Keutmann, M.K.
* 2014: CREMA-D: Crowd-Sourced Emotional Multimodal Actors Dataset
Keutzer, K.[Kurt]
* 2009: Efficient, High-quality Image Contour Detection
* 2010: Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow
* 2010: Parallel BFS graph traversal on images using structured grid
* 2011: Long term video segmentation through pixel level spectral clustering on GPUs
* 2011: parallel region based object recognition system, A
* 2012: Fast L_1-SPIRiT Compressed Sensing Parallel Imaging MRI: Scalable Parallel Implementation and Clinically Feasible Runtime
* 2013: Communication-minimizing 2D convolution in GPU registers
* 2016: FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters
* 2017: SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
* 2018: Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
* 2018: SqueezeNext: Hardware-Aware Neural Network Design
* 2019: Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization Without Accessing Target Domain Data
* 2019: FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
* 2019: HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision
* 2019: Trust Region Based Adversarial Attack on Neural Networks
* 2020: Squeezesegv3: Spatially-adaptive Convolution for Efficient Point-cloud Segmentation
* 2020: ZeroQ: A Novel Zero Shot Quantization Framework
* 2021: Emotion Recognition From Multiple Modalities: Fundamentals and methodologies
* 2021: Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
* 2021: MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation
* 2021: Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
* 2021: Region Similarity Representation Learning
* 2021: SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning
* 2021: Visual Transformers: Where Do Transformers Really Belong in Vision Models?
* 2022: Affective Image Content Analysis: Two Decades Review and New Perspectives
* 2022: Emotional Semantics-Preserved and Feature-Aligned CycleGAN for Visual Emotion Adaptation
* 2022: Hessian-Aware Pruning and Optimal Neural Implant
* 2022: Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models
* 2022: MTTrans: Cross-domain Object Detection with Mean Teacher Transformer
* 2022: PreTraM: Self-supervised Pre-training via Connecting Trajectory and Map
* 2022: Self-Supervised Pretraining Improves Self-Supervised Pretraining
* 2023: NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection
* 2023: NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
* 2023: Open-Vocabulary Point-Cloud Object Detection without 3D Annotation
* 2023: Q-Diffusion: Quantizing Diffusion Models
* 2023: QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection
* 2023: Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning
* 2023: SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection
* 2024: Multitask Vision-Language Prompt Tuning
Includes: Keutzer, K.[Kurt] Keutzer, K.
39 for Keutzer, K.