Kun Li

23

Papers

107

Total Citations

Papers (23)

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

4D Association Graph for Realtime Multi-Person Motion Capture Using Multiple Video Cameras

PISE: Person Image Synthesis and Editing With Decoupled GAN

Cross-MPI: Cross-Scale Stereo for Image Super-Resolution Using Multiplane Images

High-Fidelity Human Avatars From a Single RGB Camera

Learning Semantic-Aware Disentangled Representation for Flexible 3D Human Body Editing

Crowd3D: Towards Hundreds of People Reconstruction From a Single Image

Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer

Narrator: Towards Natural Control of Human-Scene Interaction Generation via Relationship Reasoning

RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters

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

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

GPS-Net: Graph-based Photometric Stereo Network

Implicit Transformer Network for Screen Content Image Continuous Super-Resolution

FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction