Jiankang Deng

31

Papers

327

Total Citations

1

Affiliations

Affiliations

Imperial College London

Papers (31)

CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing

WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild

Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text

Boosting Object Detection with Zero-Shot Day-Night Domain Adaptation

VkD: Improving Knowledge Distillation using Orthogonal Projections

SAGS: Structure-Aware 3D Gaussian Splatting

HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos

Three Heads Are Better than One: Complementary Experts for Long-Tailed Semi-supervised Learning

3DGazeNet: Generalizing Gaze Estimation with Weak Supervision from Synthetic Views

Self-Adaptive Reality-Guided Diffusion for Artifact-Free Super-Resolution

Unsupervised Audio-Visual Segmentation with Modality Alignment

Monocular Identity-Conditioned Facial Reflectance Reconstruction

G3DR: Generative 3D Reconstruction in ImageNet

``Principal Components" Enable A New Language of Images

From Attention to Activation: Unraveling the Enigmas of Large Language Models

Fractal Calibration for Long-tailed Object Detection

Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator

Single-view Image to Novel-view Generation for Hand-Object Interactions

ForCenNet: Foreground-Centric Network for Document Image Rectification

Unlocking the Potential of Diffusion Priors in Blind Face Restoration

VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning

ImHead: A Large-scale Implicit Morphable Model for Localized Head Modeling

CaricatureBooth: Data-Free Interactive Caricature Generation in a Photo Booth

S^3-Face: SSS-Compliant Facial Reflectance Estimation via Diffusion Priors

WaveFace: Authentic Face Restoration with Efficient Frequency Recovery

Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images

Frequency-Guided Diffusion for Training-Free Text-Driven Image Translation

Region-based Cluster Discrimination for Visual Representation Learning

CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination

DiffSED: Sound Event Detection with Denoising Diffusion

HUST: High-Fidelity Unbiased Skin Tone Estimation via Texture Quantization