Shengfeng He - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Shengfeng He

Publications
110
Citations
2,832
Publications by Year
20112025
Co-Authors:
Show All Co-Authors (289)
Image of author Shengfeng He

Shengfeng He

Affiliation

School of Computing and Information Systems, Singapore Management University, Singapore

Publication Topics

Biography

Shengfeng He (Senior Member, IEEE) received the BSc and MSc degrees from the Macau University of Science and Technology, in 2009 and 2011, respectively, and the PhD degree from the City University of Hong Kong, in 2015. He is an associate professor with the School of Computing and Information Systems, Singapore Management University. He was on the faculty of the South China University of Technology, from 2016 to 2022. His research interests include visual understanding and generative models. He is a senior member of CCF. He serves as the lead guest editor of the International Journal of Computer Vision and the associate editor of the Neurocomputing.(Based on document published on 19 March 2024).
Publications
110
Citations
2,832
Publications by Year
20112025
Co-Authors:
Show All Co-Authors (289)
Author's Published Works

Showing 1-25 of 110 results

  • Sort

Filter Results

Show

Sort By

Results

Open-set Mixed Domain Adaptation via Visual-Linguistic Focal Evolving

Bangzhen Liu;Yangyang Xu;Cheng Xu;Xuemiao Xu;Shengfeng He

IEEE Transactions on Circuits and Systems for Video Technology
Year: 2025 | Early Access Article |
We introduce a new task, Open-set Mixed Domain Adaptation (OSMDA), which considers the potential mixture of multiple distributions in the target domains, thereby better simulating real-world scenarios. To tackle the semantic ambiguity arising from multiple domains, our key idea is that the linguistic representation can serve as a universal descriptor for samples of the same category across various...Show More

Open-set Mixed Domain Adaptation via Visual-Linguistic Focal Evolving

Bangzhen Liu;Yangyang Xu;Cheng Xu;Xuemiao Xu;Shengfeng He

Year: 2025 | Early Access Article |

Self-Support Prototype-Aware For Few-Shot Semantic Segmentation

Jiaxiang Fang;Shiqiang Ma;Shengfeng He;Fei Guo

ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2025 | Conference Paper |
In recent years, significant progress has been made in prototype-based learning methods for few-shot semantic segmentation. However, prototype features originating from the support images are interfered with by intra-class diversity and thus cannot be aligned with the query foreground, resulting in poor segmentation accuracy. Therefore, we propose a novel self-support prototype-aware (SSPA) networ...Show More

Self-Support Prototype-Aware For Few-Shot Semantic Segmentation

Jiaxiang Fang;Shiqiang Ma;Shengfeng He;Fei Guo

Year: 2025 | Conference Paper |

Rotation-Adaptive Point Cloud Domain Generalization Via Intricate Orientation Learning

Bangzhen Liu;Chenxi Zheng;Xuemiao Xu;Cheng Xu;Huaidong Zhang;Shengfeng He

IEEE Transactions on Pattern Analysis and Machine Intelligence
Year: 2025 | Early Access Article |
The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not easily achieved through rotation augmentation. Motivated by the inherent advantages of intricate orientations in enhancing generalizability, we propose an innovat...Show More

Rotation-Adaptive Point Cloud Domain Generalization Via Intricate Orientation Learning

Bangzhen Liu;Chenxi Zheng;Xuemiao Xu;Cheng Xu;Huaidong Zhang;Shengfeng He

Year: 2025 | Early Access Article |

One-for-All: Towards Universal Domain Translation With a Single StyleGAN

Yong Du;Jiahui Zhan;Xinzhe Li;Junyu Dong;Sheng Chen;Ming-Hsuan Yang;Shengfeng He

IEEE Transactions on Pattern Analysis and Machine Intelligence
Year: 2025 | Volume: 47, Issue: 4 | Journal Article |
In this paper, we propose a novel translation model, UniTranslator, for transforming representations between visually distinct domains under conditions of limited training data and significant visual differences. The main idea behind our approach is leveraging the domain-neutral capabilities of CLIP as a bridging mechanism, while utilizing a separate module to extract abstract, domain-agnostic sem...Show More

One-for-All: Towards Universal Domain Translation With a Single StyleGAN

Yong Du;Jiahui Zhan;Xinzhe Li;Junyu Dong;Sheng Chen;Ming-Hsuan Yang;Shengfeng He

Year: 2025 | Volume: 47, Issue: 4 | Journal Article |

Category-Contrastive Fine-Grained Crowd Counting and Beyond

Meijing Zhang;Mengxue Chen;Qi Li;Yanchen Chen;Rui Lin;Xiaolian Li;Shengfeng He;Wenxi Liu

