Juan Carlos Niebles
【Bio】Associate Director of Research, SAIL-Toyota Center for AI Research;Co-Director, Stanford Vision and Learning Lab;
【Research】 the visual recognition and understanding of human actions and activities, objects, scenes, and events

  • 2019 WACV Action-Agnostic Human Pose Forecasting
  • 2018 NIPS Learning to Decompose and Disentangle Representations for Video Prediction
  • 2018 ECCV End-to-End Joint Semantic Segmentation of Actors and Actions in Video
  • 2017 ICCV Dense-Captioning Events in Videos
  • 2017 BMVC End-to-End, Single-Stream Temporal Action Detection in Untrimmed Videos
  • 2017 CVPR SST: Single-Stream Temporal Action Proposals
  • 2016 ECCV Connectionist Temporal Modeling for Weakly Supervised Action Labeling

Hao Su
【Bio】Assistant Professor at UCSD
【Focus on】Scene understanding,3D object recognition

  • 2017 CVPR A Point Set Generation Network for 3D Object Reconstruction from a Single Image
  • 2017 CVPR PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
  • 2017 CVPR SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation
  • 2017 CVPR Learning Shape Abstractions by Assembling Volumetric Primitives
  • 2017 CVPR Learning Non-Lambertian Object Intrinsics across ShapeNet Categories
  • 2016 NIPS FPNN: Field Probing Neural Networks for 3D Data
  • 2016 CVPR Volumetric and Multi-View CNNs for Object Classification on 3D Data
  • 2016 3DV Synthesizing Training Images for Boosting Human 3D Pose Estimation
  • 2016 ECCV ObjectNet3D: A Large Scale Database for 3D Object Recognition
  • 2016 SIGGRAPH 3D Attention-Driven Depth Acquisition for Object Identification
  • 2016 SIGGRAPH A Scalable Active Framework for Region Annotation in 3D Shape Collections
  • 2015 ICCV Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
  • 2015 SIGGRAPH Joint Embeddings of Shapes and Images via CNN Image Purification

Silvio Savarese Silvio Savarese
【Bio】Assistant Professor,leader of a group
【Focus on】Scene understanding,object recognition,tracking,activity recognition

  • 2016 ECCV 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
  • 2016 CVPR Deep Metric Learning via Lifted Structured Feature Embedding
  • 2015 CVPR Enriching Object Detection with 2D-3D Registration and Continuous Viewpoint Estimation
  • 2015 IJRR Learning to Track: Online Multi-Object Tracking by Decision Making
  • 2012 CVPR Estimating the Aspect Layout of Object Categories
  • 2012 CVPR Semantic Structure from Motion with Points, Regions, and Objects
  • 2012 CVPR An Efficient Branch-and-Bound Algorithm for Optimal Human Pose EStimation
  • 2011 ICCV Detecting and Tracking People using an RGB-D Camera via Multiple Detector Fusion

Feifei Li
【Bio】Associate Professor
【Focus on】Deep learning, Scene understanding, Object detection, Tracking, Activity recognition, Scene reconstruction

  • 2016 ECCV Visual Relationship Detection with Language Priors
  • 2016 ECCV Towards Viewpoint Invariant 3D Human Pose Estimation
  • 2016 CVPR Recurrent Attention Models for Depth-Based Person Identification
  • 2016 CVPR DenseCap: Fully Convolutional Localization Networks for Dense Captioning
  • 2015 CVPR Deep Visual-Semantic Alignments for Generating Image Descriptions
  • ImageNet Large Scale Visual Recognition Challenge
  • 2015 CVPR Deep Visual-Semantic Alignments for Generating Image Descriptions
  • 2015 CVPR Best of both worlds: human-machine collaboration for dense object annotation

Vladlen Koltun Vladlen Koltun
【Bio】Researcher of Intel
【Focus on】Scene modeling, scene parsing

