Machine Learning and Artificial Intelligence

Associated Publications

Neural Inverse Rendering of an Indoor Scene from a Single Image
Video Stitching for Linear Camera Arrays
Few-Shot Viewpoint Estimation
Matching Prescription & Visual Acuity: Towards AR for Humans
Foveated AR: Dynamically-Foveated Augmented Reality Display
GPU-Accelerated Atari Emulation for Reinforcement Learning
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image
Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera
SIDOD: A Synthetic Image Dataset for 3D Object Pose Recognition with Distractors
A Style-Based Generator Architecture for Generative Adversarial Networks
Pixel-Adaptive Convolutional Neural Networks
A 0.11 pJ/Op, 0.32-128 TOPS, Scalable Multi-Chip-Module-based Deep Neural Network Accelerator with Ground-Reference Signaling in 16nm
High Performance Graph Convolutional Networks with Applications in Testability Analysis
PRIMAL: Power Inference using Machine Learning
Analog/Mixed-Signal Hardware Error Modeling for Deep Learning Inference
DREAMPlace: Deep Learning Toolkit-Enabled GPU Acceleration for Modern VLSI Placement
NVGaze: An Anatomically-Informed Dataset for Low-Latency, Near-Eye Gaze Estimation
Manufacturing Application-Driven Foveated Near-Eye Displays
Routability-Driven Macro Placement with Embedded CNN-Based Prediction Model
Informative Object Annotations: Tell Me Something I Don't Know
Domain-Aware Generalized Zero-Shot Learning
Metaoptimization on a Distributed System for Deep Reinforcement Learning
A Fusion Approach for Multi-Frame Optical Flow Estimation
Localization-Aware Active Learning for Object Detection
Video-to-Video Synthesis
Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
Context-aware Synthesis and Placement of Object Instances
Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
RouteNet: routability prediction for mixed-size designs using convolutional neural network
Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset
Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation
Switchable Temporal Propagation Network
HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration
Multimodal Unsupervised Image-to-Image Translation
A Closed-form Solution to Photorealistic Image Stylization
EOE: Expected Overlap Estimation over Unstructured Point Cloud Data
Superpixel Sampling Networks
Machine Learning and Rendering
Steerable application-adaptive near eye displays
Noise2Noise: Learning Image Restoration without Clean Data
Light-weight Head Pose Invariant Gaze Tracking
Learning Superpixels with Segmentation-Aware Affinity Losse
MoCoGAN: Decomposing Motion and Content for Video Generation
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
Improving Landmark Localization with Semi-Supervised Learning
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
SPLATNet: Sparse Lattice Networks for Point Cloud Processing
Making Convolutional Networks Recurrent for Visual Sequence Learning
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
Geometry-Aware Learning of Maps for Camera Localization
Deep Semantic Face Deblurring
Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning
Reblur2Deblur: Deblurring Videos via Self-Supervised Learning
Progressive Growing of GANs for Improved Quality, Stability, and Variation
IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification
Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks
Learning Binary Residual Representations for Domain-specific Video Streaming
Learning Adaptive Parameter Tuning for Image Processing
Parallel Complexity of Forward and Backward Propagation
Machine Learning and Integral Equations
AdaBatch: Adaptive Batch Sizes for Training Deep Neural Networks
Learning Affinity via Spatial Propagation Networks
Unsupervised Image-to-Image Translation Networks
Parallel Jaccard and Related Graph Clustering Techniques
Understanding Error Propagation in Deep Learning Neural Network (DNN) Accelerators and Applications
Learning to Super-Resolve Blurry Face and Text Images
A Lightweight Approach for On-the-Fly Reflectance Estimation
Group online adaptive learning
Feedforward and Recurrent Neural Networks Backward Propagation and Hessian in Matrix Form
Tactics of Adversarial Attack on Deep Reinforcement Learning Agents
Audio-Driven Facial Animation by Joint End-to-End Learning of Pose and Emotion
Parallel Modularity Clustering
Pruning Convolutional Neural Networks for Resource Efficient Inference
Context-aware Captions from Context-agnostic Supervision
Learning From Noisy Large-Scale Datasets With Minimal Supervision
Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU
Loss Functions for Image Restoration with Neural Networks
Tensor Contractions with Extended BLAS Kernels on CPU and GPU
Temporal Ensembling for Semi-Supervised Learning
Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification
Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks
Parallel Spectral Graph Partitioning
Compressing Neural Networks with the Hashing Trick
Hand Gesture Recognition with 3D Convolutional Neural Networks
Short-Range FMCW Monopulse Radar for Hand-Gesture Sensing
Multi-sensor System for Driver’s Hand-Gesture Recognition
Adaptive Segmentation based on a Learned Quality Metric
Machine Learning for Adaptive Bilateral Filtering
cuDNN: Efficient Primitives for Deep Learning