Search Results - "Xuelin Qian"
-
1
Multi-scale Deep Learning Architectures for Person Re-identification
Published in 2017 IEEE International Conference on Computer Vision (ICCV) (01-10-2017)“…Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people…”
Get full text
Conference Proceeding -
2
Leader-Based Multi-Scale Attention Deep Architecture for Person Re-Identification
Published in IEEE transactions on pattern analysis and machine intelligence (01-02-2020)“…Person re-identification (re-id) aims to match people across non-overlapping camera views in a public space. This is a challenging problem because the people…”
Get full text
Journal Article -
3
Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification
Published in IEEE transactions on information forensics and security (2024)“…Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior discriminative features and…”
Get full text
Journal Article -
4
Dynamic Routing and Knowledge Re-Learning for Data-Free Black-Box Attack
Published in IEEE transactions on pattern analysis and machine intelligence (27-09-2024)“…Deep learning models have emerged as strong and efficient tools that can be applied to a broad spectrum of complex learning problems and many real-world…”
Get full text
Journal Article -
5
Advances and perspectives on the life-cycle impact assessment of personal protective equipment in the post-COVID-19 pandemic
Published in Journal of cleaner production (15-01-2024)“…The coronavirus disease 2019 (COVID-19) pandemic initiated an unprecedented surge in production and consumption of personal protective equipment (PPE). There…”
Get full text
Journal Article -
6
DST: Dynamic Substitute Training for Data-free Black-box Attack
Published in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2022)“…With the wide applications of deep neural network models in various computer vision tasks, more and more works study the model vulnerability to adversarial…”
Get full text
Conference Proceeding -
7
M ^3Lung-Sys: A Deep Learning System for Multi-Class Lung Pneumonia Screening From CT Imaging
Published in IEEE journal of biomedical and health informatics (01-12-2020)“…To counter the outbreak of COVID-19, the accurate diagnosis of suspected cases plays a crucial role in timely quarantine, medical treatment, and preventing the…”
Get full text
Journal Article -
8
M 3 Lung-Sys: A Deep Learning System for Multi-Class Lung Pneumonia Screening From CT Imaging
Published in IEEE journal of biomedical and health informatics (01-12-2020)“…To counter the outbreak of COVID-19, the accurate diagnosis of suspected cases plays a crucial role in timely quarantine, medical treatment, and preventing the…”
Get full text
Journal Article -
9
M[Formula Omitted]Lung-Sys: A Deep Learning System for Multi-Class Lung Pneumonia Screening From CT Imaging
Published in IEEE journal of biomedical and health informatics (01-01-2020)“…To counter the outbreak of COVID-19, the accurate diagnosis of suspected cases plays a crucial role in timely quarantine, medical treatment, and preventing the…”
Get full text
Journal Article -
10
ImpDet: Exploring Implicit Fields for 3D Object Detection
Published in 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (01-01-2023)“…Conventional 3D object detection approaches concentrate on bounding boxes representation learning with several parameters, i.e., localization, dimension, and…”
Get full text
Conference Proceeding -
11
Causally-Aware Intraoperative Imputation for Overall Survival Time Prediction
Published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2023)“…Previous efforts in vision community are mostly made on learning good representations from visual patterns. Beyond this, this paper emphasizes the high-level…”
Get full text
Conference Proceeding -
12
When Person Re-identification Meets Changing Clothes
Published in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01-06-2020)“…Person re-identification (ReID) is now an active research topic for AI-based video surveillance applications such as specific person search, but the practical…”
Get full text
Conference Proceeding -
13
FM2u-Net: Face Morphological Multi-Branch Network for Makeup-Invariant Face Verification
Published in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2020)“…It is challenging in learning a makeup-invariant face verification model, due to (1) insufficient makeup/non-makeup face training pairs, (2) the lack of…”
Get full text
Conference Proceeding -
14
Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification
Published 20-06-2024“…Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior discriminative features and…”
Get full text
Journal Article -
15
Distribution Aligned Semantics Adaption for Lifelong Person Re-Identification
Published 30-05-2024“…In real-world scenarios, person Re-IDentification (Re-ID) systems need to be adaptable to changes in space and time. Therefore, the adaptation of Re-ID models…”
Get full text
Journal Article -
16
Hyper-Transformer for Amodal Completion
Published 30-05-2024“…Amodal object completion is a complex task that involves predicting the invisible parts of an object based on visible segments and background information…”
Get full text
Journal Article -
17
Auto-selected Knowledge Adapters for Lifelong Person Re-identification
Published 29-05-2024“…Lifelong Person Re-Identification (LReID) extends traditional ReID by requiring systems to continually learn from non-overlapping datasets across different…”
Get full text
Journal Article -
18
Image-Text-Image Knowledge Transferring for Lifelong Person Re-Identification with Hybrid Clothing States
Published 26-05-2024“…With the continuous expansion of intelligent surveillance networks, lifelong person re-identification (LReID) has received widespread attention, pursuing the…”
Get full text
Journal Article -
19
fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decoding
Published 01-11-2023“…The exploration of brain activity and its decoding from fMRI data has been a longstanding pursuit, driven by its potential applications in brain-computer…”
Get full text
Journal Article -
20
Rethinking Person Re-identification from a Projection-on-Prototypes Perspective
Published 21-08-2023“…Person Re-IDentification (Re-ID) as a retrieval task, has achieved tremendous development over the past decade. Existing state-of-the-art methods follow an…”
Get full text
Journal Article