Search Results - "Ge, Shiming"

Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation by Ge, Shiming, Zhao, Shengwei, Li, Chenyu, Li, Jia

“…Typically, the deployment of face recognition models in the wild needs to identify low-resolution faces with extremely low computational cost. To address this…”
Get full text

Detecting Masked Faces in the Wild with LLE-CNNs by Shiming Ge, Jia Li, Qiting Ye, Zhao Luo

“…Detecting faces with occlusions is a challenging task due to two main reasons: 1) the absence of large datasets of masked faces, and 2) the absence of facial…”
Get full text

Double-Blinded Finder: a two-side secure children face recognition system by Jin, Xin, Lei, Jicheng, Ge, Shiming, Song, Chenggen, Yu, Haoyang, Wu, Chuanqiang

“…When taking photos of a suspicious missing child in the street and posting them to the social network is becoming a feasible way to find missing children, the…”
Get full text

ILGNet: inception modules with connected local and global features for efficient image aesthetic quality classification using domain adaptation by Xin Jin, Le Wu, Xiaodong Li, Xiaokun Zhang, Jingying Chi, Siwei Peng, Shiming Ge, Geng Zhao, Shuying Li

“…In this study, the authors address a challenging problem of aesthetic image classification, which is to label an input image as high‐ or low‐aesthetic quality…”
Get full text

Structure injected weight normalization for training deep networks by Yuan, Xu, Shen, Xiangjun, Mehta, Sumet, Li, Teng, Ge, Shiming, Zha, Zhengjun

“…Weight normalization (WN) can help to stabilize the distribution of activations over layers, which boost the performance of DNNs in generalization. In this…”
Get full text

Adaptive Wavelet Filter With Edge Compensation for Remote Sensing Image Denoising by Chen, Boyang, Feng, Xuan, Wu, Ronghua, Guo, Qiang, Wang, Xi, Ge, Shiming

“…Advanced Geostationary Radiation Imager (AGRI) is one of the main payloads of the second-generation geostationary orbit meteorological satellite, FengYun-4A…”
Get full text

3D textured model encryption via 3D Lu chaotic mapping by Jin, Xin, Zhu, Shuyun, Xiao, Chaoen, Sun, Hongbo, Li, Xiaodong, Zhao, Geng, Ge, Shiming

“…In the emerging Virtual/Augmented Reality（VR/AR） era, three dimensional（3 D） content will be popularized just as images and videos today. The security and…”
Get full text

Image editing by object-aware optimal boundary searching and mixed-domain composition by Ge, Shiming, Jin, Xin, Ye, Qiting, Luo, Zhao, Li, Qiang

“…When combining very different images which often contain complex objects and backgrounds, producing consistent compositions is a challenging problem requiring…”
Get full text

Discriminative Multiview Nonnegative Matrix Factorization for Classification by Ou, Weihua, Gou, Jianping, Zhou, Quan, Ge, Shiming, Long, Fei

“…Multiview nonnegative matrix has shown many promising applications in computer vision and pattern recognition. However, most existing works focus on view…”
Get full text

Geometry-Based Global Alignment for GSMS Remote Sensing Images by Zeng, Dan, Fang, Rui, Ge, Shiming, Li, Shuying, Zhang, Zhijiang

“…Alignment of latitude and longitude for all pixels is important for geo-stationary meteorological satellite (GSMS) images. To align landmarks and non-landmarks…”
Get full text

Abnormal event detection via adaptive cascade dictionary learning by Hui Wen, Shiming Ge, Shuixian Chen, Hongtao Wang, Limin Sun

“…Detecting abnormal events plays an essential role in video content analysis and has received increasing attention in surveillance system. One of the major…”
Get full text

Image Completion Using Global Patch Matching and Optimal Seam Synthesis by Shiming Ge, Kaixuan Xie, Rui Yang, Zhiqiang Shi

“…This paper presented a global exemplar-based image completion method for filling large missing or damaged regions in an image. Based on three proposed…”
Get full text

Occluded Face Recognition in the Wild by Identity-Diversity Inpainting by Ge, Shiming, Li, Chenyu, Zhao, Shengwei, Zeng, Dan

“…Face recognition has achieved advanced development by using convolutional neural network (CNN) based recognizers. Existing recognizers typically demonstrate…”
Get full text

Efficient Low-Resolution Face Recognition via Bridge Distillation by Ge, Shiming, Zhao, Shengwei, Li, Chenyu, Zhang, Yu, Li, Jia

“…Face recognition in the wild is now advancing towards light-weight models, fast inference speed and resolution-adapted capability. In this paper, we propose a…”
Get full text

Student Network Learning via Evolutionary Knowledge Distillation by Zhang, Kangkai, Zhang, Chunhui, Li, Shikun, Zeng, Dan, Ge, Shiming

“…Knowledge distillation provides an effective way to transfer knowledge via teacher-student learning, where most existing distillation approaches apply a fixed…”
Get full text

Selective-Supervised Contrastive Learning with Noisy Labels by Li, Shikun, Xia, Xiaobo, Ge, Shiming, Liu, Tongliang

“…Deep networks have strong capacities of embedding data into latent representations and finishing following tasks. However, the capacities largely come from…”
Get full text

Efficient Video Grounding With Which-Where Reading Comprehension by Gao, Jialin, Sun, Xin, Ghanem, Bernard, Zhou, Xi, Ge, Shiming

“…Video grounding aims at localizing the temporal moment related to the given language description, which is very helpful to many cross-modal content…”
Get full text

Learning Patch-Channel Correspondence for Interpretable Face Forgery Detection by Hua, Yingying, Shi, Ruixin, Wang, Pengju, Ge, Shiming

“…Beyond high accuracy, good interpretability is very critical to deploy a face forgery detection model for visual content analysis. In this paper, we propose…”
Get full text

Receptive Multi-Granularity Representation for Person Re-Identification by Wang, Guanshuo, Yuan, Yufeng, Li, Jiwei, Ge, Shiming, Zhou, Xi

“…A key for person re-identification is achieving consistent local details for discriminative representation across variable environments. Current stripe-based…”
Get full text

Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency by Li, Jia, Fu, Kui, Zhao, Shengwei, Ge, Shiming

“…The performance of video saliency estimation techniques has achieved significant advances along with the rapid development of Convolutional Neural Networks…”
Get full text