News
[2024/02] One paper accepted by CVPR 2024.
[2024/02] One paper accepted by IEEE TMM.
[2024/01] One paper accepted by AAAI 2024.
[2023/09] One paper accepted by IEEE TII.
[2023/08] One paper accepted by IEEE TIP.
[2023/07] Two papers accepted by ICCV 2023.
[2023/06] One paper accepted by IEEE TIP.
[2023/05] One paper accepted by IEEE TCSVT.
[2023/04] One paper accepted by KBS.
[2022/06] One paper accepted by IEEE TNNLS.
[2022/03] One oral paper accepted by CVPR 2022.
[2021/08] One paper accepted by IEEE TCSVT.
|
Research
I'm interested in image/video restoration, low-quality/degraded detection, and fine-grained recognition. Much of my research is about low-level vision. Representative papers are highlighted. (* indicates equal contribution)
|
|
Split-Check: Boosting Product Recognition via Instance-Level Retrieval
Chengxu Liu,
Zongyang Da,
Yuanzhi Liang,
Yao Xue,
Guoshuai Zhao,
Xueming Qian
IEEE TII, 2023
We propose a product recognition approach based on intelligent UVMs, called Split-Check, which first splits the region of interest of products by detection and then check product by instance-level retrieval.
|
|
FSI: Frequency and Spatial Interactive Learning for Image Restoration in Under-Display Cameras
Chengxu Liu,
Xuan Wang,
Shuai Li,
Yuzhi Wang,
Xueming Qian
ICCV, 2023
[PDF]
[ArXiv]
[Code]
[Supp]
We introduce a new perspective to handle various diffraction in UDC images by jointly exploring the feature restoration in the frequency and spatial domains, and present a Frequency and Spatial Interactive Learning Network (FSI).
|
|
CSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection
Changlong Gao*,
Chengxu Liu*,
Yujie Dun,
Xueming Qian
ICCV, 2023
[PDF]
[ArXiv]
[Code]
[Supp]
For better category-level feature alignment, we propose a novel DAOD framework of joint category and scale information, dubbed CSDA, such a design enables effective object learning for different scales.
|
|
TTVFI: Learning Trajectory-Aware Transformer for Video Frame Interpolation
Chengxu Liu,
Huan Yang,
Jianlong Fu,
Xueming Qian
IEEE TIP, 2023
[PDF]
[arXiv]
[Code]
We propose a novel Trajectory-aware Transformer for Video Frame Interpolation (TTVFI), which formulate the warped features with inconsistent motions as query tokens, and formulate relevant regions in a motion trajectory from two original consecutive frames into keys and values.
|
|
4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement
Chengxu Liu,
Huan Yang,
Jianlong Fu,
Xueming Qian
IEEE TIP, 2023
[PDF]
[arXiv]
[Code]
We propose a novel learnable context-aware 4-dimensional lookup table (4D LUT), which achieves content-dependent enhancement of different contents in each image via adaptively learning of photo context.
|
|
AJENet: Adaptive Joints Enhancement Network for Abnormal Behavior Detection in Office Scenario
Chengxu Liu,
Yaru Zhang,
Yao Xue,
Xueming Qian
IEEE TCSVT, 2023
We focus on human joints and take one step further to enable effective behavior characteristics learning in office scenarios. In particular, we propose a novel Adaptive Joints Enhancement Network (AJENet).
|
|
Anomaly Detection Framework for Unmanned Vending Machines
Zongyang Da,
Yujie Dun,
Chengxu Liu,
Yuanzhi Liang,
Yao Xue,
Xueming Qian
KBS, 2023
We propose an unmanned retail anomaly detection method based on deep convolutional neural networks (CNNs) called the complexity-classification anomaly detection (ClassAD) framework.
|
|
Product Recognition for Unmanned Vending Machines
Chengxu Liu,
Zongyang Da,
Yuanzhi Liang,
Yao Xue,
Guoshuai Zhao,
Xueming Qian
IEEE TNNLS, 2022
We propose a method for large-scale categories product recognition based on intelligent UVMs. The highlights of our method are mine potential similarity between large-scale category products and optimization through hierarchical multigranularity labels
|
|
Learning Trajectory-Aware Transformer for Video Super-Resolution
Chengxu Liu,
Huan Yang,
Jianlong Fu,
Xueming Qian
CVPR (Oral presentation), 2022
[PDF]
[arXiv]
[Code]
[Supp]
We propose a novel Trajectory-aware Transformer for Video Super-Resolution (TTVSR), which formulate video frames into several pre-aligned trajectories which consist of continuous visual tokens. For a query token, self-attention is only learned on relevant visual tokens along spatio-temporal trajectories.
|
|
Food and Ingredient Joint Learning for Fine-Grained Recognition
Chengxu Liu,
Yuanzhi Liang,
Yao Xue,
Xueming Qian,
Jianlong Fu
IEEE TCSVT, 2021
We propose an Attention Fusion Network (AFN) and Food-Ingredient Joint Learning module for fine-grained food and ingredients recognition.
|
Honors and Awards
[2024/01] Baidu Scholarship Top 20 in the World.
[2023/12] The postgraduate “Academic Star” of Xi'an Jiaotong University.(10 per year)
[2023/10] Excellent Graduate Student, Xi'an Jiaotong University.
[2023/10] Principal Scholarship of Postgraduates, Xi'an Jiaotong University.
[2023/08] 1st Prize in Northwest, Postgraduate Electronics Design Contest, Ministry of Education of China.
[2022/12] Pacesetter for Postgraduate Student (The highest honor in XJTU, 16 Ph.D. per year), Xi'an Jiaotong University.
[2022/12] National Scholarship, Ministry of Education of China.
[2022/11] 2nd Prize, 34th "Tengfei Cup" Innovation and Entrepreneurship Competition, Xi'an Jiaotong University.
[2022/11] 3rd Prize, 34th "Tengfei Cup" Innovation and Entrepreneurship Competition, Xi'an Jiaotong University.
[2022/08] National Most Commercially Valuable Award, Postgraduate Electronics Design Contest, Chinese Institute of Electronics (8/5700+, 0.14\% award rate).
[2022/08] National 1st Prize, Postgraduate Electronics Design Contest, Chinese Institute of Electronics (32/5700+, 0.56\% award rate).
[2022/08] 1st Prize in Northwest, Postgraduate Electronics Design Contest, Ministry of Education of China.
[2022/06] 2nd Prize, Postgraduate Internet+ Contest, Ministry of Education of Shannxi.
[2022/05] Stars of Tomorrow Internship Program, Microsoft Research Asia.
[2021/10] Excellent Graduate Student, Xi'an Jiaotong University.
[2020/10] Excellent Graduate Student, Xi'an Jiaotong University.
[2020/10] Principal Scholarship of Postgraduates, Xi'an Jiaotong University.
[2019/07] Outstanding Graduate Cadre, Xi'an Jiaotong University.
|
Reviewer
Conference: SIGGRAPH 2024, ICCV 2023, ECCV 2024,2022, CVPR 2024,2023,2022, ICME 2024,2023,2022.
Journal: IEEE TIP, IEEE TMM, IEEE TNNLS, IEEE TCSVT, KBS.
|
|