Yi Chang

37

Papers

48

Total Citations

Papers (37)

Seeing Motion at Nighttime with an Event Camera

EPSD: Early Pruning with Self-Distillation for Efficient Model Compression

Detection-Friendly Nonuniformity Correction: A Union Framework for Infrared UAV Target Detection

TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion

FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking

FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis

High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation

InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning

Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning

ContraDiff: Planning Towards High Return States via Contrastive Learning

Collaborative Discrete-Continuous Black-Box Prompt Learning for Language Models

Concept Matching with Agent for Out-of-Distribution Detection

SIGMA: Selective Gated Mamba for Sequential Recommendation

Leveraging First and Zeroth-Order Gradient to Address Imbalanced Black-Box Prompt Tuning via Minimax Optimization

Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow

DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning

An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series

Double Momentum Method for Lower-Level Constrained Bilevel Optimization

Hyper-Laplacian Regularized Unidirectional Low-Rank Tensor Recovery for Multispectral Image Denoising

Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation

Physically Disentangled Intra- and Inter-Domain Adaptation for Varicolored Haze Removal

Unsupervised Deraining: Where Contrastive Learning Meets Self-Similarity

Event-Based Video Reconstruction via Potential-Assisted Spiking Neural Network

Unsupervised Cumulative Domain Adaptation for Foggy Scene Optical Flow

Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching Between Parts and Words

Transformed Low-Rank Model for Line Pattern Noise Removal

Both Diverse and Realism Matter: Physical Attribute and Style Alignment for Rainy Image Generation

From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal

Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow

OmniStereo: Real-time Omnidireactional Depth Estimation with Multiview Fisheye Cameras

CGMatch: A Different Perspective of Semi-supervised Learning

Beyond Words: Augmenting Discriminative Richness via Diffusions in Unsupervised Prompt Learning

Query Efficient Black-Box Visual Prompting with Subspace Learning

MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler

Distributional Reward Estimation for Effective Multi-agent Deep Reinforcement Learning

Learning Generalizable Agents via Saliency-guided Features Decorrelation