USA-michgan

下面是USA-michgan的视觉人物信息

Honglak Lee Honglak Lee
http://web.eecs.umich.edu/~honglak/
【Bio】Assistant Professor, PhD from stanford
【Focus on】deep learning and representation learning, which aims to learn an abstract representation of the data by a hierarchical and compositional structure
【Code】

  • 2017 NIPS Value Prediction Network
  • 2017 BMVC Exploring the structure of a real-time, arbitrary neural artistic stylization network
  • 2017 ICML Learning to Generate Long-term Future via Hierarchical Prediction
  • 2017 ICML Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
  • 2017 CVPR Discriminative Bimodal Networks for Visual Localization and Detection with Natural Language Queries
  • 2017 ICLR Decomposing Motion and Content for Natural Video Sequence Prediction
  • 2016 NIPS Learning What and Where to Draw
  • 2016 NIPS Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
  • 2016 ECCV Attribute2Image: Conditional Image Generation from Visual Attributes
  • 2016 ICML Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification
  • 2016 ICML Control of Memory, Active Perception, and Action in Minecraft
  • 2016 ICML Generative Adversarial Text to Image Synthesis
  • 2016 CVPR Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network
  • 2016 CVPR Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
  • 2016 CVPR Learning Deep Representations of Fine-Grained Visual Descriptions
  • 2015 NIPS Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
  • 2015 CVPR Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
  • 2015 CVPR Evaluation of Output Embeddings for Fine-Grained Image Classification
  • 2015 RSS Deep Learning for Detecting Robotic Grasps
  • 2015 CVPR Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
  • 2015 CVPR Evaluation of Output Embeddings for Fine-Grained Image Classification
  • 2015 IJRR Deep Learning for Detecting Robotic Grasps
  • 2014 ICML Learning to Disentangle Factors of Variation with Manifold Interaction
  • 2014 ICML Structured Recurrent Temporal Restricted Boltzmann Machines
  • 2013 NIPS Adaptive Multi-Column Deep Neural Networks with Application to Robust Image Denoising
  • 2013 ICML Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines
  • 2013 CVPR Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling
  • 2013 CVPR Weakly Supervised Learning of Mid-Level Features with Beta-Bernoulli Process Restricted Boltzmann Machines

Xiaoming Liu
http://cvlab.cse.msu.edu/ 
http://www.cse.msu.edu/~liuxm/
【Bio】Professor, leader of a group
【Focus on】Face Analysis, reconstruction,
【Code】

  • 2016 CVPR Adaptive 3D Face Reconstruction from Unconstrained Photo Collections
  • 2016 CVPR Large-pose Face Alignment via CNN-based Dense 3D Model Fitting
  • 2015 BMVC Robust Global Motion Compensation in Presence of Predominant Foreground
  • 2015 MVA Multi-modality Imagery Database for Plant Phenotyping

Jia Deng
http://web.eecs.umich.edu/~jiadeng/
【Bio】Assistant Professor
【Focus on】Object Recognition, Human Action Recognition, Vision and Cognition, Vision and Language, Deep Learning, Probabilistic Graphical Models, Large-Scale Machine Learning, Visual Data Mining
【Code】

  • 2017 NIPS Pixels to Graphs by Associative Embedding
  • 2017 NIPS Associative Embedding: End-to-End Learning for Joint Detection and Grouping
  • 2017 CVPR Temporal Action Localization by Structured Maximal Sums
  • 2016 NIPS Single-Image Depth Perception in the Wild.
  • 2016 ECCV Structured Matching for Phrase Localization
  • 2016 ECCV Stacked Hourglass Networks for Human Pose Estimation
  • 2016 arXiv Stacked Hourglass Networks for Human Pose Estimation
  • 2015 CVPR Mining Semantic Affordances of Visual Object Categories
  • 2013 CVPR Fine-Grained Crowdsourcing for Fine-Grained Recognition
  • 2012 CVPR Hedging Your Bets: Optimizing Accuracy-Specificity Trade-offs in Large Scale Visual Recognition
  • 2010 ECCV What does classifying more than 10,000 image categories tell us?