IEEE Transactions on Multimedia
Year: 2025 | Volume: 27 | Journal Article |
Crowd counting has drawn increasing attention across various fields. However, existing crowd counting tasks primarily focus on estimating the overall population, ignoring the behavioral and semantic information of different social groups within the crowd. In this paper, we aim to address a newly proposed research problem, namely fine-grained crowd counting, which involves identifying different cat...Show More

Category-Contrastive Fine-Grained Crowd Counting and Beyond

Meijing Zhang;Mengxue Chen;Qi Li;Yanchen Chen;Rui Lin;Xiaolian Li;Shengfeng He;Wenxi Liu

Year: 2025 | Volume: 27 | Journal Article |

Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection

Hao Tang;Zechao Li;Dong Zhang;Shengfeng He;Jinhui Tang

IEEE Transactions on Pattern Analysis and Machine Intelligence
Year: 2025 | Volume: 47, Issue: 3 | Journal Article |
RGB-Thermal Salient Object Detection (RGB-T SOD) aims to pinpoint prominent objects within aligned pairs of visible and thermal infrared images. A key challenge lies in bridging the inherent disparities between RGB and Thermal modalities for effective saliency map prediction. Traditional encoder-decoder architectures, while designed for cross-modality feature interactions, may not have adequately ...Show More

Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection

Hao Tang;Zechao Li;Dong Zhang;Shengfeng He;Jinhui Tang

Year: 2025 | Volume: 47, Issue: 3 | Journal Article |

Learning an Interpretable Stylized Subspace for 3D-Aware Animatable Artforms

Chenxi Zheng;Bangzhen Liu;Xuemiao Xu;Huaidong Zhang;Shengfeng He

IEEE Transactions on Visualization and Computer Graphics
Year: 2025 | Volume: 31, Issue: 2 | Journal Article |
Cited by: Papers (2)
Throughout history, static paintings have captivated viewers within display frames, yet the possibility of making these masterpieces vividly interactive remains intriguing. This research paper introduces 3DArtmator, a novel approach that aims to represent artforms in a highly interpretable stylized space, enabling 3D-aware animatable reconstruction and editing. Our rationale is to transfer the int...Show More

Learning an Interpretable Stylized Subspace for 3D-Aware Animatable Artforms

Chenxi Zheng;Bangzhen Liu;Xuemiao Xu;Huaidong Zhang;Shengfeng He

Year: 2025 | Volume: 31, Issue: 2 | Journal Article |

Delving Into Multi-Illumination Monocular Depth Estimation: A New Dataset and Method

Yuan Liang;Zitian Zhang;Chuhua Xian;Shengfeng He

IEEE Transactions on Multimedia
Year: 2025 | Volume: 27 | Journal Article |
Monocular depth prediction has received significant attention in recent years. However, the impact of illumination variations, which can shift scenes to unseen domains, has often been overlooked. To address this, we introduce the first indoor scene dataset featuring RGB-D images captured under multiple illumination conditions, allowing for a comprehensive exploration of indoor depth prediction. Ad...Show More

Delving Into Multi-Illumination Monocular Depth Estimation: A New Dataset and Method

Yuan Liang;Zitian Zhang;Chuhua Xian;Shengfeng He

Year: 2025 | Volume: 27 | Journal Article |

StyleGAN-$\infty$: Extending StyleGAN to Arbitrary-Ratio Translation with StyleBook

Yihua Dai;Tianyi Xiang;Bailin Deng;Yong Du;Hongmin Cai;Jing Qin;Shengfeng He

IEEE Transactions on Visualization and Computer Graphics
Year: 2024 | Early Access Article |
Although pre-trained large-scale generative models StyleGAN series have proven to be effective in various editing and translation tasks, they are limited to pre-defined fixed aspect ratio. To overcome this limitation, we propose StyleGAN-$\infty$, a model that enables pre-trained StyleGAN to perform arbitrary-ratio conditional synthesis. Our key insight is to distill the expressive StyleGAN featur...Show More

StyleGAN-$\infty$: Extending StyleGAN to Arbitrary-Ratio Translation with StyleBook

