Dahai Yu

Orcid: 0000-0003-1427-8807

Affiliations:
  • TCL Corporate Research (HK) Co., Ltd., Hong Kong
  • Dublin City University, Computer School, Dublin, Ireland (PhD 2008)


According to our database1, Dahai Yu authored at least 21 papers between 2007 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models.
CoRR, March, 2026

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression.
CoRR, February, 2026

TVWorld: Foundations for Remote-Control TV Agents.
CoRR, January, 2026

2025
SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control.
CoRR, August, 2025

DnLUT: Ultra-Efficient Color Image Denoising via Channel-Aware Lookup Tables.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024
Video-based face outline recognition.
Pattern Recognit., 2024

Hundred-Kilobyte Lookup Tables for Efficient Single-Image Super-Resolution.
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

2023
Adversarial Auto-encoder Domain Adaptation for Cold-start Recommendation with Positive and Negative Hypergraphs.
ACM Trans. Inf. Syst., April, 2023

Cold-Start Next-Item Recommendation by User-Item Matching and Auto-Encoders.
IEEE Trans. Serv. Comput., 2023

Assigned MURA Defect Generation Based on Diffusion Model.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Learning Intrinsic and Extrinsic Intentions for Cold-start Recommendation with Neural Stochastic Processes.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022


Recurring the Transformer for Video Action Recognition.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Multi-Interest Refinement by Collaborative Attributes Modeling for Click-Through Rate Prediction.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

2020
End-to-End Denoising of Dark Burst Images using Recurrent Fully Convolutional Networks.
Proceedings of the 15th International Joint Conference on Computer Vision, 2020

Learning from Rankings with Multi-level Features for No-Reference Image Quality Assessment.
Proceedings of the Pattern Recognition and Computer Vision, Third Chinese Conference, 2020

2019
SRDGAN: learning the noise prior for Super Resolution with Dual Generative Adversarial Networks.
CoRR, 2019

2017
A Saliency Based Human Detection Framework for Infrared Thermal Images.
Proceedings of the Computer Vision - Second CCF Chinese Conference, 2017

2014
Efficient highlight removal of metal surfaces.
Signal Process., 2014

2009
A Novel Visual Speech Representation and HMM Classification for Visual Speech Recognition.
Proceedings of the Advances in Image and Video Technology, Third Pacific Rim Symposium, 2009

2007
A New Manifold Representation for Visual Speech Recognition.
Proceedings of the Computer Analysis of Images and Patterns, 12th International Conference, 2007


  Loading...