1.7k citations · 2.6k across the 41 of their papers we have counts for
42 papers
Beyond Facial Consistency: Personalized Person Image Generation with Holistic Identity Preservation
Yuxuan Xiao, Shanshan Zhang, Jian Yang +1
Personalized person image generation requires preserving subject identity across both local facial details and broader appearance cues. Existing methods typically emphasize only on…
Head Similarity: Modeling Structured Whole-Head Appearance Beyond Face Recognition
Yingfeng Wang, Yuxuan Xiao, Shengcai Liao
Many vision applications require identity consistency beyond strict biometric recognition, especially under non-frontal views or when facial cues are missing. However, conventional…
ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion
Yingjun Du, Zehao Xiao, Shengcai Liao +1
Prototype-based meta-learning has emerged as a powerful technique for addressing few-shot learning challenges. However, estimating a deterministic prototype using a simple average…
POCE: Pose-Controllable Expression Editing
Rongliang Wu, Yingchen Yu, Fangneng Zhan +3
Facial expression editing has attracted increasing attention with the advance of deep neural networks in recent years. However, most existing methods suffer from compromised editin…
KD-DLGAN: Data Limited Image Generation via Knowledge Distillation
Kaiwen Cui, Yingchen Yu, Fangneng Zhan +3
Generative Adversarial Networks (GANs) rely heavily on large-scale training data for training high-quality image generation models. With limited training data, the GAN discriminato…
Self-Paced Learning for Open-Set Domain Adaptation
Xinghong Liu, Yi Zhou, Tao Zhou +2
Domain adaptation tackles the challenge of generalizing knowledge acquired from a source domain to a target domain with different data distributions. Traditional domain adaptation…
Energy-Based Test Sample Adaptation for Domain Generalization
Zehao Xiao, Xiantong Zhen, Shengcai Liao +1
In this paper, we propose energy-based sample adaptation at test time for domain generalization. Where previous works adapt their models to target domains, we adapt the unseen targ…
RePFormer: Refinement Pyramid Transformer for Robust Facial Landmark Detection
Jinpeng Li, Haibo Jin, Shengcai Liao +2
This paper presents a Refinement Pyramid Transformer (RePFormer) for robust facial landmark detection. Most facial landmark detectors focus on learning representative image feature…
Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learning
Xingping Dong, Tianran Ouyang, Shengcai Liao +2
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit. To reduce the requirement of labels, a semi-supervise…
Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification
Yanan Wang, Xuezhi Liang, Shengcai Liao
Recently, large-scale synthetic datasets are shown to be very useful for generalizable person re-identification. However, synthesized persons in existing datasets are mostly cartoo…
Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond
Irtiza Hasan, Shengcai Liao, Jinpeng Li +2
Pedestrian detection is the cornerstone of many vision based applications, starting from object tracking to video surveillance and more recently, autonomous driving. With the rapid…
TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification
Yichao Yan, Junjie Li, Shengcai Liao +3
Domain generalizable person re-identification aims to apply a trained model to unseen domains. Prior works either combine the data in all the training domains to capture domain-inv…
Efficient Person Search: An Anchor-Free Approach
Yichao Yan, Jinpeng Li, Jie Qin +2
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images. To achieve this goal, state-of-the-art models typically add a re-id bran…
Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction
Fang Zhao, Wenhao Wang, Shengcai Liao +1
While single-view 3D reconstruction has made significant progress benefiting from deep shape representations in recent years, garment reconstruction is still not solved well due to…
Local-to-Global Self-Attention in Vision Transformers
Jinpeng Li, Yichao Yan, Shengcai Liao +2
Transformers have demonstrated great potential in computer vision tasks. To avoid dense computations of self-attentions in high-resolution visual data, some recent Transformer mode…
AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection
Hongsong Wang, Shengcai Liao, Ling Shao
Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised o…
When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model
Haibo Jin, Jinpeng Li, Shengcai Liao +1
In recent years, significant progress has been made in the research of facial landmark detection. However, few prior works have thoroughly discussed about models for practical appl…
Exploring Visual Context for Weakly Supervised Person Search
Yichao Yan, Jinpeng Li, Shengcai Liao +4
Person search has recently emerged as a challenging task that jointly addresses pedestrian detection and person re-identification. Existing approaches follow a fully supervised set…
TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification
Shengcai Liao, Ling Shao
Transformers have recently gained increasing attention in computer vision. However, existing studies mostly use Transformers for feature representation learning, e.g. for image cla…
Anchor-Free Person Search
Yichao Yan, Jinpeng Li, Jie Qin +5
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and pe…
Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification
Shengcai Liao, Ling Shao
Recent studies show that, both explicit deep feature matching as well as large-scale and diverse training data can significantly improve the generalization of person re-identificat…
DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations
Wenhao Wang, Shengcai Liao, Fang Zhao +2
Existing person re-identification models often have low generalizability, which is mostly due to limited availability of large-scale labeled data in training. However, labeling lar…
Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification
Yanan Wang, Shengcai Liao, Ling Shao
Person re-identification has seen significant advancement in recent years. However, the ability of learned models to generalize to unknown target domains still remains limited. One…
Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond
Wenhao Wang, Fang Zhao, Shengcai Liao +1
Unsupervised domain adaptation (UDA) for person re-identification is challenging because of the huge gap between the source and target domain. A typical self-training method is to…