu Han, Yuanqi Du, Heqin Zhu, Yinhao Li, Feng Gu, Honghu Xiao, Jun Li, Chunpeng Zhao, Li Xiao, Xinbao Wu, S. Kevin Zhou
Due to the lack of a large-scale pelvic CT dataset with annotations, deep learning methods are not fully explored.
no code implementations • 18 Jul 2020 • Han Li, Hu Han, S. Kevin Zhou
The bounding maps (BMs) are used in two-stage anchor-based ULD frameworks to reduce the FP rate.
1 code implementation • ECCV 2020 • Xuesong Niu, Zitong Yu, Hu Han, Xiaobai Li, Shiguang Shan, Guoying Zhao
Remote physiological measurements, e. g., remote photoplethysmography (rPPG) based heart rate (HR), heart rate variability (HRV) and respiration frequency (RF) measuring, are playing more and more important roles under the application scenarios where contact measurement is inconvenient or impossible.
1 code implementation • 10 Jul 2020 • Qingsong Yao, Zecheng He, Hu Han, S. Kevin Zhou
A comprehensive evaluation on a public dataset for cephalometric landmark detection demonstrates that the adversarial examples generated by ATI-FGSM break the CNN-based network more effectively and efficiently, compared with the original Iterative FGSM attack.
no code implementations • 28 May 2020 • Jiuwen Zhu, Hu Han, S. Kevin Zhou
With the mushrooming use of computed tomography (CT) images in clinical decision making, management of CT data becomes increasingly difficult.
no code implementations • CVPR 2020 • Guoqing Wang, Hu Han, Shiguang Shan, Xilin Chen
In light of this, we propose an efficient disentangled representation learning for cross-domain face PAD.
no code implementations • 26 Mar 2020 • Xiaobai Li, Hu Han, Hao Lu, Xuesong Niu, Zitong Yu, Antitza Dantcheva, Guoying Zhao, Shiguang Shan
Remote measurement of physiological signals from videos is an emerging topic.
1 code implementation • 4 Nov 2019 • Jiancheng Cai, Hu Han, Shiguang Shan, Xilin Chen
Combined variations containing low-resolution and occlusion often present in face images in the wild, e. g., under the scenario of video surveillance.
no code implementations • 25 Oct 2019 • Xuesong Niu, Shiguang Shan, Hu Han, Xilin Chen
Recently, some methods have been proposed for remote HR estimation from face videos; however, most of them focus on well-controlled scenarios, their generalization ability into less-constrained scenarios (e. g., with head movement, and bad illumination) are not known.
1 code implementation • NeurIPS 2019 • Xuesong Niu, Hu Han, Shiguang Shan, Xilin Chen
In this work, we propose a semi-supervised approach for AU recognition utilizing a large number of web face images without AU labels and a relatively small face dataset with AU annotations inspired by the co-training methods.
1 code implementation • 16 Sep 2019 • Zeju Li, Han Li, Hu Han, Gonglei Shi, Jiannan Wang, S. Kevin Zhou
We hereby propose a decomposition generative adversarial network (DecGAN) to anatomically decompose a CXR image but with unpaired data.
1 code implementation • 4 Sep 2019 • Chao Huang, Hu Han, Qingsong Yao, Shankuan Zhu, S. Kevin Zhou
Instead of a collection of multiple models, it is highly desirable to learn a universal data representation for different tasks, ideally a single model with the addition of a minimal number of parameters steered to each task.
no code implementations • 1 Nov 2018 • Hu Han, Jie Li, Anil K. Jain, Shiguang Shan, Xilin Chen
To close the gap, we propose an efficient tattoo search approach that is able to learn tattoo detection and compact representation jointly in a single convolutional neural network (CNN) via multi-task learning.
1 code implementation • 11 Oct 2018 • Xuesong Niu, Hu Han, Shiguang Shan, Xilin Chen
We also learn a deep HR estimator (named as RhythmNet) with the proposed spatial-temporal representation, which achieves promising results on both the public-domain and our VIPL-HR HR estimation databases.
no code implementations • CVPR 2018 • Hongyu Pan, Hu Han, Shiguang Shan, Xilin Chen
Age estimation has broad application prospects of many fields, such as video surveillance, social networking, and human-computer interaction.
Ranked #3 on Age Estimation on ChaLearn 2016
no code implementations • 3 Jun 2017 • Hu Han, Anil K. Jain, Fang Wang, Shiguang Shan, Xilin Chen
In DMTL, we tackle attribute correlation and heterogeneity with convolutional neural networks (CNNs) consisting of shared feature learning for all the attributes, and category-specific feature learning for heterogeneous attributes.
Ranked #5 on Facial Attribute Classification on LFWA
no code implementations • ICCV Workshop 2015 • Xin Liu, Shaoxin Li, Meina Kan, Jie Zhang, Shuzhe Wu, Wenxian Liu, Hu Han, Shiguang Shan, Xilin Chen
Another key feature of the proposed AgeNet is that, to avoid the problem of over-fitting on small apparent age training set, we exploit a general-to-specific transfer learning scheme.
Ranked #4 on Age Estimation on ChaLearn 2015