Jia-Bin Huang
Publications [show all by date] / [show selected] / [show all by topic]
Latest arXiv Manuscripts
|
Robust Consistent Video Depth Estimation |
|
Portrait Neural Radiance Fields from a Single Image |
|
Space-time Neural Irradiance Fields for Free-Viewpoint Video |
 |
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation |
|
Few-shot Adaptation of Generative Adversarial Networks |
|
Learning to See Through Obstructions with Layered Decomposition |
|
Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors |
2021
 |
DropLoss for Long-Tail Instance Segmentation |
2020
|
Flow-edge Guided Video Completion |
|
Semantic View Synthesis
|
|
DRG: Dual Relation Graph for Human-Object Interaction Detection |
|
NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
|
 |
FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning |
|
|
Shuffle and Attend: Video Domain Adaptation |
|
|
Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling |
|
Consistent Video Depth Estimation |
|
3D Photography using Context-aware Layered Depth Inpainting |
|
Learning to See Through Obstructions |
|
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline |
|
Instance-aware Image Colorization |
 |
Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation |
|
Unsupervised and Semi-Supervised Domain Adaptation for Action Recognition from Drones |
 |
Reducing Footskate in Human Motion Reconstruction with Ground Contact Constraints |
 |
Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation |
 |
DRIT++: Diverse Image-to-Image Translation via Disentangled Representations |
 |
Tracking Persons-of-Interest via Unsupervised Representation Adaptation |
2019
 |
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition |
 |
Guided Image-to-Image Translation with Bi-Directional Feature Transformation |
 |
CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency |
|
SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and Baselines |
 |
A Closer Look at Few-shot Classification |
 |
Connecting the Digital and Physical World: Improving the Robustness of Adversarial Attacks |
 |
Deep Paper Gestalt |
 |
Source Form: An Automated Crowdsourced Object Generator |
 |
Progressive Representation Adaptation for Weakly Supervised Object Localization |
 |
Joint Image Filtering with Deep Convolutional Networks |
2018
|
Multi-view Wire Art |
 |
Diverse Image-to-Image Translation via Disentangled Representations |
 |
DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency |
|
Learning Blind Video Temporal Consistency |
|
VideoMatch: Matching based Video Object Segmentation |
|
Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation |
 |
iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection |
 |
DeepMVS: Learning Multi-View Stereopsis |
 |
Deep Semantic Matching with Foreground Detection and Cycle-Consistency |
 |
Semi-Automated Home-based Therapy for the Upper Extremity of Stroke Survivors |
 |
Progressive Cyber-Human Intelligence for Social Good |
 |
Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks |
 |
Robust Visual Tracking via Hierarchical Convolutional Features |
 |
Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking |
 |
Ensemble of Convolutional Neural Networks for Pose Estimation |
2017
 |
Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks |
 |
MaskRNN: Instance Level Video Object Segmentation |
 |
Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight |
 |
Unsupervised Representation Learning by Sorting Sequences |
|
|
Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution |
|
|
HOMER: an interactive system for home based stroke rehabilitation |
2016
 |
Visual Analysis and Synthesis with Physically Grounded Constraints |
 |
Temporally Coherent Completion of Dynamic Video |
 |
Deep Joint Image Filter |
|
|
Tracking Persons-of-Interest via Adaptive Discriminative Features |
 |
Unsupervised Visual Representation Learning by Graph-based Consistent Constraints |
 |
Detecting Migrating Birds at Night |
 |
A Comparative Study for Single Image Blind Deblurring |
|
|
Weakly Supervised Object Localization with Progressive Domain Adaptation |
2015
|
|
Hierarchical Convolutional Features for Visual Tracking |
 |
Single Image Super-Resolution from Transformed Self-Exemplars |
2014
 |
Image Completion using Planar Structure Guidance |
 |
Towards Accurate and Robust Cross-Ratio based Gaze Trackers Through Learning From Simulation |
Before 2013
 |
Transformation Guided Image Completion |
 |
Saliency Detection via Divergence Analysis: A Unified Perspective ICPR 2012 Best Student Paper Award (Computer and Robotic Vision Track) |
 |
Exploiting Self-Similarities for Single Frame Super-Resolution |
 |
Single Image Deblurring with Adaptive Dictionary Learning |
 |
Fast Sparse Representation with Prototypes |
 |
Estimating Human Pose from Occluded Images |
 |
Moving Cast Shadow Detection Using Physics-based Features |
 |
A Physical Approach to Moving Cast Shadow Detection |
 |
Image Recolorization For The Colorblind |
 |
Learning Moving Cast Shadows for Foreground Detection |
 |
Enhancing Color Representation for the Color Vision Impaired |
 |
Information Preserving Color Transformation for Protanopia and Deuteranopia |