Alexandre Alahi - Research Scientist - Stanford University

Brief Bio

  • Currently Research Scientist at Stanford Vision & CVG labs working with Prof. Fei-Fei Li and Prof. Silvio Savarese
  • Over 30 publications, 3 patents, 3 book chapters, and over 10 awards
  • Ph.D.  from EPFL advised by Prof. Pierre Vandergheynst and Prof. Murat Kunt (nominated for the EPFL Ph.D. prize in 2011)
  • BS+MS from EPFL
  • Awarded to study at Carnegie Mellon University for my Junior year
  • Co-Founded the startup VisioSafe (in 2011), and currently advising several startups
  • Working experience at MERL and Logitech
  • More details on my resume

Research Overview

I work on the theoretical challenges and practical applications of socially-aware systems, i.e., machines that can not only perceive human behavior, but reason with social intelligence in the context of transportation problems and smart spaces.

I envision a future where intelligent machines are ubiquitous, where self-driving cars, delivery robots, and self-moving Segways are facts of everyday life. Beyond embodied agents, we will also see our living spaces – our homes, buildings, and cities – become equipped with ambient intelligence which can sense and respond to human behavior. However, to realize this future, intelligent machines need to develop social intelligence and the ability to make safe and consistent decisions in unconstrained crowded social scenes. Self-driving vehicles must learn social etiquettes in order to navigate cities like Paris or Naples. Social robots need to comply with social conventions and obey (unwritten) common-sense rules to effectively operate in crowded terminals. For instance, they need to respect personal space, yield right-of-way, and “read” the behavior of others to predict future actions.

My research is centered around understanding and predicting human social behavior with multi-modal visual data. My work spans multiple aspects of socially-aware systems: from 1- collecting over 100 million human walking trajectories in crowds with one of the largest networks of multi-modal sensors (more than 130 RGB/Thermal/Depth cameras), 2- developing sparsity-driven algorithms that can perceive and reason in real-time, 3- designing deep learning methods that can learn to predict human social behavior in a fully data-driven way, to 4- integrating the developed methods in real-world systems such as JackRabbot, a socially-aware robot that navigates crowded social scenes:

1- Sensing

Collecting multi-modal data at scale

  • RGB, Depth, Thermal, and
  • Wireless signals
2- Perceiving

Extracting coarse-to-fine grained behaviors

  • Motion trajectories, 3D poses,
  • Collective activities and social interactions
3- Forecasting

Predicting future behaviors

  • Actions, Intentions, and
  • Critical scenarios
4- Acting

Making decisions in real-world settings with

  • Social robots and
  • Smart spaces
My research is at the intersection of:

  • Machine Learning
  • Computer Vision
  • Human-Robot Interaction
  • Signal Processing
  • My interests are:

  • Deep learning
  • Representation Learning
  • Multi-modal processing
  • Sparse approximation
  • I aim to reshape the future of:

  • Transportation systems
  • Mobility
  • Ambient Intelligence
  • Smart spaces
  • News / Media


    Recent News

    Press / Media Coverage

    Awards

    Research awards

    Swiss NSF

    2014

    • Advanced researcher award (12 months fund)

    Swiss NSF

    2013

    • Researcher award (18 months fund)

    CVPR

    2012

    • Winner of the Open Source Award

    EPFL

    2011

    • Ph.D. nominated for the EPFL prize (top 5% of university)

    ICDSC

    2009

    • Challenge prize winner

    Entrepeneurial awards

    LDV

    2014

    • Winner of the startup competition + entrepeneurial challenge

    AVF

    2014

    • Alpine venture forum winner

    Boston Pitch Fest

    2010

    • Ranked 1st out of the top 20 venture leaders

    PTE

    2012

    • Winner of the elevator pitch competition

    Venture Leaders

    2010

    • Selected as the top 20 Swiss Venture leaders of the year

    Venture kick

    2009

    • Winner of the 1st phase

    Publications


    2017

    People tracking

    Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition
    Timur Bagautdinov, Alexandre Alahi, Francois Fleuret, Pascal Fua, Silvio Savarese.
    To come (arxiv link).
    [pdf | project page]

    People tracking

    Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies
    Amir Sadeghian, Alexandre Alahi, Silvio Savarese.
    To come (arxiv link).
    [pdf | project page]

    People tracking

    Unsupervised Learning of Long-Term Motion Dynamics for Videos
    Zelun Luo, Boya Peng, De-An Huang, Alexandre Alahi, Li Fei-Fei.
    To come (arxiv link).
    [pdf | project page]

    People tracking

    Tracking millions of humans
    Alexandre Alahi, Vignesh Ramanathan, Li Fei-Fei.
    To appear in the book on “Group and Crowd Behavior for Computer Vision” by Elsevier.
    [pdf | project page]

    People tracking

    Learning to predict in crowds
    Alexandre Alahi, Vignesh Ramanathan, Kratarth Goel, Alexandre Robicquet, AmirAbbas Sadeghian, Li Fei-Fei, Silvio Savarese.
    To appear in the book on “Group and Crowd Behavior for Computer Vision” by Elsevier.
    [pdf | project page]


