Zhangyang Wang

Orcid: 0000-0002-2050-5693

Affiliations:
  • University of Texas at Austin, Cockrell School of Engineering, TX, USA
  • Texas A&M University, College Station, TX, USA (former)
  • University of Illinois Urbana-Champaign, Urbana, IL, USA (PhD 2016)


According to our database1, Zhangyang Wang authored at least 460 papers between 2012 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Neuro-Symbolic Computing: Advancements and Challenges in Hardware-Software Co-Design.
IEEE Trans. Circuits Syst. II Express Briefs, March, 2024

Understanding and Accelerating Neural Architecture Search With Training-Free and Theory-Grounded Metrics.
IEEE Trans. Pattern Anal. Mach. Intell., February, 2024

InstantSplat: Unbounded Sparse-view Pose-free Gaussian Splatting in 40 Seconds.
CoRR, 2024

Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D.
CoRR, 2024

Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study.
CoRR, 2024

Comp4D: LLM-Guided Compositional 4D Scene Generation.
CoRR, 2024

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression.
CoRR, 2024

StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text.
CoRR, 2024

Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk.
CoRR, 2024

Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding.
CoRR, 2024

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection.
CoRR, 2024

Principled Architecture-aware Scaling of Hyperparameters.
CoRR, 2024

Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization.
CoRR, 2024

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark.
CoRR, 2024

Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community.
CoRR, 2024

Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference.
CoRR, 2024

LLaGA: Large Language and Graph Assistant.
CoRR, 2024

AGG: Amortized Generative 3D Gaussians for Single Image to 3D.
CoRR, 2024

VASE: Object-Centric Appearance and Shape Manipulation of Real Videos.
CoRR, 2024

Taming Mode Collapse in Score Distillation for Text-to-3D Generation.
CoRR, 2024

SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity.
CoRR, 2024

FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

2023
Integrating the traffic science with representation learning for city-wide network congestion prediction.
Inf. Fusion, November, 2023

SmartDeal: Remodeling Deep Network Weights for Efficient Inference and Training.
IEEE Trans. Neural Networks Learn. Syst., October, 2023

Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays.
IEEE Trans. Medical Imaging, March, 2023

Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study.
IEEE Trans. Pattern Anal. Mach. Intell., March, 2023

Troubleshooting image segmentation models with human-in-the-loop.
Mach. Learn., March, 2023

How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts.
Trans. Mach. Learn. Res., 2023

Can Pruning Improve Certified Robustness of Neural Networks?
Trans. Mach. Learn. Res., 2023

Broad Spectrum Image Deblurring via an Adaptive Super-Network.
IEEE Trans. Image Process., 2023

A Multi-Purpose Realistic Haze Benchmark With Quantifiable Haze Levels and Ground Truth.
IEEE Trans. Image Process., 2023

Taxonomy of Machine Learning Safety: A Survey and Primer.
ACM Comput. Surv., 2023

4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency.
CoRR, 2023

HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models.
CoRR, 2023

The Counterattack of CNNs in Self-Supervised Learning: Larger Kernel Size might be All You Need.
CoRR, 2023

DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer.
CoRR, 2023

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields.
CoRR, 2023

Rethinking PGD Attack: Is Sign Function Necessary?
CoRR, 2023

Meta ControlNet: Enhancing Task Adaptation via Meta Learning.
CoRR, 2023

FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting.
CoRR, 2023

LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS.
CoRR, 2023

Fine-Tuning Language Models Using Formal Methods Feedback.
CoRR, 2023

Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge.
CoRR, 2023

Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else.
CoRR, 2023

Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality.
CoRR, 2023

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity.
CoRR, 2023

Drag View: Generalizable Novel View Synthesis with Unposed Imagery.
CoRR, 2023

Efficient-3DiM: Learning a Generalizable Single-image Novel-view Synthesizer in One Day.
CoRR, 2023

Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity.
CoRR, 2023

Compressing LLMs: The Truth is Rarely Pure and Never Simple.
CoRR, 2023

(Dynamic) Prompting might be all you need to repair Compressed LLMs.
CoRR, 2023

Safe and Robust Watermark Injection with a Single OoD Image.
CoRR, 2023

Doubly Robust Instance-Reweighted Adversarial Training.
CoRR, 2023

Reference-based Painterly Inpainting via Diffusion: Crossing the Wild Reference Domain Gap.
CoRR, 2023

Polynomial Width is Sufficient for Set Representation with High-dimensional Features.
CoRR, 2023

Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities.
CoRR, 2023

FarSight: A Physics-Driven Whole-Body Biometric System at Large Distance and Altitude.
CoRR, 2023

