Ka Chun Cheung

16

Papers

71

Total Citations

Papers (16)

One-Minute Video Generation with Test-Time Training

Meme Trojan: Backdoor Attacks Against Hateful Meme Detection via Cross-Modal Triggers

Parallel Sequence Modeling via Generalized Spatial Propagation Network

Test-Time Adaptation on Noisy Data via Model-Pruning-Based Filtering and Flatness-Aware Entropy Minimization

RegionGPT: Towards Region Understanding Vision Language Model

AHIVE: Anatomy-aware Hierarchical Vision Encoding for Interactive Radiology Report Retrieval

A Simple Baseline for Video Restoration With Grouped Spatial-Temporal Shift

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation

TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses

VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation

CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields

MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection

FlowFormer: A Transformer Architecture for Optical Flow

Learning Degradation Representations for Image Deblurring

Token-Efficient VLM: High-Resolution Image Understanding via Dynamic Region Proposal

M3Net: Multimodal Multi-task Learning for 3D Detection, Segmentation, and Occupancy Prediction in Autonomous Driving