Yihua Dai;Tianyi Xiang;Bailin Deng;Yong Du;Hongmin Cai;Jing Qin;Shengfeng He

Year: 2024 | Early Access Article |

MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention

Rui Yang;Xiaojun Wu;Shengfeng He

IEEE Transactions on Visualization and Computer Graphics
Year: 2024 | Early Access Article |
Current sketch extraction methods either require extensive training or fail to capture a wide range of artistic styles, limiting their practical applicability and versatility. We introduce Mixture-of-Self-Attention (MixSA), a training-free sketch extraction method that leverages strong diffusion priors for enhanced sketch perception. At its core, MixSA employs a mixture-of-self-attention technique...Show More

MixSA: Training-free Reference-based Sketch Extraction via Mixture-of-Self-Attention

Rui Yang;Xiaojun Wu;Shengfeng He

Year: 2024 | Early Access Article |

Rethinking Multi-View Representation Learning via Distilled Disentangling

Guanzhou Ke;Bo Wang;Xiaoli Wang;Shengfeng He

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2024 | Conference Paper |
Cited by: Papers (1)
Multi-view representation learning aims to derive robust representations that are both view-consistent and view-specific from diverse data sources. This paper presents an in-depth analysis of existing approaches in this domain, highlighting a commonly overlooked aspect: the redundancy between view-consistent and view-specific representations. To this end, we propose an innovative framework for mul...Show More

Rethinking Multi-View Representation Learning via Distilled Disentangling

Guanzhou Ke;Bo Wang;Xiaoli Wang;Shengfeng He

Year: 2024 | Conference Paper |

Learning with Unreliability: Fast Few-Shot Voxel Radiance Fields with Relative Geometric Consistency

Yingjie Xu;Bangzhen Liu;Hao Tang;Bailin Deng;Shengfeng He

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2024 | Conference Paper |
We propose a voxel-based optimization framework, Re VoRF, for few-shot radiance fields that strategically ad-dress the unreliability in pseudo novel view synthesis. Our method pivots on the insight that relative depth relationships within neighboring regions are more reliable than the ab-solute color values in disoccluded areas. Consequently, we devise a bilateral geometric consistency loss that c...Show More

Learning with Unreliability: Fast Few-Shot Voxel Radiance Fields with Relative Geometric Consistency

Yingjie Xu;Bangzhen Liu;Hao Tang;Bailin Deng;Shengfeng He

Year: 2024 | Conference Paper |

Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation

Haofeng Liu;Chenshu Xu;Yifei Yang;Lihua Zeng;Shengfeng He

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2024 | Conference Paper |
Cited by: Papers (2)
Point-based interactive editing serves as an essential tool to complement the controllability of existing generative mod-els. A concurrent work, DragD iffus ion, updates the diffusion latent map in response to user inputs, causing global latent map alterations. This results in imprecise preservation of the original content and unsuccessful editing due to gradient vanishing. In contrast, we present...Show More

Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation

Haofeng Liu;Chenshu Xu;Yifei Yang;Lihua Zeng;Shengfeng He

Year: 2024 | Conference Paper |

D3still: Decoupled Differential Distillation for Asymmetric Image Retrieval

Yi Xie;Yihong Lin;Wenjie Cai;Xuemiao Xu;Huaidong Zhang;Yong Du;Shengfeng He

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2024 | Conference Paper |
Cited by: Papers (3)
Existing methods for asymmetric image retrieval employ a rigid pairwise similarity constraint between the query network and the larger gallery network. However, these one-to-one constraint approaches often fail to maintain retrieval order consistency, especially when the query network has limited representational capacity. To overcome this problem, we introduce the Decoupled Differential Distillat...Show More

D3still: Decoupled Differential Distillation for Asymmetric Image Retrieval

Yi Xie;Yihong Lin;Wenjie Cai;Xuemiao Xu;Huaidong Zhang;Yong Du;Shengfeng He

Year: 2024 | Conference Paper |

Beyond Textual Constraints: Learning Novel Diffusion Conditions with Fewer Examples

Yuyang Yu;Bangzhen Liu;Chenxi Zheng;Xuemiao Xu;Shengfeng He;Huaidong Zhang

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2024 | Conference Paper |
Cited by: Papers (1)
In this paper, we delve into a novel aspect of learning novel diffusion conditions with datasets an order of magnitude smaller. The rationale behind our approach is the elimination of textual constraints during the few-shot learning process. To that end, we implement two optimization strategies. The first, prompt-free conditional learning, utilizes a prompt-free encoder derived from a pre-trained ...Show More

Beyond Textual Constraints: Learning Novel Diffusion Conditions with Fewer Examples