H<sub>2</sub>O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
CoRR, 2023

Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images.
CoRR, 2023

Dynamic Sparsity Is Channel-Level Sparsity Learner.
CoRR, 2023

Are Large Kernels Better Teachers than Transformers for ConvNets?
CoRR, 2023

Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models.
CoRR, 2023

POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference.
CoRR, 2023

Learning imaging mechanism directly from optical microscopy observations.
CoRR, 2023

Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling.
CoRR, 2023

Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models.
CoRR, 2023

PAIR-Diffusion: Object-Level Image Editing with Structure-and-Appearance Paired Diffusion Models.
CoRR, 2023

You Only Transfer What You Share: Intersection-Induced Graph Transfer Learning for Link Prediction.
CoRR, 2023

Ten Lessons We Have Learned in the New "Sparseland": A Short Handbook for Sparse Neural Network Researchers.
CoRR, 2023

Evaluate underdiagnosis and overdiagnosis bias of deep learning model on primary open-angle glaucoma diagnosis in under-served patient populations.
CoRR, 2023

Pruning Before Training May Improve Generalization, Provably.
CoRR, 2023

Convergence and Generalization of Wide Neural Networks with Large Bias.
CoRR, 2023

Search Behavior Prediction: A Hypergraph Perspective.
Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, 2023

Attend Who is Weak: Pruning-assisted Medical Image Localization under Sophisticated and Implicit Imbalances.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

QuantumSEA: In-Time Sparse Exploration for Noise Adaptive Quantum Circuits.
Proceedings of the IEEE International Conference on Quantum Computing and Engineering, 2023

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

In-Context Learning Unlocked for Diffusion Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Don't just prune by magnitude! Your mask topology is a secret weapon.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Dynamic Sparsity Is Channel-Level Sparsity Learner.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

How Does Pruning Impact Long-Tailed Multi-label Medical Image Classifiers?
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2023, 2023

Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation.
Proceedings of the International Conference on Machine Learning, 2023

Data Efficient Neural Scaling Law via Model Reusing.
Proceedings of the International Conference on Machine Learning, 2023

Lowering the Pre-training Tax for Gradient-based Subset Training: A Lightweight Distributed Pre-Training Toolkit.
Proceedings of the International Conference on Machine Learning, 2023

Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models.
Proceedings of the International Conference on Machine Learning, 2023

Graph Ladling: Shockingly Simple Parallel GNN Training without Intermediate Communication.
Proceedings of the International Conference on Machine Learning, 2023

Are Large Kernels Better Teachers than Transformers for ConvNets?
Proceedings of the International Conference on Machine Learning, 2023

Learning to Optimize Differentiable Games.
Proceedings of the International Conference on Machine Learning, 2023

Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
Proceedings of the International Conference on Machine Learning, 2023

Towards Constituting Mathematical Structures for Learning to Optimize.
Proceedings of the International Conference on Machine Learning, 2023

Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Graph Domain Adaptation via Theory-Grounded Spectral Regularization.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Equivariant Hypergraph Diffusion Neural Operators.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Learning to Grow Pretrained Models for Efficient Transformer Training.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Is Attention All That NeRF Needs?
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
Proceedings of the Eleventh International Conference on Learning Representations, 2023

More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Revisiting Pruning at Initialization Through the Lens of Ramanujan Graph.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Continuous-Discrete Convolution for Geometry-Sequence Modeling in Proteins.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

HotProtein: A Novel Framework for Protein Thermostability Prediction and Editing.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Robust Mixture-of-Expert Training for Convolutional Neural Networks.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Versatile Diffusion: Text, Images and Variations All in One Diffusion Model.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

StegaNeRF: Embedding Invisible Information within Neural Radiance Fields.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Physics-Driven Turbulence Image Restoration with Stochastic Refinement.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Vision HGNN: An Image is More than a Graph of Nodes.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-Level Sparsity via Mixture-of-Experts.
Proceedings of the IEEE/ACM International Conference on Computer Aided Design, 2023

INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing.
Proceedings of the IEEE/ACM International Conference on Computer Aided Design, 2023

AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

NeuralLift-360: Lifting an in-the-Wild 2D Photo to A 3D Object with 360° Views.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models to Learn Any Unseen Style.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Accelerable Lottery Tickets with the Mixed-Precision Quantization.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Many-Task Federated Learning: A New Problem Setting and A Simple Baseline.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

"No Free Lunch" in Neural Architectures? A Joint Analysis of Expressivity, Convergence, and Generalization.
Proceedings of the International Conference on Automated Machine Learning, 2023

Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices.
Proceedings of the 28th Asia and South Pacific Design Automation Conference, 2023

On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

Learning to Generalize Provably in Learning to Optimize.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

Safeguarded Learned Convex Optimization.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
Scalable Perception-Action-Communication Loops With Convolutional and Graph Neural Networks.
IEEE Trans. Signal Inf. Process. over Networks, 2022

DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference.
ACM Trans. Design Autom. Electr. Syst., 2022

Can You Win Everything with A Lottery Ticket?
Trans. Mach. Learn. Res., 2022

Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning.
Trans. Mach. Learn. Res., 2022

Adversarial Feature Augmentation and Normalization for Visual Recognition.
Trans. Mach. Learn. Res., 2022

CERL: A Unified Optimization Framework for Light Enhancement With Realistic Noise.
IEEE Trans. Image Process., 2022

Guest Editorial Special Section on Learning With Multimodal Data for Biomedical Informatics.
IEEE Trans. Circuits Syst. Video Technol., 2022

Conference on graphics, patterns and images.
Pattern Recognit. Lett., 2022

Shape-Matching GAN++: Scale Controllable Dynamic Artistic Text Style Transfer.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

Privacy-Preserving Deep Action Recognition: An Adversarial Learning Framework and A New Dataset.
IEEE Trans. Pattern Anal. Mach. Intell., 2022

Learning to Optimize: A Primer and A Benchmark.
J. Mach. Learn. Res., 2022

Symbolic Visual Reinforcement Learning: A Scalable Framework with Object-Level Abstraction and Differentiable Expression Search.
CoRR, 2022

Versatile Diffusion: Text, Images and Variations All in One Diffusion Model.
CoRR, 2022

QuanGCN: Noise-Adaptive Training for Robust Quantum Graph Convolutional Networks.
CoRR, 2022

StyleNAT: Giving Each Head a New Perspective.
CoRR, 2022

M<sup>3</sup>ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design.
CoRR, 2022

Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?
CoRR, 2022

Is Attention All NeRF Needs?
CoRR, 2022

Self-Supervised Learning of Echocardiogram Videos Enables Data-Efficient Clinical Diagnosis.
CoRR, 2022

Neural Implicit Dictionary via Mixture-of-Expert Training.
CoRR, 2022

More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity.
CoRR, 2022

A Multi-purpose Real Haze Benchmark with Quantifiable Haze Levels and Ground Truth.
CoRR, 2022

E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles.
CoRR, 2022

Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN.
CoRR, 2022

E^2TAD: An Energy-Efficient Tracking-based Action Detector.
CoRR, 2022

APP: Anytime Progressive Pruning.
CoRR, 2022

On the Neural Tangent Kernel Analysis of Randomly Pruned Wide Neural Networks.
CoRR, 2022

VAQF: Fully Automatic Software-hardware Co-design Framework for Low-bit Vision Transformer.
CoRR, 2022

Fast and High-Quality Image Denoising via Malleable Convolutions.
CoRR, 2022

Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations.
Proceedings of the WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining, Virtual Event / Tempe, AZ, USA, February 21, 2022

Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022

Knowledge-Augmented Contrastive Learning for Abnormality Classification and Localization in Chest X-rays with Radiomics using a Feedback Loop.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022

Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022

Signal Processing for Implicit Neural Representations.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Sparse Winning Tickets are Data-Efficient Image Recognizers.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Symbolic Distillation for Learned TCP Congestion Control.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropagation.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

ReCoRo: Region-Controllable Robust Light Enhancement with User-Specified Imprecise Masks.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

TxVAD: Improved Video Action Detection by Transformers.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Cloud2Sketch: Augmenting Clouds with Imaginary Sketches.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Density-Aware Personalized Training for Risk Prediction in Imbalanced Medical Data.
Proceedings of the Machine Learning for Healthcare Conference, 2022

Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study.
Proceedings of the Data Augmentation, Labelling, and Imperfections, 2022

You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets.
Proceedings of the Learning on Graphs Conference, 2022

Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition.
Proceedings of the International Conference on Machine Learning, 2022

Removing Batch Normalization Boosts Adversarial Training.
Proceedings of the International Conference on Machine Learning, 2022

Neural Implicit Dictionary Learning via Mixture-of-Expert Training.
Proceedings of the International Conference on Machine Learning, 2022

Universality of Winning Tickets: A Renormalization Group Perspective.
Proceedings of the International Conference on Machine Learning, 2022

Training Your Sparse Neural Network Better with Any Mask.
Proceedings of the International Conference on Machine Learning, 2022

Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness.
Proceedings of the International Conference on Machine Learning, 2022

Data-Efficient Double-Win Lottery Tickets from Robust Pre-training.
Proceedings of the International Conference on Machine Learning, 2022

Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets.
Proceedings of the International Conference on Machine Learning, 2022

VariGrow: Variational Architecture Growing for Task-Agnostic Continual Learning based on Bayesian Novelty.
Proceedings of the International Conference on Machine Learning, 2022

Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Symbolic Learning to Optimize: Towards Interpretability and Scalability.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Unified Visual Transformer Compression.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining.
Proceedings of the Tenth International Conference on Learning Representations, 2022

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Optimizer Amalgamation.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Sparsity Winning Twice: Better Robust Generalization from More Efficient Training.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Auto-scaling Vision Transformers without Training.
Proceedings of the Tenth International Conference on Learning Representations, 2022

RoS-KD: A Robust Stochastic Knowledge Distillation Approach for Noisy Medical Imaging.
Proceedings of the IEEE International Conference on Data Mining, 2022

Towards Lifelong Learning of Multilingual Text-to-Speech Synthesis.
Proceedings of the IEEE International Conference on Acoustics, 2022

Dynimp: Dynamic Imputation for Wearable Sensing Data through Sensory and Temporal Relatedness.
Proceedings of the IEEE International Conference on Acoustics, 2022

Auto-ViT-Acc: An FPGA-Aware Automatic Acceleration Framework for Vision Transformer with Mixed-Scheme Quantization.
Proceedings of the 32nd International Conference on Field-Programmable Logic and Applications, 2022

Model elasticity for hardware heterogeneity in federated learning systems.
Proceedings of the 1st ACM Workshop on Data Privacy and Federated Learning Technologies for Mobile Edge Network, 2022

Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent.
Proceedings of the FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21, 2022

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image.
Proceedings of the Computer Vision - ECCV 2022, 2022

Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and a New Physics-Inspired Transformer Model.
Proceedings of the Computer Vision - ECCV 2022, 2022

Point Cloud Domain Adaptation via Masked Local 3D Structure Prediction.
Proceedings of the Computer Vision - ECCV 2022, 2022

Fast and High Quality Image Denoising via Malleable Convolution.
Proceedings of the Computer Vision - ECCV 2022, 2022

DnA: Improving Few-Shot Transfer Learning with Low-Rank Decomposition and Alignment.
Proceedings of the Computer Vision - ECCV 2022, 2022

Unified Implicit Neural Stylization.
Proceedings of the Computer Vision - ECCV 2022, 2022

A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation.
Proceedings of the Computer Vision - ECCV 2022, 2022

Scalable Learning to Optimize: A Learned Optimizer Can Train Big Models.
Proceedings of the Computer Vision - ECCV 2022, 2022

FPGA-aware automatic acceleration framework for vision transformer with mixed-scheme quantization: late breaking results.
Proceedings of the DAC '22: 59th ACM/IEEE Design Automation Conference, San Francisco, California, USA, July 10, 2022

DiSparse: Disentangled Sparsification for Multitask Model Compression.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Locating Urban Trees near Electric Wires using Google Street View Photos: A New Dataset and A Semi-Supervised Learning Approach in the Wild.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022

EI-CLIP: Entity-aware Interventional Contrastive Learning for E-commerce Cross-modal Retrieval.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

CADTransformer: Panoptic Symbol Spotting Transformer for CAD Drawings.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

AutoMARS: Searching to Compress Multi-Modality Recommendation Systems.
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022

Supervised pretraining through contrastive categorical positive samplings to improve COVID-19 mortality prediction.
Proceedings of the BCB '22: 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, Northbrook, Illinois, USA, August 7, 2022

AutoCoG: A Unified Data-Model Co-Search Framework for Graph Neural Networks.
Proceedings of the International Conference on Automated Machine Learning, 2022

VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study.
ACM Trans. Multim. Comput. Commun. Appl., 2021

AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles.
IEEE Trans. Mob. Comput., 2021

Controllable Sketch-to-Image Translation for Robust Face Synthesis.
IEEE Trans. Image Process., 2021

EnlightenGAN: Deep Light Enhancement Without Paired Supervision.
IEEE Trans. Image Process., 2021

Fast Sequential Feature Extraction for Recurrent Neural Network-Based Hyperspectral Image Classification.
IEEE Trans. Geosci. Remote. Sens., 2021

Deep Adversarial Data Augmentation for Extremely Low Data Regimes.
IEEE Trans. Circuits Syst. Video Technol., 2021

Contrastive learning improves critical event prediction in COVID-19 patients.
Patterns, 2021

Bridging the Gap Between Computational Photography and Visual Recognition.
IEEE Trans. Pattern Anal. Mach. Intell., 2021

Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts.
J. Chem. Inf. Model., 2021

Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition.
Int. J. Comput. Vis., 2021

A Comprehensive Benchmark Analysis of Single Image Deraining: Current Challenges and Future Perspectives.
Int. J. Comput. Vis., 2021

Report on UG2+ challenge Track 1: Assessing algorithms to improve video object detection and classification from unconstrained mobility platforms.
Comput. Vis. Image Underst., 2021

