Kun Li

12

Papers

107

Total Citations

Papers (12)

Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition

Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture

BotSim: LLM-Powered Malicious Social Botnet Simulation

BVINet: Unlocking Blind Video Inpainting with Zero Annotations

LPSNet: End-to-End Human Pose and Shape Estimation with Lensless Imaging

ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning

Joint2Human: High-Quality 3D Human Generation via Compact Spherical Embedding of 3D Joints

MMAD: Multi-label Micro-Action Detection in Videos

Patch-level Sounding Object Tracking for Audio-Visual Question Answering

EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer

KeDuSR: Real-World Dual-Lens Super-resolution via Kernel-Free Matching

RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters