Keutmann, M.K.
Co Author Listing * CREMA-D: Crowd-Sourced Emotional Multimodal Actors Dataset
Keutzer, K.[Kurt]
Co Author Listing * Affective Image Content Analysis: Two Decades Review and New Perspectives
* Communication-minimizing 2D convolution in GPU registers
* Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow
* Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data
* Efficient, High-quality Image Contour Detection
* Emotion Recognition From Multiple Modalities: Fundamentals and methodologies
* Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation
* Fast L_1-SPIRiT Compressed Sensing Parallel Imaging MRI: Scalable Parallel Implementation and Clinically Feasible Runtime
* FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
* FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters
* HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision
* Hessian-Aware Pruning and Optimal Neural Implant
* Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models
* Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
* Long term video segmentation through pixel level spectral clustering on GPUs
* MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
* MTTrans: Cross-domain Object Detection with Mean Teacher Transformer
* NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection
* NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
* Open-Vocabulary Point-Cloud Object Detection without 3D Annotation
* Parallel BFS graph traversal on images using structured grid
* parallel region based object recognition system, A
* PreTraM: Self-supervised Pre-training via Connecting Trajectory and Map
* Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
* Q-Diffusion: Quantizing Diffusion Models
* QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection
* Region Similarity Representation Learning
* Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning
* Self-Supervised Pretraining Improves Self-Supervised Pretraining
* SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning
* Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
* SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection
* SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
* SqueezeNext: Hardware-Aware Neural Network Design
* Squeezesegv3: Spatially-adaptive Convolution for Efficient Point-cloud Segmentation
* Trust Region Based Adversarial Attack on Neural Networks
* Visual Transformers: Where Do Transformers Really Belong in Vision Models?
* ZeroQ: A Novel Zero Shot Quantization Framework
Includes: Keutzer, K.[Kurt] Keutzer, K.
38 for Keutzer, K.