A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation.
CoRR, 2021

Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling.
CoRR, 2021

Universality of Deep Neural Network Lottery Tickets: A Renormalization Group Perspective.
CoRR, 2021

Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs.
CoRR, 2021

Font Completion and Manipulation by Cycling Between Multi-Modality Representations.
CoRR, 2021

Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics.
CoRR, 2021

FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity.
CoRR, 2021

IA-RED<sup>2</sup>: Interpretability-Aware Redundancy Reduction for Vision Transformers.
CoRR, 2021

Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning.
CoRR, 2021

Practical Machine Learning Safety: A Survey and Primer.
CoRR, 2021

Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors.
CoRR, 2021

Cross-Modal Contrastive Learning for Abnormality Classification and Localization in Chest X-rays with Radiomics using a Feedback Loop.
CoRR, 2021

Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data.
CoRR, 2021

UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution.
CoRR, 2021

Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly.
CoRR, 2021

Sandwich Batch Normalization.
CoRR, 2021

Weak NAS Predictors Are All You Need.
CoRR, 2021

TransGAN: Two Transformers Can Make One Strong GAN.
CoRR, 2021

On Dynamic Noise Influence in Differentially Private Learning.
CoRR, 2021

Good Students Play Big Lottery Better.
CoRR, 2021

SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training.
CoRR, 2021

Foreword to the special section on SIBGRAPI-Conference on Graphics, Patterns and Images is an international conference 2020.
Comput. Graph., 2021

Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Stronger NAS with Weaker Predictors.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

AugMax: Adversarial Composition of Random Augmentations for Robust Training.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Improving Contrastive Learning on Imbalanced Data via Open-World Sampling.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Hyperparameter Tuning is All You Need for LISTA.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

The Elastic Lottery Ticket Hypothesis.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Chasing Sparsity in Vision Transformers: An End-to-End Exploration.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Federated Adversarial Debiasing for Fair and Transferable Representations.
Proceedings of the KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021

Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm.
Proceedings of the 38th International Conference on Machine Learning, 2021

Efficient Lottery Ticket Finding: Less Data is More.
Proceedings of the 38th International Conference on Machine Learning, 2021

Graph Contrastive Learning Automated.
Proceedings of the 38th International Conference on Machine Learning, 2021

Self-Damaging Contrastive Learning.
Proceedings of the 38th International Conference on Machine Learning, 2021

A Unified Lottery Ticket Hypothesis for Graph Neural Networks.
Proceedings of the 38th International Conference on Machine Learning, 2021

SAFIN: Arbitrary Style Transfer with Self-Attentive Factorized Instance Normalization.
Proceedings of the 2021 IEEE International Conference on Multimedia and Expo, 2021

UMEC: Unified model and embedding compression for efficient recommendation systems.
Proceedings of the 9th International Conference on Learning Representations, 2021

Learning A Minimax Optimizer: A Pilot Study.
Proceedings of the 9th International Conference on Learning Representations, 2021

A Design Space Study for LISTA and Beyond.
Proceedings of the 9th International Conference on Learning Representations, 2021

Undistillable: Making A Nasty Teacher That CANNOT teach students.
Proceedings of the 9th International Conference on Learning Representations, 2021

Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning.
Proceedings of the 9th International Conference on Learning Representations, 2021

Robust Overfitting may be mitigated by properly learned smoothening.
Proceedings of the 9th International Conference on Learning Representations, 2021

Contrastive Syn-to-Real Generalization.
Proceedings of the 9th International Conference on Learning Representations, 2021

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective.
Proceedings of the 9th International Conference on Learning Representations, 2021

SSH: A Self-Supervised Framework for Image Harmonization.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Searching for Two-Stream Models in Multivariate Space for Video Recognition.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

VGAI: End-to-End Learning of Vision-Based Decentralized Controllers for Robot Swarms.
Proceedings of the IEEE International Conference on Acoustics, 2021

An Al-based Spatial Knowledge Graph for Enhancing Spatial Data and Knowledge Search and Discovery.
Proceedings of the GeoSearch'21: Proceedings of the 1st ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data, 2021

InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks.
Proceedings of the 58th ACM/IEEE Design Automation Conference, 2021

Troubleshooting Blind Image Quality Models in the Wild.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

E2VTS: Energy-Efficient Video Text Spotting From Unmanned Aerial Vehicles.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021

"BNN - BN = ?": Training Binary Neural Networks Without Batch Normalization.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021

The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Debiased Subjective Assessment of Real-World Image Enhancement.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Dissecting the High-Frequency Bias in Convolutional Neural Networks.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2021

DynEHR: Dynamic adaptation of models with data heterogeneity in electronic health records.
Proceedings of the IEEE EMBS International Conference on Biomedical and Health Informatics, 2021

