Xiaoming Liu

84

Papers

55

Total Citations

Papers (84)

Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector

SapiensID: Foundation for Human Recognition

HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID

Dialogue for Prompting: A Policy-Gradient-Based Discrete Prompt Generation for Few-Shot Learning

H-MoRe: Learning Human-centric Motion Representation for Action Analysis

Generalizable Object Re-Identification via Visual In-Context Prompting

TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimming

Remove Projective LiDAR Depthmap Artifacts via Exploiting Epipolar Geometry

SeaBird: Segmentation in Bird’s View with Dice Loss Improves Monocular 3D Detection of Large Objects

BigGait: Learning Gait Representation You Want by Large Vision Models

Unconstrained 3D Face Reconstruction

Face Alignment Across Large Poses: A 3D Solution

Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting

Adaptive 3D Face Reconstruction From Unconstrained Photo Collections

Missing Modalities Imputation via Cascaded Residual Autoencoder

Disentangled Representation Learning GAN for Pose-Invariant Face Recognition

Image Super-Resolution via Deep Recursive Residual Network

Spatio-Temporal Alignment of Non-Overlapping Sequences From Independently Panning Cameras

Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision

FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors

Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition

Nonlinear 3D Face Morphable Model

Towards High-Fidelity Nonlinear 3D Face Morphable Model

Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild

Deep Tree Learning for Zero-Shot Face Anti-Spoofing

Gait Recognition via Disentangled Representation Learning

Feature Transfer Learning for Face Recognition With Under-Represented Data

Pedestrian Detection With Autoregressive Network Phases

Depth Coefficients for Depth Completion

Camera Trace Erasing

Deep Facial Non-Rigid Multi-View Stereo

CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition

On the Detection of Digital Face Manipulation

LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood

Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing

The Edge of Depth: Explicit Constraints Between Segmentation and Depth

Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction

Towards High Fidelity Face Relighting With Realistic Shadows

Mitigating Face Recognition Bias via Group Adaptive Classifier

GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection

Depth Completion With Twin Surface Extrapolation at Occlusion Boundaries

Riggable 3D Face Reconstruction via In-Network Optimization

Radar-Camera Pixel Depth Association for Depth Completion

AdaFace: Quality Adaptive Margin for Face Recognition

Proactive Image Manipulation Detection

Face Relighting With Geometrically Consistent Shadows

Rethinking Domain Generalization for Face Anti-Spoofing: Separability and Alignment

MaLP: Manipulation Localization Using a Proactive Scheme

LightedDepth: Video Depth Estimation in Light of Limited Inference View Angles

PMatch: Paired Masked Image Modeling for Dense Geometric Matching

DCFace: Synthetic Face Generation With Dual Condition Diffusion Model

Hierarchical Fine-Grained Image Forgery Detection and Localization

Pose-Invariant 3D Face Alignment

Pose-Invariant Face Alignment With a Single CNN

Towards Large-Pose Face Frontalization in the Wild

MemNet: A Persistent Memory Network for Image Restoration

Monocular Video-Based Trailer Coupler Detection Using Multiplexer Convolutional Neural Network

M3D-RPN: Monocular 3D Region Proposal Network for Object Detection

Towards Interpretable Face Recognition

3D Face Modeling From Diverse Raw Scan Data

Full-Velocity Radar Returns by Radar-Camera Fusion

Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification

On Disentangling Spoof Trace for Generic Face Anti-Spoofing

Kinematic 3D Object Detection in Monocular Video

Jointly De-biasing Face Recognition and Demographic Attribute Estimation

Improving Face Recognition from Hard Samples via Distribution Distillation Loss

2D GANs Meet Unsupervised Single-View 3D Reconstruction

DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

Controllable and Guided Face Synthesis for Unconstrained Face Recognition

Multi-Domain Learning for Updating Face Anti-Spoofing Models

Illuminating Pedestrians via Simultaneous Detection & Segmentation

RICCARDO: Radar Hit Prediction and Convolution for Camera-Radar 3D Object Detection

CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector

A Quality-Guided Mixture of Score-Fusion Experts Framework for Human Recognition

Distilling CLIP with Dual Guidance for Learning Discriminative Human Body Shape Representation

ProMark: Proactive Diffusion Watermarking for Causal Attribution

TIGER: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion Process

KeyPoint Relative Position Encoding for Face Recognition

Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence

Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image

Cluster and Aggregate: Face Recognition with Large Probe Set

Tame a Wild Camera: In-the-Wild Monocular Camera Calibration

ChatGPT-Powered Hierarchical Comparisons for Image Classification

PrObeD: Proactive Object Detection Wrapper