Search Results - "Dong, Xuanyi"

Searching for a Robust Neural Architecture in Four GPU Hours by Dong, Xuanyi, Yang, Yi

“…Conventional neural architecture search (NAS) approaches are usually based on reinforcement learning or evolutionary strategy, which take more than 1000 GPU…”
Get full text

NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size by Dong, Xuanyi, Liu, Lu, Musial, Katarzyna, Gabrys, Bogdan

“…Neural architecture search (NAS) has attracted a lot of attention and has been illustrated to bring tangible benefits in a large number of applications in the…”
Get full text

Style Aggregated Network for Facial Landmark Detection by Dong, Xuanyi, Yan, Yan, Ouyang, Wanli, Yang, Yi

“…Recent advances in facial landmark detection achieve success by learning discriminative features from rich deformation of face shapes and poses. Besides the…”
Get full text

Progressive Learning for Person Re-Identification With One Example by Wu, Yu, Lin, Yutian, Dong, Xuanyi, Yan, Yan, Bian, Wei, Yang, Yi

“…In this paper, we focus on the one-example person re-identification (re-ID) task, where each identity has only one labeled example along with many unlabeled…”
Get full text

More is Less: A More Complicated Network with Less Inference Complexity by Xuanyi Dong, Junshi Huang, Yi Yang, Shuicheng Yan

“…In this paper, we present a novel and general network structure towards accelerating the inference process of convolutional neural networks, which is more…”
Get full text

Auto-ReID: Searching for a Part-Aware ConvNet for Person Re-Identification by Quan, Ruijie, Dong, Xuanyi, Wu, Yu, Zhu, Linchao, Yang, Yi

“…Prevailing deep convolutional neural networks (CNNs) for person re-IDentification (reID) are usually built upon ResNet or VGG backbones, which were originally…”
Get full text

Exploit the Unknown Gradually: One-Shot Video-Based Person Re-identification by Stepwise Learning by Wu, Yu, Lin, Yutian, Dong, Xuanyi, Yan, Yan, Ouyang, Wanli, Yang, Yi

“…We focus on the one-shot learning for video-based person re-Identification (re-ID). Unlabeled tracklets for the person re-ID tasks can be easily obtained by…”
Get full text

Eye tracking and eye expression decoding based on transparent, flexible and ultra-persistent electrostatic interface by Shi, Yuxiang, Yang, Peng, Lei, Rui, Liu, Zhaoqi, Dong, Xuanyi, Tao, Xinglin, Chu, Xiangcheng, Wang, Zhong Lin, Chen, Xiangyu

“…Eye tracking provides valuable insight for analyzing visual attention and underlying thinking progress through the observation of eye movements. Here, a…”
Get full text

Late Fusion via Subspace Search With Consistency Preservation by Xuanyi Dong, Yan Yan, Mingkui Tan, Yi Yang, Tsang, Ivor W.

“…In many real-world applications, data can be represented by multiple ways or multi-view features to describe various characteristics of data. In this sense,…”
Get full text

Harvesting Wind Energy Based on Triboelectric Nanogenerators by Dong, Xuanyi, Liu, Zhaoqi, Yang, Peng, Chen, Xiangyu

“…The utilization of various distributed energy is becoming a prominent research topic due to the rapid development of the Internet of Things and wireless…”
Get full text

One-Shot Neural Architecture Search via Self-Evaluated Template Network by Dong, Xuanyi, Yang, Yi

“…Neural architecture search (NAS) aims to automate the search procedure of architecture instead of manual design. Even if recent NAS approaches finish the…”
Get full text

Teacher Supervises Students How to Learn From Partially Labeled Images for Facial Landmark Detection by Dong, Xuanyi, Yang, Yi

“…Facial landmark detection aims to localize the anatomically defined points of human faces. In this paper, we study facial landmark detection from partially…”
Get full text

Few-Example Object Detection with Model Communication by Dong, Xuanyi, Zheng, Liang, Ma, Fan, Yang, Yi, Meng, Deyu

“…In this paper, we study object detection using a large pool of unlabeled images and only a few labeled images per category, named “few-example object…”
Get full text

Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks by He, Yang, Dong, Xuanyi, Kang, Guoliang, Fu, Yanwei, Yan, Chenggang, Yang, Yi

“…Deeper and wider convolutional neural networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such overparameterized…”
Get full text

Triboelectric nanogenerator powered dielectric elastomer: Mechanism and applications by Wang, Dandan, Liu, Zhaoqi, Dong, Xuanyi, Zhang, Dandan, Chen, Xiangyu

“…This paper reviews the research progress of TENG powered dielectric elastomer in recent years. The mechanism, material structure and performance of diverse…”
Get full text

Characterization of Partially Overlapped Inductors for Compact Layout Design in 130nm RFCMOS and 22nm FinFET Processes by Dong, Xuanyi, Weisshaar, Andreas

“…Based on the principle of magnetic flux cancellation, partially overlapped spiral inductors can achieve nearly zero magnetic coupling with ultra-compact…”
Get full text

Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors by Dong, Xuanyi, Yu, Shoou-I, Weng, Xinshuo, Wei, Shih-En, Yang, Yi, Sheikh, Yaser

“…In this paper, we present supervision-by-registration, an unsupervised approach to improve the precision of facial landmark detectors on both images and video…”
Get full text

A Piezo‐Tribovoltaic Nanogenerator with Ultrahigh Output Power Density and Dynamic Sensory Functions by Qin, Siyao, Chen, Jiaqi, Yang, Peng, Liu, Zhaoqi, Tao, Xinglin, Dong, Xuanyi, Hu, Jun, Chu, Xiangcheng, Wang, Zhong Lin, Chen, Xiangyu

“…Tribovoltaic nanogenerator (TVNG) mainly collects energy from sliding motions of two semiconducting materials, but it cannot effectively react to the pressure…”
Get full text

Hierarchically Recognizing Vector Graphics and A New Chart-Based Vector Graphics Dataset by Dou, Shuguang, Jiang, Xinyang, Liu, Lu, Ying, Lu, Shan, Caihua, Shen, Yifei, Dong, Xuanyi, Wang, Yun, Li, Dongsheng, Zhao, Cairong

“…The conventional approach to image recognition has been based on raster graphics, which can suffer from aliasing and information loss when scaled up or down…”
Get full text

Hierarchical Recognizing Vector Graphics and A New Chart-based Vector Graphics Dataset by Dou, Shuguang, Jiang, Xinyang, Liu, Lu, Ying, Lu, Shan, Caihua, Shen, Yifei, Dong, Xuanyi, Wang, Yun, Li, Dongsheng, Zhao, Cairong

“…The conventional approach to image recognition has been based on raster graphics, which can suffer from aliasing and information loss when scaled up or down…”
Get full text