  • 2017 Arxiv MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments
  • 2017 CoRL CARLA: An Open Urban Driving Simulator
  • 2017 PNAS Robust Continuous Clustering
  • 2017 ICCV Photographic Image Synthesis with Cascaded Refinement Networks
  • 2017 ICCV Playing for Benchmarks
  • 2017 ICCV Fast Image Processing with Fully-Convolutional Networks
  • 2017 ICCV Learning Compact Geometric Features
  • 2017 CVPR Accurate Optical Flow via Direct Cost Volume Processing
  • 2017 ICLR Learning to Act by Predicting the Future
  • 2017 PAMI Direct Sparse Odometry
  • 2016 ECCV Fast Global Registration
  • 2016 ECCV Playing for Data: Ground Truth from Computer Games
  • 2016 CVPR Feature Space Optimization for Semantic Video Segmentation
  • 2016 CVPR Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids
  • 2016 ICLR Multi-Scale Context Aggregation by Dilated Convolutions2015 CVPR Learning to Propose Objects
  • 2015 CVPR Robust Reconstruction of Indoor Scenes
  • 2014 ECCV Geodesic Object Proposals
  • 2014 CVPR Fast MRF Optimization with Application to Depth Reconstruction
  • 2014 CVPR Simultaneous Localization and Calibration: Self-Calibration of Consumer Depth Cameras
  • 2013 ICCV Elastic Fragments for Dense Scene Reconstruction
  • 2013 ICCV A Simple Model for Intrinsic Image Decomposition with Depth Cues
  • 2013 ICML Parameter Learning and Convergent Inference for Dense Random Fields
  • 2011 NIPS Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
  • 2011 TOG Metropolis Procedural Modeling

Stephen Gould Stephen Gould
【Bio】Associate Professor, PhD from Stanford
【Focus on】Scene Understanding: Object Detection, Segmentation, and Contextual Reasoning

  • 2017 WACV Higher-order Pooling of CNN Features via Kernel Linearization for Action Recognition
  • 2016 ECCV SPICE: Semantic Propositional Image Caption Evaluation
  • 2016 TR On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization
  • 2016 CVPR Discriminative Hierarchical Rank Pooling for Activity Recognition
  • 2016 CVPR Dynamic Image Networks for Action Recognition
  • 2015 PAMI Learning Weighted Lower Linear Envelope Potentials in Binary Markov Random Fields
  • 2014 ECCV Superpixel Graph Label Transfer with Learned Distance Metric
  • 2014 PAMI Learning Weighted Lower Linear Envelope Potentials in Binary Markov Random Fields
  • 2014 ECCV perpixel Graph Label Transfer with Learned Distance Metric
  • 2013 ISBI A Framework for Generating Realistic Synthetic Sequences of Total Internal Reflection Flourescence Microscopy Images
  • 2012 JMLR DARWIN: A Framework for Machine Learning and Computer Vision Research and Development
  • 2012 ECCV PatchMatchGraph: Building a Graph of Dense Patch Correspondences for Label Transfer
  • 2012 ACCV A Noise Tolerant Watershed Transformation with Viscous Force for Seeded Image Segmentation
  • 2011 ICML Max-margin Learning for Lower Linear Envelope Potentials in Binary Markov Random Fields
  • 2011 ICML Max-margin Learning for Lower Linear Envelope Potentials in Binary Markov Random Fields
  • Darwin

Roozbeh Mottaghi Roozbeh Mottaghi
【Bio】Researcher at AI2, postdoc from Stanford, PhD from UC,LA
【Focus on】Scene Understanding: Object Detection, Segmentation, and Contextual Reasoning

  • 2016 ECCV “What happens if…” Learning to Predict the Effect of Forces in Images
  • 2016 CVPR Newtonian Image Understanding: Unfolding the Dynamics of Objects in Static Images
  • 2011 ICCV A Compositional Approach to Learning Part-based Models of Objects
  • 2010 TR Online Selection of Discriminative Tracking Features

Marc Levoy Marc Levoy
【Bio】Professor, leader of a group
【Focus on】computational photography, digital camera


Andrew Ng Andrew Ng
【Bio】Associate Professor, Chief Scientist of Baidu
【Focus on】deep learning, action recognition, machine learning, Robotics

Daphne Koller Daphne Koller
【Focus on】machine learning, probabilistic models, bayesian networks

Youzhi Zou Youzhi Zou
【Bio】Researcher at microsoft, PhD from Stanford
【Focus on】deep learning, action recognition, machine translation

  • 2012 NIPS Deep Learning of Invariant Features via Simulated Fixations in Video
  • 2011 CVPR Learning Hierarchical Spatio-temporal Features for Action Recognition with Independent Subspace Analysis

Qianyi Zhou
【Bio】PhD candidate, Page not found
【Focus on】3d reconstruction

  • Elastic Fragments for DenseScene Reconstruction
  • Simultaneous Localization andCalibration: Self-Calibration of Consumer Depth Cameras

Kilian Pohl Kilian Pohl
【Bio】Associate Professor, Page not found
【Focus on】computational medical image analysis