    2016

    People tracking

    Perceptual Losses for Real-time Style Transfer and Single Image Super-Resolution
    Justin Johnson, Alexandre Alahi, and Li Fei-Fei.
    European Conference on Computer Vision (ECCV), 2016.
    [pdf | project page]

    People tracking

    Knowledge Transfer for Scene-specific Motion Prediction
    Lamberto Ballan, Francesco Castaldo, Alexandre Alahi, Francesco Palmieri, Silvio Savarese.
    European Conference on Computer Vision (ECCV), 2016.
    [pdf | project page]

    People tracking


    Towards Viewpoint Invariant 3D Human Pose Estimation
    Albert Haque, Boya Peng*, Zelun Luo*, Alexandre Alahi, Serena Yeung, Li Fei-Fei.
    European Conference on Computer Vision (ECCV), 2016.
    [pdf | project page]


    People tracking

    Learning Social Etiquette: Human Trajectory Prediction
    Alexandre Robicquet, Amir Sadeghian, Alexandre Alahi, Silvio Savarese.
    European Conference on Computer Vision (ECCV), 2016.
    [pdf | project page]

    freak Recurrent Attention Models for Depth-Based Person Identification
    Albert Haque, Alexandre Alahi, and Li Fei-Fei.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
    [pdf | project page]
    People tracking

    Social LSTM: Human Trajectory Prediction in Crowded Spaces
    Alexandre Alahi*, Kratarth Goel*, Vignesh Ramanathan, Alexandre Robicquet, Li Fei-Fei, Silvio Savarese.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (* equal contribution)
    (Spotlight oral)

    [pdf | project page]

    People tracking

    Vision-Based Hand Hygiene Monitoring in Hospitals
    Yeung S, Alahi A, Haque A, Luo Z, Peng B, Singh A, Platchek T, Milstein A, Fei-Fei L. .
    In proceedings of the American Medical Informatics Association (AMIA) Symposium, 2016.


    2015

    freak

    Biologically Inspired Keypoints
    Alexandre Alahi, Georges Goetz, and Emmanuel D’Angelo.
    Book
     on Biologically Inspired Computer Vision: Fundamentals and Applications, 2015.
    [pdf | project page]

    Graph matching RGB-W: When Vision Meets Wireless
    Alexandre Alahi, Albert Haque, and Li Fei-Fei.  
    IEEE International Conference on Computer Vision (ICCV), 2015.
    [pdf | project page]
    freak
    Learning to Track: Online Multi-Object Tracking by Decision Making
    Yu Xiang, Alexandre Alahi, and Silvio Savarese.  
    IEEE International Conference on Computer Vision (ICCV), 2015.
    (Oral, acceptance rate: 3.3%)
    [pdf | project page]
    People tracking

    Vision-Based Hand Hygiene Monitoring in Hospitals
    Yeung S, Alahi A, Luo Z, Peng B, Haque A, Singh A, Platchek T, Milstein A, Fei-Fei L.
    In Proceedings of the NIPS Workshop on Machine Learning in Healthcare, 2015.


    2014

    Graph matching

    Robust real-time pedestrians detection in urban environments with low-resolution camera
    Alexandre Alahi, Michel Bierlaire, and Pierre Vandergheynst.  
    Transportation research part C: emerging technologies, 2014.
    [pdf | project page]

    Graph matching Scoop: A real-time sparsity driven people localization algorithm
    Mohammad Golbabaee, Alexandre Alahi, and Pierre Vandergheynst.
     Journal of mathematical imaging and vision, 2014.
    [pdf | project page]
    Graph matching Method and system for automatic objects localization
    Alexandre Alahi, Mohammad Golbabaee, and Pierre Vandergheynst.
    U.S. Patent No. 8,749,630. 10 Jun. 2014.

    [pdf | project page]
    People tracking


    Socially-aware large-scale crowd forecasting
    Alexandre Alahi, Vignesh Ramanathan, and Li Fei-Fei.  
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014
    .
    (Oral
    , acceptance rate: 5.8%)
    .
    [pdf]


    Graph matching System and method for media library navigation and recommendation
    Alexandre Alahi, Pierre Vandergheynst, and Kirell Benzi. 
    No. EPFL-PATENT-211599. 2014.

    freak From bits to images: Inversion of local binary descriptors
    Emmanuel D'Angelo, Jacques L, Alexandre Alahi, Pierre Vandergheynst
    IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2014.
    [pdf | project page]

    2012

    freak Beyond bits: Reconstructing images from local binary descriptors
    Emmanuel D'Angelo, Alexandre Alahi, and Pierre Vandergheynst.  
    IEEE International Conference on Pattern Recognition (ICPR), 2012
    .
    [pdf | project page]

    freak

    FREAK: Fast Retina Keypoint
    Alexandre Alahi, Raphael Ortiz, and Pierre Vandergheynst.  
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012
    .
    (Open Source Award Winner)
    [pdf | project page]

    Graph matching Foreground silhouette extraction robust to sudden changes of background appearance
    Alexandre Alahi, Luigi Bagnato, Damien Matti, and Pierre Vandergheynst.
    IEEE International Conference on Image Processing (ICIP), 2012.
    [pdf | project page]

    2011

    Graph matching

    Sparsity driven people localization with a heterogeneous network of cameras
    Alexandre Alahi, Laurent Jacques, Yannick Boursier, and Pierre Vandergheynst.  
    Journal of Mathematical Imaging and Vision, 2011.
    [pdf | project page]

     


    2010

    Graph matching Stream carving: an adaptive seam carving algorithm
    Daniel Domingues, Alexandre Alahi, and Pierre Vandergheynst.  
    IEEE International Conference on Image Processing (ICIP), 2010.

