USA-washington

下面是USA-washington的视觉人物信息

Hannaneh Hajishirzi
https://homes.cs.washington.edu/~hannaneh/
【Bio】Assistant Professor.
【Research】 designing algorithms for semantic understanding, question answering, and information extraction about different
types of textual and visual data such as web data, news articles, scientific articles, and conversations
【Code】

  • 2018 ECCV ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
  • 2018 NAACL Semi-Supervised Event Extraction with Paraphrase Clusters
  • 2018 ICLR Neural Speed Reading via Skim-RNN
  • 2017 ICLR Query-Reduction Networks for Question Answering

Robert Pless
https://www.cse.wustl.edu/~pless/
【Bio】Professor at Washington Univ, Leader of the Media and Machines Lab, PhD from Maryland
【Research】computer vision with applications to environmental science, medical imaging, robotics and virtual reality.


Ali Farhadi Ali Farhadi

http://homes.cs.washington.edu/~ali/index.html
【Bio】Assistant Professor
【Focus on】Object and action recognition, Multitask learning and annotation prediction, Image segmentation
【Code】

  • 2016 CVPR Situation Recognition: Visual Semantic Role Labeling for Image Understanding
  • 2016 CVPR Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images
  • 2016 CVPR You Only Look Once: Unified, Real-Time Object Detection
  • 2016 ICML Unsupervised Deep Embedding for Clustering Analysis
  • 2012 ECCV Attribute Discovery via Predictable Discriminative Binary Codes

Ira Kemelmacher-Shlizerman
http://homes.cs.washington.edu/~kemelmi/
【Bio】Assistant Professor
【Focus on】3-dimensional reconstruction, Visualization of massive photo collections, Synthesis and prediction of appearances, Planet-scale face recognition
【Code】

  • 2017 CVPR Level Playing Field for Million Scale Face Recognition
  • 2016 CVPR The MegaFace Benchmark: 1 Million Faces for Recognition at Scale

Liefeng Bo
http://research.cs.washington.edu/istc/lfb/
【Bio】Researcher at JD, previous at Amazon, not updated since 2014
【Focus on】image descriptors, boundary detection, image segmentation
【Code】

  • 2013 CVPR Multipath Sparse Coding Using Hierarchical Matching Pursuit
  • 2012 NIPS Discriminatively Trained Sparse Code Gradients for Contour Detection
  • 2012 CVPR RGB-(D) Scene Labeling: Features and Algorithms
  • 2011 NIPS Hierarchical Matching Pursuit for Image Classification: Architecture and Fast Algorithms
  • 2011 IROS Depth Kernel Descriptors for Object Recognition
  • 2010 NIPS Kernel Descriptors for Visual Recognition

Xiaofeng Ren Xiaofeng Ren
http://homes.cs.washington.edu/~xren/
【Bio】researcher of Autonavi, Alibaba, previous at Amazon,worked at Washington, PhD from UC Berkeley, not updated since 2014
【Focus on】image descriptors, boundary detection, image segmentation, figure-ground grouping, object and pose recognition, human body detection and pose estimation, object segmentation and tracking, and optical flow
【Code】

  • 2013 CVPR Histograms of Sparse Codes for Object Detection
  • 2013 CVPR Multipath Sparse Coding Using Hierarchical Matching Pursuit
  • 2013 IROS RGB-D Flow: Dense 3-D Motion Estimation Using Color and Depth
  • 2012 NIPS Discriminatively Trained Sparse Code Gradients for Contour Detection
  • 2012 ISER Unsupervised Feature Learning for RGB-D Based Object Recognition
  • 2012 CVPR RGB-(D) Scene Labeling: Features and Algorithms
  • 2011 NIPS Hierarchical Matching Pursuit for Image Classification: Architecture and Fast Algorithms
  • 2011 IROS Depth Kernel Descriptors for Object Recognition
  • 2010 NIPS Kernel Descriptors for Visual Recognition

GRAIL GRAIL
http://grail.cs.washington.edu/
【Bio】Institute
【Focus on】Image-Based Rendering, 3D Shape Reconstruction
【Code】

  • Bundler: Structure from Motion for Unordered Image Collections.
  • Coordinate-free library from geometric processing: C version, C++ version.
  • CMVS: Clustering Views for Multi-view Stereo
  • GradientShop: A Gradient-Domain Optimization Framework for Image and Video Filtering
  • Multicore Bundle Adjustment software for 3D scene reconstruction.
  • Snoop: Onscreen magnification tool for Windows.
  • Surface reconstruction from unorganized points.
  • VisualSFM: A Visual “Structure from Motion” System.
  • VripPack: Volumetric range image processing package.

Brian Curless Brian Curless
http://homes.cs.washington.edu/~curless/
【Bio】Professor
【Focus on】3D photography, Computational photography and videography, 3D interaction, Visualization
【Code】

  • 2011 CVPR Multicore Bundle Adjustment.
  • 2007 ESR Using Photographs to Enhance Videos of a Static Scene

Steven Seitz Steven Seitz
http://homes.cs.washington.edu/~seitz/
【Bio】Professor
【Focus on】Photo Collections, Image-Based Rendering and Illumination, 3D Shape Reconstruction, Motion and Animation, Vision for HCI


Pedro Domingos Pedro Domingos
http://homes.cs.washington.edu/~pedrod/
【Bio】Professor
【Focus on】Machine learning, Data mining
【Code】

  • Alchemy: Statistical relational AI.
  • SPN: Sum-product networks for tractable deep learning.
  • BVD: Bias-variance decomposition for zero-one loss.
  • NBE: Bayesian learner with very fast inference.
  • RISE: Unified rule- and instance-based learner.
  • VFML: Toolkit for mining massive data sources.

Neeraj Kumar Neeraj Kumar
http://homes.cs.washington.edu/~neeraj/
【Bio】Researcher of Dropbox, Postdoctor form Washington, PhD from Columbia
【Focus on】human faces, fine-grained visual categorization, large collections of real-world images for a variety of applications
【Code】

  • Leafsnap
  • Attribute Calibration Software
  • MugHunt Online Face Search Engine
  • Smileys Be Gone! source code
  • Compose-by-Chords Max/MSP code

【Dataset】

  • Leafsnap
  • Labeled Face Parts in the Wild (LFPW)
  • PubFig: Public Figures Face Database
  • FaceTracer Database

Santosh Divvala Santosh Divvala
http://homes.cs.washington.edu/~santosh/
【Bio】Researcher at AI2, Postdoc from Washington, PhD from CMU
【Focus on】Object recognition, Scene parsing
【Code】

  • A “lazy learning” framework (combination of kNN and SVM) for pedestrian detection the CALTECH dataset
  • Mexed version of Felzenszwalb segmentation code (to avoid the annoying reading/writing ppm images)
  • Fast implementation of the l1-distance. Uses SIMD compiler intrinsics and OpenMP parallelism for high speed

 

Aleksandr Aravkin
https://uw-amo.github.io/saravkin/
https://www.slim.eos.ubc.ca/sasha
【Bio】Assistant Professor
【Research】Machine learning


Li Zhang Li Zhang
http://pages.cs.wisc.edu/~lizhang/
【Bio】Researcher of google, Assistant professor of WISC, not updated since 2011
【Focus on】Semantic Image Analysis and Search,Computational Photography and Camera, 3D Reconstruction


Linda Shapiro Linda Shapiro
http://homes.cs.washington.edu/~shapiro/
【Bio】Professor
【Focus on】Object and Activity Recognition, Multimedia Information Retrieval,3D Object Recognition