Yuyang Yu;Bangzhen Liu;Chenxi Zheng;Xuemiao Xu;Shengfeng He;Huaidong Zhang

Year: 2024 | Conference Paper |

G²Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors

Haoxin Yang;Xuemiao Xu;Cheng Xu;Huaidong Zhang;Jing Qin;Yi Wang;Pheng-Ann Heng;Shengfeng He

IEEE Transactions on Information Forensics and Security
Year: 2024 | Volume: 19 | Journal Article |
Reversible face anonymization, unlike traditional face pixelization, seeks to replace sensitive identity information in facial images with synthesized alternatives, preserving privacy without sacrificing image clarity. Traditional methods, such as encoder-decoder networks, often result in significant loss of facial details due to their limited learning capacity. Additionally, relying on latent man...Show More

G²Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors

Haoxin Yang;Xuemiao Xu;Cheng Xu;Huaidong Zhang;Jing Qin;Yi Wang;Pheng-Ann Heng;Shengfeng He

Year: 2024 | Volume: 19 | Journal Article |

Modality-Aware Discriminative Fusion Network for Integrated Analysis of Brain Imaging Genomics

Xiaoqi Sheng;Hongmin Cai;Yongwei Nie;Shengfeng He;Yiu-Ming Cheung;Jiazhou Chen

IEEE Transactions on Neural Networks and Learning Systems
Year: 2024 | Early Access Article |
Mild cognitive impairment (MCI) represents an early stage of Alzheimer’s disease (AD), characterized by subtle clinical symptoms that pose challenges for accurate diagnosis. The quest for the identification of MCI individuals has highlighted the importance of comprehending the underlying mechanisms of disease causation. Integrated analysis of brain imaging and genomics offers a promising avenue fo...Show More

Modality-Aware Discriminative Fusion Network for Integrated Analysis of Brain Imaging Genomics

Xiaoqi Sheng;Hongmin Cai;Yongwei Nie;Shengfeng He;Yiu-Ming Cheung;Jiazhou Chen

Year: 2024 | Early Access Article |

3D Snapshot: Invertible Embedding of 3D Neural Representations in a Single Image

Yuqin Lu;Bailin Deng;Zhixuan Zhong;Tianle Zhang;Yuhui Quan;Hongmin Cai;Shengfeng He

IEEE Transactions on Pattern Analysis and Machine Intelligence
Year: 2024 | Volume: 46, Issue: 12 | Journal Article |
3D neural rendering enables photo-realistic reconstruction of a specific scene by encoding discontinuous inputs into a neural representation. Despite the remarkable rendering results, the storage of network parameters is not transmission-friendly and not extendable to metaverse applications. In this paper, we propose an invertible neural rendering approach that enables generating an interactive 3D...Show More

3D Snapshot: Invertible Embedding of 3D Neural Representations in a Single Image

Yuqin Lu;Bailin Deng;Zhixuan Zhong;Tianle Zhang;Yuhui Quan;Hongmin Cai;Shengfeng He

Year: 2024 | Volume: 46, Issue: 12 | Journal Article |

Question Type-Aware Debiasing for Test-Time Visual Question Answering Model Adaptation

Jin Liu;Jialong Xie;Fengyu Zhou;Shengfeng He

IEEE Transactions on Circuits and Systems for Video Technology
Year: 2024 | Volume: 34, Issue: 11 | Journal Article |
In Visual Question Answering (VQA), addressing language prior bias, where models excessively rely on superficial correlations between questions and answers, is crucial. This issue becomes more pronounced in real-world applications with diverse domains and varied question-answer distributions during testing. To tackle this challenge, Test-time Adaptation (TTA) has emerged, allowing pre-trained VQA ...Show More

Question Type-Aware Debiasing for Test-Time Visual Question Answering Model Adaptation

Jin Liu;Jialong Xie;Fengyu Zhou;Shengfeng He

Year: 2024 | Volume: 34, Issue: 11 | Journal Article |

Delving Into Important Samples of Semi-Supervised Old Photo Restoration: A New Dataset and Method

Weiwei Cai;Huaidong Zhang;Xuemiao Xu;Chenshu Xu;Kun Zhang;Shengfeng He

IEEE Transactions on Multimedia
Year: 2024 | Volume: 26 | Journal Article |
The degradation of printed photographs due to inadequate preservation is a major problem that can be addressed through deep learning-based restoration methods. However, these methods are often limited by their reliance on annotated data, making them less effective for new domains with limited training samples. In this paper, we propose a semi-supervised old photo restoration network that employs a...Show More