Sparse Gated Mixture-of-Experts to Separate and Interpret Patient Heterogeneity in EHR data.
Proceedings of the IEEE EMBS International Conference on Biomedical and Health Informatics, 2021


EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets.
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021

Learning Model-Based Privacy Protection under Budget Constraints.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study.
IEEE Trans. Image Process., 2020

Connecting Image Denoising and High-Level Vision Tasks via Deep Learning.
IEEE Trans. Image Process., 2020

Learning Simple Thresholded Features With Sparse Support Recovery.
IEEE Trans. Circuits Syst. Video Technol., 2020

Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding.
IEEE Trans. Circuits Syst. Video Technol., 2020

Dual Dynamic Inference: Enabling More Efficient, Adaptive, and Controllable Deep Inference.
IEEE J. Sel. Top. Signal Process., 2020

Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing.
CoRR, 2020

PCAL: A Privacy-preserving Intelligent Credit Risk Modeling Framework Based on Adversarial Learning.
CoRR, 2020

MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis.
CoRR, 2020

AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation.
CoRR, 2020

Can 3D Adversarial Logos Cloak Humans?
CoRR, 2020

L^2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks.
CoRR, 2020

VGAI: A Vision-Based Decentralized Controller Learning Framework for Robot Swarms.
CoRR, 2020

An adversarial learning framework for preserving users' anonymity in face-based emotion recognition.
CoRR, 2020

Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2020

DAVID: Dual-Attentional Video Deblurring.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2020

ShiftAddNet: A Hardware-Inspired Deep Network.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Graph Contrastive Learning with Augmentations.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Robust Pre-Training by Adversarial Contrastive Learning.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Training Stronger Baselines for Learning to Optimize.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

MATE: Plugging in Model Awareness to Task Embedding for Meta Learning.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

The Lottery Ticket Hypothesis for Pre-trained BERT Networks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

MM-Hand: 3D-Aware Multi-Modal Guided Hand Generation for 3D Hand Pose Synthesis.
Proceedings of the MM '20: The 28th ACM International Conference on Multimedia, 2020

SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation.
Proceedings of the 47th ACM/IEEE Annual International Symposium on Computer Architecture, 2020

AutoSpeech: Neural Architecture Search for Speaker Recognition.
Proceedings of the Interspeech 2020, 2020

GPSRL: Learning Semi-Parametric Bayesian Survival Rule Lists from Heterogeneous Patient Data.
Proceedings of the 25th International Conference on Pattern Recognition, 2020

When Does Self-Supervision Help Graph Convolutional Networks?
Proceedings of the 37th International Conference on Machine Learning, 2020

Eliminating the Invariance on the Loss Landscape of Linear Autoencoders.
Proceedings of the 37th International Conference on Machine Learning, 2020

AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks.
Proceedings of the 37th International Conference on Machine Learning, 2020

Automated Synthetic-to-Real Generalization.
Proceedings of the 37th International Conference on Machine Learning, 2020

Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training.
Proceedings of the 37th International Conference on Machine Learning, 2020

NADS: Neural Architecture Distribution Search for Uncertainty Awareness.
Proceedings of the 37th International Conference on Machine Learning, 2020

Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks.
Proceedings of the 8th International Conference on Learning Representations, 2020

I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively.
Proceedings of the 8th International Conference on Learning Representations, 2020

Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference.
Proceedings of the 8th International Conference on Learning Representations, 2020

FasterSeg: Searching for Faster Real-time Semantic Segmentation.
Proceedings of the 8th International Conference on Learning Representations, 2020

Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches.
Proceedings of the Computer Vision - ECCV 2020, 2020

GAN Slimming: All-in-One GAN Compression by a Unified Optimization Framework.
Proceedings of the Computer Vision - ECCV 2020, 2020

HALO: Hardware-Aware Learning to Optimize.
Proceedings of the Computer Vision - ECCV 2020, 2020

What Does CNN Shift Invariance Look Like? A Visualization Study.
Proceedings of the Computer Vision - ECCV 2020 Workshops, 2020

In Defense of the Triplet Loss Again: Learning Robust Person Re-Identification with Fast Approximated Triplet Loss and Label Distillation.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Focus Longer to See Better: Recursively Refined Attention for Fine-Grained Image Classification.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane Representations.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Fractional Skipping: Towards Finer-Grained Dynamic CNN Inference.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

Self-Supervised Learning for Generalizable Out-of-Distribution Detection.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

Practical Solutions for Machine Learning Safety in Autonomous Vehicles.
Proceedings of the Workshop on Artificial Intelligence Safety, 2020

2019
Convolutional Sparse Coding for Compressed Sensing CT Reconstruction.
IEEE Trans. Medical Imaging, 2019

Enhance Visual Recognition Under Adverse Conditions via Deep Networks.
IEEE Trans. Image Process., 2019

