Search Results - "Huaxin Xiao"

Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi-Supervised Semantic Segmentation by Wei, Yunchao, Xiao, Huaxin, Shi, Honghui, Jie, Zequn, Feng, Jiashi, Huang, Thomas S.

“…Despite the remarkable progress, weakly supervised segmentation approaches are still inferior to their fully supervised counterparts. We obverse the…”
Get full text

Online Meta Adaptation for Fast Video Object Segmentation by Xiao, Huaxin, Kang, Bingyi, Liu, Yu, Zhang, Maojun, Feng, Jiashi

“…Conventional deep neural networks based video object segmentation (VOS) methods are dominated by heavily fine-tuning a segmentation model on the first frame of…”
Get full text

A Class Imbalance Loss for Imbalanced Object Recognition by Zhang, Linbin, Zhang, Caiguang, Quan, Sinong, Xiao, Huaxin, Kuang, Gangyao, Liu, Li

“…The class imbalance problem exists widely in vision data. In these imbalanced datasets, the majority classes dominate the loss and influence the gradient…”
Get full text

Are RGB-based salient object detection methods unsuitable for light field data? by Liu, Yu, Xiao, Huaxin, Tan, Hanlin, Li, Ping

“…Considering the significant progress made on RGB-based deep salient object detection (SOD) methods, this paper seeks to bridge the gap between those 2D methods…”
Get full text

Video Scene Parsing with Predictive Feature Learning by Xiaojie Jin, Xin Li, Huaxin Xiao, Xiaohui Shen, Zhe Lin, Jimei Yang, Yunpeng Chen, Jian Dong, Luoqi Liu, Zequn Jie, Jiashi Feng, Shuicheng Yan

“…Video scene parsing is challenging due to the following two reasons: firstly, it is non-trivial to learn meaningful video representations for producing the…”
Get full text

Boosting adversarial robustness via feature refinement, suppression, and alignment by Wu, Yulun, Guo, Yanming, Chen, Dongmei, Yu, Tianyuan, Xiao, Huaxin, Guo, Yuanhao, Bai, Liang

“…Deep neural networks are vulnerable to adversarial attacks, bringing high risk to numerous security-critical applications. Existing adversarial defense…”
Get full text

MSBA: Multiple Scales, Branches and Attention Network With Bag of Tricks for Person Re-Identification by Tan, Hanlin, Xiao, Huaxin, Zhang, Xiaoyu, Dai, Bin, Lai, Shiming, Liu, Yu, Zhang, Maojun

“…Person re-identification (Re-ID) has become a hot topic in both research and industry. We joined in a person Re-ID challenge of the First National Artificial…”
Get full text

A robust motion detection algorithm on noisy videos by Yu Liu, Huaxin Xiao, Wei Wang, Maojun Zhang

“…The applicability and performance of motion detection methods dramatically degrade with the increasing noise. In this paper, we propose a robust…”
Get full text

MoNet: Deep Motion Exploitation for Video Object Segmentation by Xiao, Huaxin, Feng, Jiashi, Lin, Guosheng, Liu, Yu, Zhang, Maojun

“…In this paper, we propose a novel MoNet model to deeply exploit motion cues for boosting video object segmentation performance from two aspects, i.e., frame…”
Get full text

SA-CGAN: An oversampling method based on single attribute guided conditional GAN for multi-class imbalanced learning by Dong, Yongfeng, Xiao, Huaxin, Dong, Yao

“…Imbalanced data can always be observed in our daily life and various practical tasks. A lot of well-constructed machine learning methodologies may produce…”
Get full text

Deep Salient Object Detection With Dense Connections and Distraction Diagnosis by Xiao, Huaxin, Feng, Jiashi, Wei, Yunchao, Zhang, Maojun, Yan, Shuicheng

“…In this paper, we propose two novel components for improving deep salient object detection models. The first component, called saliency detection network…”
Get full text

Time–frequency recurrent transformer with diversity constraint for dense video captioning by Li, Ping, Zhang, Pan, Wang, Tao, Xiao, Huaxin

“…Describing a long video using multiple sentences, i.e., dense video captioning, is a very challenging task. Existing methods neglect the important fact that…”
Get full text

Efficient Long-Short Temporal Attention network for unsupervised Video Object Segmentation by Li, Ping, Zhang, Yu, Yuan, Li, Xiao, Huaxin, Lin, Binbin, Xu, Xianghua

Get full text

Zoom-GAN: learn to colorize multi-scale targets by Liu, Yu, Guo, Zhe, Guo, Haojie, Xiao, Huaxin

“…In recent years, the research of image colorization based on deep learning has made great progress. Most of the existing methods have achieved impressive…”
Get full text

Accelerating thrombolysis using a precision and clot-penetrating drug delivery strategy by nanoparticle-shelled microbubbles by Wang, Siyu, Guo, Xixi, Xiu, Weijun, Liu, Yang, Ren, Lili, Xiao, Huaxin, Yang, Fang, Gao, Yu, Xu, Chenjie, Wang, Lianhui

“…Conventional thrombolytic drugs for vascular blockage such as tissue plasminogen activator (tPA) are challenged by the low bioavailability, off-target side…”
Get full text

Learning to colorize near-infrared images with limited data by Liu, Yu, Guo, Zhe, Guo, Haojie, Xiao, Huaxin

“…With large amount of training data, Convolutional Neural Network (CNN)-based methods have made great progress for colorizing visible grayscale images. However,…”
Get full text

Deep ladder reconstruction-classification network for unsupervised domain adaptation by Deng, Wanxia, Su, Zhuo, Qiu, Qiang, Zhao, Lingjun, Kuang, Gangyao, Pietikäinen, Matti, Xiao, Huaxin, Liu, Li

“…•The paper points out the drawback that existing methods apply entire information of images to adapt.•The paper proposes a new framework to suppress…”
Get full text

Does partisan conflict affect US innovation? by Zhou, Zehai, Sun, Wantao, Xiao, Huaxin, You, Wanhai

“…This article explores the influence of partisan conflict on innovation using panel data of 48 mainland US states over the period from 1992 to 2013. A novel…”
Get full text

Perfluorooctane sulfonate enhances mRNA expression of PPARγ and ap2 in human mesenchymal stem cells monitored by long-retained intracellular nanosensor by Gao, Yu, Guo, Xixi, Wang, Siyu, Chen, Fubin, Ren, Xiaomin, Xiao, Huaxin, Wang, Lianhui

“…Perfluorooctane sulfonate (PFOS) has been widely used as a surface coating for household products. It still exists in living environments despite being…”
Get full text

A photo-responsive self-healing hydrogel loaded with immunoadjuvants and MoS 2 nanosheets for combating post-resection breast cancer recurrence by Wang, Siyu, Qian, Zhuoping, Xiao, Huaxin, Yang, Guangwen, Zhu, Ziyi, Gu, Yubin, Song, Junjie, Zhang, Xin, Huang, Xinxuan, Weng, Lixing, Gao, Yu, Yang, Wenjing, Wang, Lianhui

“…Tumor recurrence after surgical resection remains a significant challenge in breast cancer treatment. Immune checkpoint blockade therapy, as a promising…”
Get more information