Q. Tang
Ħ (+86) 188-1307-5618 | ć qitang@bjtu.edu.cn | u www.tang5618.com | ^ Tang1705 | ŵ QiTang
Education
Information & Communication Engineering (State Key Disciplines of First-class) Beijing Jiaotong University
Advised by Prof. Yao Zhao (IEEE Fellow). Research interest lies in Image/Video Restoration, Segmentation and Generation. Sept. 2022 -- Present
Software Engineering | Finance (Dual Degree) Beijing Jiaotong University
B.Eng. | B.Ec. (with honors) Sept. 2017 -- Jun. 2021
Publications
SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution } CCF-A
Qi Tang, Yao Zhao, Meiqin Liu*, and Chao Yao* NeurIPS 2024
Semantic Lens: Instance-Centric Semantic Alignment for Video Super-Resolution } CCF-A
Qi Tang, Yao Zhao, Meiqin Liu*, Jian Jin, and Chao Yao* AAAI 2024
A Review of Video Super-Resolution Algorithms Based on Deep Learning CCF-A
Qi Tang, Yao Zhao, Meiqin Liu*, and Chao Yao AAS 2024
BridgeNet: A Joint Learning Network of Depth Map Super-Resolution and Monocular Depth Estimation } CCF-A
Qi Tang, Runmin Cong*, Ronghui Sheng, Lingzhi He, Dan Zhang, Yao Zhao, and Sam Kwong ACM MM 2021
Noisy-Residual Continuous Diffusion Models for Real Image Denoising (Oral) } CCF-B
Xuan Long, Meiqin Liu*, Qi Tang, Chao Yao, Jian Jin, and Yao Zhao ICME 2024
TLVC: Temporal Bit-rate Allocation for Learned Video Compression (Oral) } CCF-B
Yifan Zhang, Meiqin Liu*, Chenming Xu, Qi Tang, Chao Yao, and Yao Zhao ICME 2024
DATA-VSR: Dynamic Trajectory Attention and Texture Adaptive Rooter for Video Super-Resolution CCF-B
Linfeng He, Meiqin Liu*, Qi Tang, Chao Yao, and Yao Zhao ICASSP 2025
ALIC: Adaptive Fusion Entropy Model for Learned Image Compression CCF-B
Lingxue Li, Meiqin Liu*, Yifan Zhang, Qi Tang, Chao Yao, and Yao Zhao ICASSP 2025
Experiences
Towards Human-Machine Friendly Learning-Based Video Coding International (Regional) Cooperation & Exchanges of NSFC
Beijing Key Laboratory of Advanced Information Science and Network Technology Participator
• Devised semantic-controlled VSR that combines patch-level blurring and residual shift in diffusion process and determines conditions by the
instance-centric and channel-wise semantics within and across clips during generation, enhancing content realism and temporal coherence.
• Proposed semantic-guided inter-frame alignment that decouples video into instance, event and scene and conducts semantic-guided instance-
centric alignment among adjacent frames, gaining better performance when facing with large motion amplitude and background change.
• Designed motion-driven temporal gate and texture-condition spatial gate based on the characteristic of residual coding, balancing the bit
allocation within video compression along the temporal axis.
Enhancement and Cognition of Video Content in Complex Scenes National Natural Science Foundation of China
Visual Intelligence + X International Cooperation Joint Laboratory of MOE Participator
• Exploring the inherent capability of MLLM to perceive semantics and degradation for the sake of dealing with complex and unknown deteri-
oration of video captured in real world via LoRA, etc.
High-Speed Railway Wheel-Rail Dynamic Contact Posture
Inspection System Based on High-Precision Structured Light
National Major Scientific Instruments and
Equipments Development Project of NSFC
Beijing Key Lab of Traffic Data Analysis and Mining Participator
• Implementing visualization and editing platform for dense point cloud that focuses on 3D reconstruction of wheel-rail posture of high-speed
railway via coded structured light in the single-shot manner.
Awards
National Scholarship for Graduate Excellence (top 1/50) 2023 -- 2024
Xiaomi Special Scholarship (only rewarding 6 graduate students annually) 2024
Merit Graduate Student 2024
First-class Scholarship of Beijing Jiaotong University 2022 -- 2024
Excellent Undergraduate Graduation Design (Thesis) of Beijing Ordinary Colleges and Universities 2021
National Training Program of Innovation and Entrepreneurship for Undergraduates 2020
Skills
Programming Python, JAVA, C, C++, PyTorch, TensorFlow, MindSpore, PaddlePaddle
Language & Tools Chinese & English (CET-6 547 | CET-4 540), L
A
T
E
X, MATLAB, PowerPoint, etc.
Q. Tang · Curriculum Vitae 1