Benchmarking Single-Image Dehazing and Beyond.
IEEE Trans. Image Process., 2019

Hyperspectral Image Classification Using Similarity Measurements-Based Deep Recurrent Neural Networks.
Remote. Sens., 2019

E2-Train: Energy-Efficient Deep Network Training with Data-, Model-, and Algorithm-Level Saving.
CoRR, 2019

Drawing early-bird tickets: Towards more efficient training of deep networks.
CoRR, 2019

Report on UG^2+ Challenge Track 1: Assessing Algorithms to Improve Video Object Detection and Classification from Unconstrained Mobility Platforms.
CoRR, 2019

Privacy-Preserving Deep Visual Recognition: An Adversarial Learning Framework and A New Dataset.
CoRR, 2019

ArcticNet: A Deep Learning Solution to Classify Arctic Wetlands.
CoRR, 2019

Segmentation-Aware Image Denoising without Knowing True Segmentation.
CoRR, 2019

Predicting Model Failure using Saliency Maps in Autonomous Driving Systems.
CoRR, 2019

UG<sup>2</sup> Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments.
CoRR, 2019

Adversarially Trained Model Compression: When Robustness Meets Efficiency.
CoRR, 2019

DeepAffinity: interpretable deep learning of compound-protein affinity through unified recurrent and convolutional neural networks.
Bioinform., 2019

E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Model Compression with Adversarial Robustness: A Unified Optimization Framework.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Learning to Optimize in Swarms.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Novel Framework for 3D-2D Vertebra Matching.
Proceedings of the 2nd IEEE Conference on Multimedia Information Processing and Retrieval, 2019

Self-Reproducing Video Frame Interpolation.
Proceedings of the 2nd IEEE Conference on Multimedia Information Processing and Retrieval, 2019

Cone-Beam Computed Tomography (CBCT) Segmentation by Adversarial Learning Domain Adaptation.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2019, 2019

Plug-and-Play Methods Provably Converge with Properly Trained Denoisers.
Proceedings of the 36th International Conference on Machine Learning, 2019

ALISTA: Analytic Weights Are As Good As Learned Weights in LISTA.
Proceedings of the 7th International Conference on Learning Representations, 2019

Cross-Modal Person Search: A Coarse-to-Fine Framework using Bi-Directional Text-Image Matching.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops, 2019

Controllable Artistic Text Style Transfer via Shape-Matching GAN.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Delving Into Robust Object Detection From Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

AutoGAN: Neural Architecture Search for Generative Adversarial Networks.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

ABD-Net: Attentive but Diverse Person Re-Identification.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification.
Proceedings of the IEEE International Conference on Acoustics, 2019

All-in-One Underwater Image Enhancement Using Domain-Adversarial Learning.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019

Single Image Deraining: A Comprehensive Benchmark Analysis.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

ArcticNet: A Deep Learning Solution to Classify the Arctic Area.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019

Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018
Learning Temporal Dynamics for Video Super-Resolution: A Deep Learning Approach.
IEEE Trans. Image Process., 2018

Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?
CoRR, 2018

U-Finger: Multi-Scale Dilated Convolutional Network for Fingerprint Image Denoising and Inpainting.
CoRR, 2018

Improved Techniques for Learning to Dehaze and Beyond: A Collective Study.
CoRR, 2018

DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks.
CoRR, 2018

L<sub>p</sub>-Norm Constrained Coding With Frank-Wolfe Network.
CoRR, 2018

Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Can We Gain More from Orthogonality Regularizations in Training Deep Networks?
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

MusicMapp: A Deep Learning Based Solution for Music Exploration and Visual Interaction.
Proceedings of the 2018 ACM Multimedia Conference on Multimedia Conference, 2018

Subspace Network: Deep Multi-Task Censored Regression for Modeling Neurodegenerative Diseases.
Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018

When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach.
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018

Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions.
Proceedings of the 35th International Conference on Machine Learning, 2018

Growing Deep Forests Efficiently with Soft Routing and Learned Connectivity.
Proceedings of the 2018 IEEE International Conference on Data Mining Workshops, 2018

VisDrone-DET2018: The Vision Meets Drone Object Detection in Image Challenge Results.
Proceedings of the Computer Vision - ECCV 2018 Workshops, 2018

Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study.
Proceedings of the Computer Vision - ECCV 2018, 2018

Predicting Depression Severity by Multi-Modal Feature Engineering and Fusion.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

End-to-End United Video Dehazing and Detection.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

Visual Recognition in Very Low-Quality Settings: Delving Into the Power of Pre-Training.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017
Greedy Batch-Based Minimum-Cost Flows for Tracking Multiple Objects.
IEEE Trans. Image Process., 2017

Biomedical informatics with optimization and machine learning.
EURASIP J. Bioinform. Syst. Biol., 2017

