Ke Xu

42

Papers

101

Total Citations

Papers (42)

Learning Influence Functions from Incomplete Observations

NeurIPS 2016arXiv

Boosting Neural Cognitive Diagnosis with Student’s Affective State Modeling

Multi-View Dynamic Reflection Prior for Video Glass Surface Detection

PTMQ: Post-training Multi-Bit Quantization of Neural Networks

ZOOM: Learning Video Mirror Detection with Extremely-Weak Supervision

Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Prompts

TopNet: Transformer-Efficient Occupancy Prediction Network for Octree-Structured Point Cloud Geometry Compression

Recasting Regional Lighting for Shadow Removal

Effective Video Mirror Detection with Inconsistent Motion Cues

Color Shift Estimation-and-Correction for Image Enhancement

Unsupervised Salient Instance Detection

LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling

Image Correction via Deep Reciprocating HDR Transformation

Spatial Attentive Single-Image Deraining With a High Quality Real Rain Dataset

Learning to Restore Low-Light Images via Decomposition-and-Enhancement

Bi-Directional Object-Context Prioritization Learning for Saliency Ranking

ISDNet: Integrating Shallow and Deep Networks for Efficient Ultra-High Resolution Segmentation

Rethinking Efficient Lane Detection via Curve Modeling

Where Is My Mirror?

Location-Aware Single Image Reflection Removal

Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting

EQ-Net: Elastic Quantization Neural Networks

Lighting up NeRF via Unsupervised Decomposition and Enhancement

Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence

Adaptive Illumination Mapping for Shadow Detection in Raw Images

Language-Guided Salient Object Ranking

Referring Image Segmentation Using Text Supervision

Learning Image Harmonization in the Linear Color Space

OneFace: One Threshold for All

CoupleFace: Relation Matters for Face Recognition Distillation

Harmonizer: Learning to Perform White-Box Image and Video Harmonization

Local Color Distributions Prior for Image Enhancement

SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-Time Performance on Mobile Device

SEHDR: Single-Exposure HDR Novel View Synthesis via 3D Gaussian Bracketing

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction

Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues

Structural Entropy Guided Unsupervised Graph Out-Of-Distribution Detection

Adversarial Robust Safeguard for Evading Deep Facial Manipulation

Active Matting

BERT Loses Patience: Fast and Robust Inference with Early Exit

Geometry-aware Two-scale PIFu Representation for Human Reconstruction