61 citations · 239 across the 18 of their papers we have counts for
18 papers
CasIL: Cognizing and Imitating Skills via a Dual Cognition-Action Architecture
Zixuan Chen, Ze Ji, Shuyang Liu +3
Enabling robots to effectively imitate expert skills in longhorizon tasks such as locomotion, manipulation, and more, poses a long-standing challenge. Existing imitation learning (…
Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation
Kelei He, Wen Ji, Tao Zhou +7
Accurate segmentation of brain tumors from multi-modal Magnetic Resonance (MR) images is essential in brain tumor diagnosis and treatment. However, due to the existence of domain s…
CariMe: Unpaired Caricature Generation with Multiple Exaggerations
Zheng Gu, Chuanqi Dong, Jing Huo +2
Caricature generation aims to translate real photos into caricatures with artistic styles and shape exaggerations while maintaining the identity of the subject. Different from the…
Unsupervised Domain Attention Adaptation Network for Caricature Attribute Recognition
Wen Ji, Kelei He, Jing Huo +2
Caricature attributes provide distinctive facial features to help research in Psychology and Neuroscience. However, unlike the facial photo attribute datasets that have a quantity…
Manifold Alignment for Semantically Aligned Style Transfer
Jing Huo, Shiyin Jin, Wenbin Li +4
Most existing style transfer methods follow the assumption that styles can be represented with global statistics (e.g., Gram matrices or covariance matrices), and thus address the…
MetricUNet: Synergistic Image- and Voxel-Level Learning for Precise CT Prostate Segmentation via Online Sampling
Kelei He, Chunfeng Lian, Ehsan Adeli +5
Fully convolutional networks (FCNs), including UNet and VNet, are widely-used network architectures for semantic segmentation in recent studies. However, conventional FCN is typica…
Asymmetric Distribution Measure for Few-shot Learning
Wenbin Li, Lei Wang, Jing Huo +3
The core idea of metric-based few-shot image classification is to directly measure the relations between query images and support classes to learn transferable feature embeddings.…
MW-GAN: Multi-Warping GAN for Caricature Generation with Multi-Style Geometric Exaggeration
Haodi Hou, Jing Huo, Jing Wu +2
Given an input face photo, the goal of caricature generation is to produce stylized, exaggerated caricatures that share the same identity as the photo. It requires simultaneous sty…
Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification
Lei Qi, Lei Wang, Jing Huo +2
In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which only has the intra-camera (within-camera) labels but not inter-camera (cross-camera) lab…
GreyReID: A Two-stream Deep Framework with RGB-grey Information for Person Re-identification
Lei Qi, Lei Wang, Jing Huo +2
In this paper, we observe that most false positive images (i.e., different identities with query images) in the top ranking list usually have the similar color information with the…
Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification
Lei Qi, Lei Wang, Jing Huo +3
In person re-identification (Re-ID), supervised methods usually need a large amount of expensive label information, while unsupervised ones are still unable to deliver satisfactory…
Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning
Wenbin Li, Lei Wang, Jinglin Xu +3
Few-shot learning in image classification aims to learn a classifier to classify images when only few training examples are available for each class. Recent work has achieved promi…
A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification
Lei Qi, Lei Wang, Jing Huo +3
Unsupervised cross-domain person re-identification (Re-ID) faces two key issues. One is the data distribution discrepancy between source and target domains, and the other is the la…
CariGAN: Caricature Generation through Weakly Paired Adversarial Learning
Wenbin Li, Wei Xiong, Haofu Liao +3
Caricature generation is an interesting yet challenging task. The primary goal is to generate plausible caricatures with reasonable exaggerations given face images. Conventional ca…
Cross-Domain Adversarial Auto-Encoder
Haodi Hou, Jing Huo, Yang Gao
In this paper, we propose the Cross-Domain Adversarial Auto-Encoder (CDAAE) to address the problem of cross-domain image inference, generation and transformation. We make the assum…
MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification
Lei Qi, Jing Huo, Lei Wang +2
Person retrieval faces many challenges including cluttered background, appearance variations (e.g., illumination, pose, occlusion) among different camera views and the similarity a…
WebCaricature: a benchmark for caricature recognition
Jing Huo, Wenbin Li, Yinghuan Shi +2
Studying caricature recognition is fundamentally important to understanding of face perception. However, little research has been conducted in the computer vision community, largel…
OPML: A One-Pass Closed-Form Solution for Online Metric Learning
Wenbin Li, Yang Gao, Lei Wang +3
To achieve a low computational cost when performing online metric learning for large-scale data, we present a one-pass closed-form solution namely OPML in this paper. Typically, th…