71 citations · 227 across the 18 of their papers we have counts for
18 papers
FreqGRL: Suppressing Low-Frequency Bias and Mining High-Frequency Knowledge for Cross-Domain Few-Shot Learning
Siqi Hui, Sanping Zhou, Ye deng +2
Cross-domain few-shot learning (CD-FSL) aims to recognize novel classes with only a few labeled examples under significant domain shifts. While recent approaches leverage a limited…
CEM-Net: Cross-Emotion Memory Network for Emotional Talking Face Generation
Kangyi Wu, Pengna Li, Jingwen Fu +4
Emotional talking face generation aims to animate a human face in given reference images and generate a talking video that matches the content and emotion of driving audio. However…
Autoregressive Images Watermarking through Lexical Biasing: An Approach Resistant to Regeneration Attack
Siqi Hui, Yiren Song, Sanping Zhou +3
Autoregressive (AR) image generation models have gained increasing attention for their breakthroughs in synthesis quality, highlighting the need for robust watermarking to prevent…
REGNav: Room Expert Guided Image-Goal Navigation
Pengna Li, Kangyi Wu, Jingwen Fu +1
Image-goal navigation aims to steer an agent towards the goal location specified by an image. Most prior methods tackle this task by learning a navigation policy, which extracts vi…
Semantic-aware Representation Learning for Homography Estimation
Yuhan Liu, Qianxin Huang, Siqi Hui +5
Homography estimation is the task of determining the transformation from an image pair. Our approach focuses on employing detector-free feature matching methods to address this iss…
Camera-aware Label Refinement for Unsupervised Person Re-identification
Pengna Li, Kangyi Wu, Wenli Huang +2
Unsupervised person re-identification aims to retrieve images of a specified person without identity labels. Many recent unsupervised Re-ID approaches adopt clustering-based method…
Understanding the Overfitting of the Episodic Meta-training
Siqi Hui, Sanping Zhou, Ye deng +1
Despite the success of two-stage few-shot classification methods, in the episodic meta-training stage, the model suffers severe overfitting. We hypothesize that it is caused by ove…
T-former: An Efficient Transformer for Image Inpainting
Ye Deng, Siqi Hui, Sanping Zhou +2
Benefiting from powerful convolutional neural networks (CNNs), learning-based image inpainting methods have made significant breakthroughs over the years. However, some nature of C…
Pseudo Labels Refinement with Intra-camera Similarity for Unsupervised Person Re-identification
Pengna Li, Kangyi Wu, Sanping Zhou. Qianxin Huang +1
Unsupervised person re-identification (Re-ID) aims to retrieve person images across cameras without any identity labels. Most clustering-based methods roughly divide image features…
Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection
Rongye Meng, Sanping Zhou, Xingyu Wan +2
Due to the high annotation cost of large-scale facial landmark detection tasks in videos, a semi-supervised paradigm that uses self-training for mining high-quality pseudo-labels t…
End-to-End Multi-Object Tracking with Global Response Map
Xingyu Wan, Jiakai Cao, Sanping Zhou +1
Most existing Multi-Object Tracking (MOT) approaches follow the Tracking-by-Detection paradigm and the data association framework where objects are firstly detected and then associ…
Meta Corrupted Pixels Mining for Medical Image Segmentation
Jixin Wang, Sanping Zhou, Chaowei Fang +2
Deep neural networks have achieved satisfactory performance in piles of medical image analysis tasks. However the training of deep neural network requires a large amount of samples…
Multiple Object Tracking by Flowing and Fusing
Jimuyang Zhang, Sanping Zhou, Xin Chang +4
Most of Multiple Object Tracking (MOT) approaches compute individual target features for two subtasks: estimating target-wise motions and conducting pair-wise Re-Identification (Re…
Frame-wise Motion and Appearance for Real-time Multiple Object Tracking
Jimuyang Zhang, Sanping Zhou, Jinjun Wang +1
The main challenge of Multiple Object Tracking (MOT) is the efficiency in associating indefinite number of objects between video frames. Standard motion estimators used in tracking…
SE2Net: Siamese Edge-Enhancement Network for Salient Object Detection
Sanping Zhou, Jimuyang Zhang, Jinjun Wang +2
Deep convolutional neural network significantly boosted the capability of salient object detection in handling large variations of scenes and object appearances. However, convoluti…
Discriminative Feature Learning with Foreground Attention for Person Re-Identification
Sanping Zhou, Jinjun Wang, Deyu Meng +3
The performance of person re-identification (Re-ID) has been seriously effected by the large cross-view appearance variations caused by mutual occlusions and background clutters. H…
Deep Self-Paced Learning for Person Re-Identification
Sanping Zhou, Jinjun Wang, Deyu Meng +4
Person re-identification (Re-ID) usually suffers from noisy samples with background clutter and mutual occlusion, which makes it extremely difficult to distinguish different indivi…
Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
Jiayun Wang, Sanping Zhou, Jinjun Wang +1
Person re-identification aims to match images of the same person across disjoint camera views, which is a challenging problem in video surveillance. The major challenge of this tas…