    [pdf]
    freak Cascade of descriptors to detect and track objects across any network of cameras
    Alexandre Alahi, Pierre Vandergheynst, Michel Bierlaire, and Murat Kunt.  
    Journal on Computer Vision and Image Understanding, 2010.
    [pdf | project page]

    2009

    Graph matching Sparsity-driven people localization algorithm: Evaluation in crowded scenes environments
    Alexandre Alahi, Laurent Jacques, Yannick Boursier, and Pierre Vandergheynst.
    Performance Evaluation of Tracking and Surveillance (PETS-Winter), 2009.

    [pdf | project page]
    Graph matching

    Sport players detection and tracking with a mixed network of planar and omnidirectional cameras
    Alexandre Alahi, Yannick Boursier, Laurent Jacques, and Pierre Vandergheynst.  
    ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC), 2009
    .
    (Challenge price winner)
    [pdf | project page]

    Graph matching A sparsity constrained inverse problem to locate people in a network of cameras
    Alexandre Alahi, Yannick Boursier, Laurent Jacques, and Pierre Vandergheynst.   
    IEEE International Conference on Digital Signal Processing, 2009.

    [pdf | project page]

    2008

    freak

    Object detection and matching with mobile cameras collaborating with fixed cameras
    Alexandre Alahi, Michel Bierlaire, and Murat Kunt.  
    ECCV workshop on Multi-camera and Multi-modal Sensor Fusion
    , 2008.
    [pdf | project page]

    freak Object detection and matching in a mixed network of fixed and mobile cameras
    Alexandre Alahi, Pierre Vandergheynst, Michel Bierlaire, and Murat Kunt.
    ACM Multimedia workshop on analysis and retrieval of events/actions, 2008.
    [pdf | project page]
    freak A master-slave approach for object detection and matching with fixed and mobile cameras
    Alexandre Alahi, David Marimon, Michel Bierlaire, and Murat Kunt.  
    IEEE International Conference on Image Processing (ICIP), 2008.
    [pdf | project page]
    People tracking

    System and method for measuring performances of surveillance systems
    Ali Azarbayejani, Alexandre Alahi, and Murat Erdem.
    U.S. Patent No. 7,415,385. 19 Aug. 2008.
    [pdf]


     

    My thesis

     

    Code/Datasets

     

    Soure code

    People tracking

    Social LSTM: Human Trajectory Prediction in Crowded Spaces
    Alexandre Alahi*, Kratarth Goel*, Vignesh Ramanathan, Alexandre Robicquet, Li Fei-Fei, Silvio Savarese.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (* equal contribution)
    (Spotlight oral)

    [pdf | code | project page]

    People tracking


    Perceptual Losses for Real-time Style Transfer and Single Image Super-Resolution
    Justin Johnson, Alexandre Alahi, and Li Fei-Fei.
    European Conference on Computer Vision (ECCV), 2016.
    [pdf | code | project page]

       
    freak
    Learning to Track: Online Multi-Object Tracking by Decision Making
    Xiang, Yu, Alexandre Alahi, and Silvio Savarese.
    IEEE International Conference on Computer Vision (ICCV), 2015.
    (Oral, acceptance rate: 3.3%)
    [pdf | code | project page]

    freak


    FREAK: Fast Retina Keypoint
    Alexandre Alahi, Raphael Ortiz, and Pierre Vandergheynst.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012
    .
    (Open Source Award Winner)
    [pdf code | project page]

       

     

    Datasets

    Over the past years, I have collected data to detect, track, and predict human social dynamics in various scenes:

    Here are the links to download the collected data:

    People tracking [April 16] Depth videos + ground truth human poses from 2 viewpoints to improve 3D human pose estimation. [project page]
    freak [April 16] Depth images + ground truth identity to improve human identification with depth images. [project page]
    Graph matching [Dec 15] RGB images +Wireless signals (RSS) from individuals in both indoor and outdoor spaces to improve localization and tracking algorithms. [project page]
    People tracking [Jan 16] Aerial RGB videos + ground truth trajectories from multiple targets (e.g., pedestrians, bicyclist, skateboarders, carts,...) navigating an outdoor campus to learn all interactions between humans and their surrounding. [project page]
    People tracking


    [Jun 14] Human trajectories from an indoor train terminal to learn social dynamics in crowded scenes. [project page]


    freak [Aug 09] Low-resolution RGB videos + ground truth trajectories from multiple fixed and moving cameras monitoring the same scenes (indoor and outdoor) to improve object tracking and matching. [project page]

     

     

    TOP