RESIDE: A Benchmark for Single Image Dehazing.
CoRR, 2017

An All-in-One Network for Dehazing and Beyond.
CoRR, 2017

Image aesthetics assessment using Deep Chatterjee's machine.
Proceedings of the 2017 International Joint Conference on Neural Networks, 2017

Doubly Sparsifying Network.
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

Computed tomography super-resolution using convolutional neural networks.
Proceedings of the 2017 IEEE International Conference on Image Processing, 2017

Robust Video Super-Resolution with Learned Temporal Dynamics.
Proceedings of the IEEE International Conference on Computer Vision, 2017

AOD-Net: All-in-One Dehazing Network.
Proceedings of the IEEE International Conference on Computer Vision, 2017


Balanced Two-Stage Residual Networks for Image Super-Resolution.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017

Transformed Anti-Sparse Hashing.
Proceedings of the British Machine Vision Conference 2017, 2017

Robust emotion recognition from low quality and low bit rate video: A deep learning approach.
Proceedings of the Seventh International Conference on Affective Computing and Intelligent Interaction, 2017

2016
Task-specific and interpretable feature learning
PhD thesis, 2016

Deep Double Sparsity Encoder: Learning to Sparsify Not Only Features But Also Parameters.
CoRR, 2016

$\mathbf{D^3}$: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images.
CoRR, 2016

Brain-Inspired Deep Networks for Image Aesthetics Assessment.
CoRR, 2016

Learning A Task-Specific Deep Architecture For Clustering.
Proceedings of the 2016 SIAM International Conference on Data Mining, 2016

UnitBox: An Advanced Object Detection Network.
Proceedings of the 2016 ACM Conference on Multimedia Conference, 2016

Learning A Deep ℓ<sub>∞</sub> Encoder for Hashing.
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016

D3: Deep Dual-Domain Based Fast Restoration of JPEG-Compressed Images.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Studying Very Low Resolution Recognition Using Deep Networks.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Epitomic Image Super-Resolution.
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016

Learning Deep ℓ<sub>0</sub> Encoders.
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016

2015
Learning Super-Resolution Jointly From External and Internal Examples.
IEEE Trans. Image Process., 2015

Semisupervised Hyperspectral Classification Using Task-Driven Dictionary Learning With Laplacian Regularization.
IEEE Trans. Geosci. Remote. Sens., 2015

Real-World Font Recognition Using Deep Network and Domain Adaptation.
Proceedings of the 3rd International Conference on Learning Representations, 2015

Decentralized Recommender Systems.
CoRR, 2015

Learning A Task-Specific Deep Architecture For Clustering.
CoRR, 2015

Designing a composite dictionary adaptively from joint examples.
Proceedings of the 2015 Visual Communications and Image Processing, 2015

DeepFont: Identify Your Font from An Image.
Proceedings of the 23rd Annual ACM Conference on Multimedia Conference, MM '15, Brisbane, Australia, October 26, 2015

DeepFont: A System for Font Recognition and Similarity.
Proceedings of the 23rd Annual ACM Conference on Multimedia Conference, MM '15, Brisbane, Australia, October 26, 2015

A Joint Optimization Framework of Sparse Coding and Discriminative Clustering.
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, 2015

Self-tuned deep super resolution.
Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2015

Sparse Coding and its Applications in Computer Vision
WorldScientific, ISBN: 9789814725064, 2015

2014
A joint perspective towards image super-resolution: Unifying external- and self-examples.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2014

On a Theory of Nonparametric Pairwise Similarity for Clustering: Connecting Clustering to Classification.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Active Planning, Sensing, and Recognition Using a Resource-Constrained Discriminant POMDP.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014

Regularized l1-Graph for Data Clustering.
Proceedings of the British Machine Vision Conference, 2014

Data Clustering by Laplacian Regularized L1-Graph.
Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, 2014

2013
Multi-Level Video Frame Interpolation: Exploiting the Interaction Among Different Levels.
IEEE Trans. Circuits Syst. Video Technol., 2013

Robust Temporal-Spatial Decomposition and Its Applications in Video Processing.
IEEE Trans. Circuits Syst. Video Technol., 2013

Detection of Blotch and Scratch in Video Based on Video Decomposition.
IEEE Trans. Circuits Syst. Video Technol., 2013

2012
Mixed Gaussian-impulse video noise removal via temporal-spatial decomposition.
Proceedings of the 2012 IEEE International Symposium on Circuits and Systems, 2012

Video error concealment via total variation regularized matrix completion.
Proceedings of the 19th IEEE International Conference on Image Processing, 2012

Video frame interpolation using 3-D total variation regularized completion.
Proceedings of the 19th IEEE International Conference on Image Processing, 2012


  Loading...