Search Results - "Cuiling Lan"

Spatio-Temporal Attention-Based LSTM Networks for 3D Action Recognition and Detection by Song, Sijie, Lan, Cuiling, Xing, Junliang, Zeng, Wenjun, Liu, Jiaying

“…Human action analytics has attracted a lot of attention for decades in computer vision. It is important to extract discriminative spatio-temporal features to…”
Get full text

View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition by Zhang, Pengfei, Lan, Cuiling, Xing, Junliang, Zeng, Wenjun, Xue, Jianru, Zheng, Nanning

“…Skeleton-based human action recognition has recently attracted increasing attention thanks to the accessibility and the popularity of 3D skeleton data. One of…”
Get full text

Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition by Zhang, Pengfei, Lan, Cuiling, Zeng, Wenjun, Xing, Junliang, Xue, Jianru, Zheng, Nanning

“…Skeleton-based human action recognition has attracted great interest thanks to the easy accessibility of the human skeleton data. Recently, there is a trend of…”
Get full text

View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data by Pengfei Zhang, Cuiling Lan, Junliang Xing, Wenjun Zeng, Jianru Xue, Nanning Zheng

“…Skeleton-based human action recognition has recently attracted increasing attention due to the popularity of 3D skeleton data. One main challenge lies in the…”
Get full text

Compress Compound Images in H.264/MPGE-4 AVC by Exploiting Spatial Correlation by Lan, Cuiling, Shi, Guangming, Wu, Feng

“…Compound images are a combination of text, graphics and natural image. They present strong anisotropic features, especially on the text and graphics parts…”
Get full text

Structure-Preserving Hybrid Digital-Analog Video Delivery in Wireless Networks by He, Dongliang, Luo, Chong, Lan, Cuiling, Wu, Feng, Zeng, Wenjun

“…Hybrid digital-analog (HDA) transmission has gained increasing attention recently in the context of wireless video delivery , for its ability to simultaneously…”
Get full text

Progressive Pseudo-analog Transmission for Mobile Video Streaming by He, Dongliang, Lan, Cuiling, Luo, Chong, Chen, Enhong, Wu, Feng, Zeng, Wenjun

“…We propose a progressive pseudo-analog video transmission scheme that simultaneously handles SNR and bandwidth variations with graceful quality degradation for…”
Get full text

Human Pose Estimation Using Global and Local Normalization by Ke Sun, Cuiling Lan, Junliang Xing, Wenjun Zeng, Dong Liu, Jingdong Wang

“…In this paper, we address the problem of estimating the positions of human joints, i.e., articulated pose estimation. Recent state-of-the-art solutions model…”
Get full text

Nanostructured carbon black for simultaneous electrochemical determination of trace lead and cadmium by differential pulse stripping voltammetry by Xie, Ruigang, Zhou, Lingli, Lan, Cuiling, Fan, Fangfang, Xie, Ruifeng, Tan, Hongyu, Xie, Tiansheng, Zhao, Lingmin

“…Nanostructured carbon black (CB) was first employed directly in this paper for the simultaneous electrochemical determination of trace Pb(II) and Cd(II) using…”
Get full text

Exploiting Non-Local Correlation via Signal-Dependent Transform (SDT) by Lan, Cuiling, Xu, Jizheng, Shi, Guangming, Wu, Feng

“…Over the past few decades, many studies on image and video compression have found various approaches to the exploitation of spatial and temporal local…”
Get full text

Electrochemical Reaction Mechanism of Phenacetin at a Carboxylated Multiwall Carbon Nanotube Modified Electrode and Its Analytical Applications by Zhang, Jinlei, Lan, Cuiling, Shi, Bingfang, Liu, Fang, Zhao, Dandan, Tan, Xuecai

“…A novel type of carboxylated multiwalled carbon nanotube modified electrode（c-MWCNTs/GCE） was constructed and the electrochemical properties of phenacetin（PHE）…”
Get full text

Relation-Aware Global Attention for Person Re-Identification by Zhang, Zhizheng, Lan, Cuiling, Zeng, Wenjun, Jin, Xin, Chen, Zhibo

“…For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing…”
Get full text

Style Normalization and Restitution for Generalizable Person Re-Identification by Jin, Xin, Lan, Cuiling, Zeng, Wenjun, Chen, Zhibo, Zhang, Li

“…Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps. The key to solving…”
Get full text

Energy-efficient design of real-time stream mining systems by Shaolei Ren, Cuiling Lan, van der Schaar, Mihaela

“…In this paper, we propose an efficient solution for supporting real-time stream mining applications on heterogeneous systems operating at various processing…”
Get full text

Densely Semantically Aligned Person Re-Identification by Zhang, Zhizheng, Lan, Cuiling, Zeng, Wenjun, Chen, Zhibo

“…We propose a densely semantically aligned person re-identification (re-ID) framework. It fundamentally addresses the body misalignment problem caused by…”
Get full text

Intra frame coding with template matching prediction and adaptive transform by Cuiling Lan, Jizheng Xu, Feng Wu, Guangming Shi

“…For natural images, there are usually repeating similar contents but hard to be well predicted locally. Prediction using template matching is an effective…”
Get full text

Style Normalization and Restitution for Domain Generalization and Adaptation by Jin, Xin, Lan, Cuiling, Zeng, Wenjun, Chen, Zhibo

“…For many computer vision applications, the learned models usually have high performance on the training datasets but suffer from significant performance…”
Get full text

ReSTR: Convolution-free Referring Image Segmentation Using Transformers by Kim, Namyup, Kim, Dongwon, Kwak, Suha, Lan, Cuiling, Zeng, Wenjun

“…Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of…”
Get full text

Generalizing to Unseen Domains: A Survey on Domain Generalization by Wang, Jindong, Lan, Cuiling, Liu, Chang, Ouyang, Yidong, Qin, Tao, Lu, Wang, Chen, Yiqiang, Zeng, Wenjun, Yu, Philip S.

“…Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that…”
Get full text

Skeleton-Based Action Recognition With Gated Convolutional Neural Networks by Cao, Congqi, Lan, Cuiling, Zhang, Yifan, Zeng, Wenjun, Lu, Hanqing, Zhang, Yanning

“…For skeleton-based action recognition, most of the existing works used recurrent neural networks. Using convolutional neural networks (CNNs) is another…”
Get full text