Yaping Zhao

Ph.D. Candidate at HKU
Email: zhaoyp (at) connect.hku.hk
Google Scholar | ResearchGate

Selected Publications

(#Co-first Author  *Corresponding Author)

ICIP 2024 (Oral Acceptance Rate ~15%)
Controllable Unsupervised Event-based Video Generation
Y. Zhao, P. Zhang, C. Wang, E. Y. Lam
paper | code

ICONIP 2024 (Oral)
eSports Broadcasts with Event Cameras
Y. Zhao, R. Chen, C. Wang, E. Y. Lam
code

ICASSP 2024
SASA: Saliency-Aware Self-Adaptive Snapshot Compressive Imaging
Y. Zhao, E. Y. Lam
paper | code

ICASSP 2024
Cross-Camera Human Motion Transfer by Time Series Analysis
Y. Zhao, G. Li, E. Y. Lam
paper | code

BDMA 2024 (Impact Factor upon Acceptance: 13.6)
House Price Prediction: A Multi-Source Data Fusion Perspective
Y. Zhao, J. Zhao, E. Y. Lam
paper | dataset | code

BDMA 2024 (Impact Factor upon Acceptance: 13.6)
A Large-Scale Spatio-Temporal Multimodal Fusion Framework for Traffic Prediction
B. Zhou, J. Liu, S. Cui, Y. Zhao*
paper | dataset

TIP 2024 (Impact Factor upon Acceptance: 10.8)
Semi-Supervised Semantic Segmentation for Light Field Images using Disparity Information
S. Zhang, Y. Zhao, E. Y. Lam
paper

Neuromorphic Imaging with Super-Resolution
(under review)
P. Zhang, S. Zhu, C. Wang, Y. Zhao, E. Y. Lam
paper

IEEE OGC 2024 (Oral)
LUCK: Lighting Up Colors in the Dark
Y. Zhao, E. Y. Lam
paper | code

AAAI 2023 (Acceptance Rate 19.6%)
Deep Equilibrium Models for Video Snapshot Compressive Imaging
Y. Zhao, S. Zheng, X. Yuan
paper | code | Mathematical Cookbook
reported by QbitAI, IntelligentOptics
video presentation on YouTube, Bilibili (English, Chinese, Cantonese)

ICIP 2023
Improving Video Colorization by Test-Time Tuning
Y. Zhao, H. Zheng, J. Luo, E. Y. Lam
paper | code | video presentation on YouTube, Bilibili

ICIP 2023
Point Cloud Denoising via Momentum Ascent in Gradient Fields
Y. Zhao, H. Zheng, Z. Wang, J. Luo, E. Y. Lam
paper | code | video presentation on YouTube, Bilibili

DSAA 2023 (Acceptance Rate 26.1%)
Adaptive Compressed Sensing for Real-Time Video Compression, Transmission, and Reconstruction
Y. Zhao, Q. Zeng, E. Y. Lam
paper | code

DSAA 2023 (Acceptance Rate 26.1%)
Solving Inverse Problems in Compressive Imaging with Score-Based Generative Models
Z. Y. Chong, Y. Zhao*#, Z. Wang, E. Y. Lam
paper | code

CICAI 2022 (Oral Acceptance Rate 3.8%)
Cross-Camera Deep Colorization
Y. Zhao, H. Zheng, M. Ji, R. Huang
paper | code
video presentation on YouTube, Bilibili

ICIP 2022
MANet: Improving Video Denoising with a Multi-Alignment Network
Y. Zhao, H. Zheng, Z. Wang, J. Luo, E. Y. Lam
paper | code | reported by IntelligentOptics
video presentation on YouTube, Bilibili

DSAA 2022 (Acceptance Rate 22.5%)
Improving Source Localization by Perturbing Graph Diffusion
Y. Zhao, Z. Wang, E. Y. Lam
paper | code

DSAA 2022 (Acceptance Rate 22.5%)
Large-Scale Traffic Congestion Prediction based on Multimodal Fusion and Representation Mapping
B. Zhou, J. Liu, S. Cui, Y. Zhao*
paper | dataset | code

DSAA 2022 (Acceptance Rate 22.5%)
H4M: Heterogeneous, Multi-source, Multi-modal, Multi-view and Multi-distributional Dataset for Socioeconomic Analytics in Case of Beijing
Y. Zhao, S. Shi, R. Ravi, Z. Wang, E. Y. Lam, J. Zhao
paper | dataset | code
video presentation on YouTube, Bilibili

DSAA 2022 (Acceptance Rate 22.5%)
PATE: Property, Amenities, Traffic and Emotions Coming Together for Real Estate Price Prediction
Y. Zhao, R. Ravi, S. Shi, Z. Wang, E. Y. Lam, J. Zhao
paper | dataset | code
video presentation on YouTube, Bilibili

CICAI 2021
EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation
Y. Zhao, M. Ji, R. Huang, B. Wang, S. Wang
paper | code

SPIE Proceedings 2021
Revisit Dictionary Learning for Video Compressive Sensing under the Plug-and-Play Framework
Q. Yang, Y. Zhao#
paper

ICIP 2020
Zoom in to the Details of Human-centric Videos
G. Li, Y. Zhao, M. Ji, X. Yuan, L. Fang
paper

Mathematical Cookbook for Snapshot Compressive Imaging (working, unfinished)
Y. Zhao*
paper

At the bottom of this page, you will find a list of my rejected papers. I record these for three reasons: first, to trace my own development over time; second, to remind myself during times of rejection that each paper will eventually find its place, alleviating unnecessary stress; and third, to demonstrate that success is not only about victories but also about growth.
To anyone who stumbles upon this list, I hope it serves as a source of encouragement and solace.

Rejected Papers

9. Y. Zhao et al., "SASA: Saliency-Aware Self-Adaptive Snapshot Compressive Imaging", rejected by IEEE International Conference on Image Processing (ICIP), 2023. Later accepted to ICASSP 2024.
8. Y. Zhao et al., "Cross-Camera Human Motion Transfer by Time Series Analysis", rejected by IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2022. Later accepted to ICASSP 2024.
7. Y. Zhao et al., "Point Cloud Denoising via Momentum Ascent in Gradient Fields", rejected by Asian Conference on Computer Vision (ACCV), 2022. Later accepted to ICIP 2023.
6. Y. Zhao et al., "Point Cloud Denoising via Momentum Ascent in Gradient Fields", rejected by IEEE International Conference on Image Processing (ICIP), 2022. Later submitted to ACCV 2022.
5. Y. Zhao et al., "Deep Equilibrium Models for Video Snapshot Compressive Imaging", rejected by European Conference on Computer Vision (ECCV), 2022. Later accepted to AAAI 2023.
4. Y. Zhao et al., "Deep Equilibrium Models for Video Snapshot Compressive Imaging", rejected by IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022. Later submitted to ECCV 2022.
3. Y. Zhao et al., "Cross-Camera Deep Colorization", rejected by IEEE Transactions on Image Processing (TIP), 2022. Later accepted to CICAI 2022.
2. Y. Zhao et al., "Cross-Camera Deep Colorization", rejected by IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021. Later submitted to TIP.
1. Y. Zhao et al., "Cross-Camera Deep Colorization", rejected by ACM Multimedia, 2020. Later submitted to WACV 2021.