Ka Chun Cheung
24 papers · 2022–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (54) π Interdisciplinary Bridge π Conference Polyglot (6) π Renaissance Researcher (6) π§ Keyword Pioneer
π
Conference Polyglot
(6)
π
Renaissance Researcher
(6)
π€
Dynamic Duo
(14)
β‘
Prolific Year
(7)
π
Century Club
(24)
ποΈ
Keyword Collector
(97)
Conferences
CVPR (6)
ECCV (5)
AAAI (4)
ICCV (4)
EMNLP (3)
NIPS (2)
Top co-authors
Keywords
multimodal learning
(3)
copyright protection
(3)
multi-modal learning
(2)
model calibration
(2)
autonomous driving
(2)
knowledge distillation
(2)
state-space model
(2)
optical flow
(2)
vision-language model
(2)
vision language model
(2)
optical flow estimation
(2)
attention mechanism
(1)
temporal modeling
(1)
medical imaging
(1)
motion estimation
(1)
multi-task learning
(1)
3d reconstruction
(1)
video generation
(1)
trajectory prediction
(1)
adversarial learning
(1)
Papers
One-Minute Video Generation with Test-Time Training
CVPR 2025
Parallel Sequence Modeling via Generalized Spatial Propagation Network
CVPR 2025
Token-Efficient VLM: High-Resolution Image Understanding via Dynamic Region Proposal
ICCV 2025
M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving
AAAI 2025
Meme Trojan: Backdoor Attacks Against Hateful Meme Detection via Cross-Modal Triggers
AAAI 2025
Test-Time Adaptation on Noisy Data via Model-Pruning-Based Filtering and Flatness-Aware Entropy Minimization
AAAI 2025
GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting
NIPS 2024
Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images
NIPS 2024
RegionGPT: Towards Region Understanding Vision Language Model
CVPR 2024
AHIVE: Anatomy-aware Hierarchical Vision Encoding for Interactive Radiology Report Retrieval
CVPR 2024
GeometrySticker: Enabling Ownership Claim of Recolorized Neural Radiance Fields
ECCV 2024
Protecting NeRFs' Copyright via Plug-And-Play Watermarking Base Model
ECCV 2024
Unlocking Continual Learning Abilities in Language Models
EMNLP 2024
NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension
AAAI 2023
TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses
ICCV 2023
FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
CVPR 2023
A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift
CVPR 2023
VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
ICCV 2023
CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields
ICCV 2023
MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
ECCV 2022
Learning Degradation Representations for Image Deblurring
ECCV 2022
Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation
EMNLP 2022
Hard Gate Knowledge Distillation - Leverage Calibration for Robust and Reliable Language Model
EMNLP 2022
FlowFormer: A Transformer Architecture for Optical Flow
ECCV 2022