Kai Zhu

16

Papers

150

Total Citations

Papers (16)

Recognize Complex Events From Static Images by Fusing Deep Channels

Improved Video VAE for Latent Video Diffusion Model

BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs

State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning

Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning

Neural Dependencies Emerging From Learning Massive Categories

Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection

Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-Trained Vision-Language Models

Self-Organizing Pathway Expansion for Non-Exemplar Class-Incremental Learning

MangaNinja: Line Art Colorization with Precise Reference Following

Hypercorrelation Evolution for Video Class-Incremental Learning

HomoFormer: Homogenized Transformer for Image Shadow Removal

CCM: Real-Time Controllable Visual Content Creation Using Text-to-Image Consistency Models

Uncertainty-Aware Hierarchical Refinement for Incremental Implicitly-Refined Classification

Customizable Image Synthesis with Multiple Subjects