1k citations · 2.5k across the 64 of their papers we have counts for
47 papers · 1 filter
SMC-UDA: Structure-Modal Constraint for Unsupervised Cross-Domain Renal Segmentation
Zhusi Zhong, Jie Li, Lulu Bi +6
Medical image segmentation based on deep learning often fails when deployed on images from a different domain. The domain adaptation methods aim to solve domain-shift challenges, b…
Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition
Haojun Xu, Yan Gao, Zheng Hui +2
How humans understand and recognize the actions of others is a complex neuroscientific problem that involves a combination of cognitive mechanisms and neural networks. Research has…
Seeking Subjectivity in Visual Emotion Distribution Learning
Jingyuan Yang, Jie Li, Leida Li +3
Visual Emotion Analysis (VEA), which aims to predict people's emotions towards different visual stimuli, has become an attractive research topic recently. Rather than a single labe…
Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction
De Cheng, Yan Li, Dingwen Zhang +3
Single image dehazing as a fundamental low-level vision task, is essential for the development of robust intelligent surveillance system. In this paper, we make an early effort to…
Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margin
Hangyu Li, Nannan Wang, Xi Yang +2
Only parts of unlabeled data are selected to train models for most semi-supervised learning methods, whose confidence scores are usually higher than the pre-defined threshold (i.e.…
Semi-parametric Makeup Transfer via Semantic-aware Correspondence
Mingrui Zhu, Yun Yi, Nannan Wang +2
The large discrepancy between the source non-makeup image and the reference makeup image is one of the key challenges in makeup transfer. Conventional approaches for makeup transfe…
SOLVER: Scene-Object Interrelated Visual Emotion Reasoning Network
Jingyuan Yang, Xinbo Gao, Leida Li +2
Visual Emotion Analysis (VEA) aims at finding out how people feel emotionally towards different visual stimuli, which has attracted great attention recently with the prevalence of…
Hybrid Dynamic Contrast and Probability Distillation for Unsupervised Person Re-Id
De Cheng, Jingyu Zhou, Nannan Wang +1
Unsupervised person re-identification (Re-Id) has attracted increasing attention due to its practical application in the read-world video surveillance system. The traditional unsup…
Single Image Dehazing with An Independent Detail-Recovery Network
Yan Li, De Cheng, Jiande Sun +3
Single image dehazing is a prerequisite which affects the performance of many computer vision tasks and has attracted increasing attention in recent years. However, most existing d…
Stimuli-Aware Visual Emotion Analysis
Jingyuan Yang, Jie Li, Xiumei Wang +2
Visual emotion analysis (VEA) has attracted great attention recently, due to the increasing tendency of expressing and understanding emotions through images on social networks. Dif…
Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds
Fangcen Liu, Chenqiang Gao, Fang Chen +3
The infrared small-dim target detection is one of the key techniques in the infrared search and tracking system. Since the local regions similar to infrared small-dim targets sprea…
Support-Set Based Cross-Supervision for Video Grounding
Xinpeng Ding, Nannan Wang, Shiwei Zhang +5
Current approaches for video grounding propose kinds of complex architectures to capture the video-text relations, and have achieved impressive improvements. However, it is hard to…
A Circular-Structured Representation for Visual Emotion Distribution Learning
Jingyuan Yang, Jie Li, Leida Li +2
Visual Emotion Analysis (VEA) has attracted increasing attention recently with the prevalence of sharing images on social networks. Since human emotions are ambiguous and subjectiv…
Towards Defending against Adversarial Examples via Attack-Invariant Features
Dawei Zhou, Tongliang Liu, Bo Han +3
Deep neural networks (DNNs) are vulnerable to adversarial noise. Their adversarial robustness can be improved by exploiting adversarial examples. However, given the continuously ev…
Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
Dawei Zhou, Nannan Wang, Xinbo Gao +4
Deep neural networks (DNNs) are vulnerable to adversarial noise. A range of adversarial defense techniques have been proposed to mitigate the interference of adversarial noise, amo…
Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
Tianwei Lin, Zhuoqi Ma, Fu Li +6
Artistic style transfer aims at migrating the style from an example image to a content image. Currently, optimization-based methods have achieved great stylization quality, but exp…
Transitional Learning: Exploring the Transition States of Degradation for Blind Super-resolution
Yuanfei Huang, Jie Li, Yanting Hu +2
Being extremely dependent on iterative estimation of the degradation prior or optimization of the model from scratch, the existing blind super-resolution (SR) methods are generally…
TSGCNet: Discriminative Geometric Feature Learning with Two-Stream GraphConvolutional Network for 3D Dental Model Segmentation
Lingming Zhang, Yue Zhao, Deyu Meng +5
The ability to segment teeth precisely from digitized 3D dental models is an essential task in computer-aided orthodontic surgical planning. To date, deep learning based methods ha…
D-Unet: A Dual-encoder U-Net for Image Splicing Forgery Detection and Localization
Bo Liu, Ranglei Wu, Xiuli Bi +4
Recently, many detection methods based on convolutional neural networks (CNNs) have been proposed for image splicing forgery detection. Most of these detection methods focus on the…
Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution
Yuanfei Huang, Jie Li, Xinbo Gao +2
Benefiting from the strong capabilities of deep CNNs for feature representation and nonlinear mapping, deep-learning-based methods have achieved excellent performance in single ima…
Robust Person Re-Identification through Contextual Mutual Boosting
Zhikang Wang, Lihuo He, Xinbo Gao +1
Person Re-Identification (Re-ID) has witnessed great advance, driven by the development of deep learning. However, modern person Re-ID is still challenged by background clutter, oc…
Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
Lei Zhang, Zhenwei He, Yi Yang +2
The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an ima…
Weakly Supervised Temporal Action Localization with Segment-Level Labels
Xinpeng Ding, Nannan Wang, Xinbo Gao +3
Temporal action localization presents a trade-off between test performance and annotation-time cost. Fully supervised methods achieve good performance with time-consuming boundary…
Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition
Bing Cao, Nannan Wang, Xinbo Gao +2
Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios. This paper presents a deep neural…