Delving Into Important Samples of Semi-Supervised Old Photo Restoration: A New Dataset and Method

Weiwei Cai;Huaidong Zhang;Xuemiao Xu;Chenshu Xu;Kun Zhang;Shengfeng He

Year: 2024 | Volume: 26 | Journal Article |

DreamAnime: Learning Style-Identity Textual Disentanglement for Anime and Beyond

Chenshu Xu;Yangyang Xu;Huaidong Zhang;Xuemiao Xu;Shengfeng He

IEEE Transactions on Visualization and Computer Graphics
Year: 2024 | Early Access Article |
Text-to-image generation models have significantly broadened the horizons of creative expression through the power of natural language. However, navigating these models to generate unique concepts, alter their appearance, or reimagine them in unfamiliar roles presents an intricate challenge. For instance, how can we exploit language-guided models to transpose an anime character into a different ar...Show More

DreamAnime: Learning Style-Identity Textual Disentanglement for Anime and Beyond

Chenshu Xu;Yangyang Xu;Huaidong Zhang;Xuemiao Xu;Shengfeng He

Year: 2024 | Early Access Article |

DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollers

Xiao Ma;Shengfeng He;Hezhe Qiao;Dong Ma

2024 IEEE International Conference on Pervasive Computing and Communications (PerCom)
Year: 2024 | Conference Paper |
Cited by: Papers (1)
Enabling efficient and accurate deep neural network (DNN) inference on microcontrollers is non-trivial due to the constrained on-chip resources. Current methodologies primarily focus on compressing larger models yet at the expense of model accuracy. In this paper, we rethink the problem from the inverse perspective by constructing small/weak models directly and improving their accuracy. Thus, we i...Show More

DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollers

Xiao Ma;Shengfeng He;Hezhe Qiao;Dong Ma

Year: 2024 | Conference Paper |

Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting

Zheng Xiong;Liangyu Chai;Wenxi Liu;Yongtuo Liu;Sucheng Ren;Shengfeng He

2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Year: 2024 | Conference Paper |
Cited by: Papers (3)
Crowd image is arguably one of the most laborious data to annotate. In this paper, we aim to reduce the massive demand for densely labeled crowd data, and propose a novel weakly-supervised setting, in which we leverage the binary ranking of two images with high-contrast crowd counts as training guidance. To enable training under this new setting, we convert the crowd count regression problem to a ...Show More

Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting

Zheng Xiong;Liangyu Chai;Wenxi Liu;Yongtuo Liu;Sucheng Ren;Shengfeng He

Year: 2024 | Conference Paper |

Unifying Global-Local Representations in Salient Object Detection With Transformers

Sucheng Ren;Nanxuan Zhao;Qiang Wen;Guoqiang Han;Shengfeng He

IEEE Transactions on Emerging Topics in Computational Intelligence
Year: 2024 | Volume: 8, Issue: 4 | Journal Article |
Cited by: Papers (5)
The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global receptive field and such a deep model always leads to the loss of local details. In this paper, we introduce a new attention-based encoder, vision transformer, into salient object detection to ensure the globalization of the re...Show More

Unifying Global-Local Representations in Salient Object Detection With Transformers

Sucheng Ren;Nanxuan Zhao;Qiang Wen;Guoqiang Han;Shengfeng He

Year: 2024 | Volume: 8, Issue: 4 | Journal Article |

Monocular BEV Perception of Road Scenes via Front-to-Top View Projection

Wenxi Liu;Qi Li;Weixiang Yang;Jiaxin Cai;Yuanlong Yu;Yuexin Ma;Shengfeng He;Jia Pan

IEEE Transactions on Pattern Analysis and Machine Intelligence
Year: 2024 | Volume: 46, Issue: 9 | Journal Article |
HD map reconstruction is crucial for autonomous driving. LiDAR-based methods are limited due to expensive sensors and time-consuming computation. Camera-based methods usually need to perform road segmentation and view transformation separately, which often causes distortion and missing content. To push the limits of the technology, we present a novel framework that reconstructs a local map formed ...Show More

Monocular BEV Perception of Road Scenes via Front-to-Top View Projection

Wenxi Liu;Qi Li;Weixiang Yang;Jiaxin Cai;Yuanlong Yu;Yuexin Ma;Shengfeng He;Jia Pan

Year: 2024 | Volume: 46, Issue: 9 | Journal Article |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.