Bharath Hariharan

We are all trapped between the beautiful blueprints of the most perfect systems and the World that contradicts itself, the World that is "large and contains multitudes" - Stefan Themerson, The Mystery of the Sardine



My interests are broadly in recognition in computer vision. I want to build systems that understand the visual world as well as people do. Currently, I am working on building systems that can learn about tens of thousands of visual concepts with very little or no supervision, produce rich and detailed outputs such as precise 3D shape, and reason about the world and communicate this reasoning to humans. I am looking for graduate students interested in deep learning and visual recognition.


Before joining Cornell, I was a postdoc working with Ross Girshick, Piotr Dollár, Larry Zitnick, Laurens van der Maaten and other amazing people at Facebook AI Research. I did my PhD at beautiful Berkeley with Jitendra Malik.
Important note: As of 4 Aug, 2017, I no longer have access to my Facebook email id. Please use my Cornell email id to contact me.

Assistant Professor
311 Gates Hall
Cornell University
bharathh-AT-cs-DOT-cornell-DOT-edu

Teaching

I will be teaching graduate computer vision (CS6670) in Fall 2017.

Publications

Thesis

  • Beyond Bounding Boxes: Precise Localization of Objects in Images (Thesis)
    Tech report    code

Computer Vision

  • New Low-shot Visual Recognition by Shrinking and Hallucinating Features
    Bharath Hariharan, Ross Girshick
    ICCV, 2017 (Spotlight).
    arxiv    supplementary    code
  • New Inferring and Executing Programs for Visual Reasoning
    Justin Johnson, Bharath Hariharan, Laurens van der Maaten, Judy Hoffman, Li Fei-Fei, C. Lawrence Zitnick, Ross Girshick
    ICCV, 2017 (Oral).
    arxiv    project page
  • Learning Features by Watching Objects Move
    Deepak Pathak, Ross Girshick, Piotr Dollár, Trevor Darrell, Bharath Hariharan
    CVPR, 2017 (To appear).
    arxiv    bib    project page
  • CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
    Justin Johnson, Bharath Hariharan, Laurens van der Maaten, Li Fei-Fei, C. Lawrence Zitnick, Ross Girshick
    CVPR, 2017 (To appear).
    arxiv    bib    project page
  • Feature Pyramid Networks for Object Detection
    Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie
    CVPR, 2017 (To appear).
    arxiv    bib
  • Iterative Instance Segmentation
    Ke Li, Bharath Hariharan, Jitendra Malik
    CVPR, 2016.
    pdf    bib    abstract
  • Object Instance Segmentation and Fine-grained Localization using Hypercolumns
    Bharath Hariharan, Pablo Arbeláez, Ross Girshick, Jitendra Malik
    TPAMI, 2016.
    pdf    bib    abstract    code
  • DeepBox: Learning Objectness with Convolutional Networks
    Weicheng Kuo, Bharath Hariharan, Jitendra Malik
    ICCV, 2015.
    pdf    bib    abstract
  • Hypercolumns for Object Segmentation and Fine-grained Localization
    Bharath Hariharan, Pablo Arbeláez, Ross Girshick, Jitendra Malik
    CVPR, 2015 (Oral).
    pdf    bib    abstract    code
  • Simultaneous Detection and Segmentation
    Bharath Hariharan, Pablo Arbeláez, Ross Girshick, Jitendra Malik
    ECCV,2014.
    pdf    bib    abstract    project page
  • Detecting objects using Deformation Dictionaries
    Bharath Hariharan, Larry Zitnick, Piotr Dollar
    CVPR, 2014.
    pdf    bib    abstract    code
  • Using k-poselets for detecting people and localizing their keypoints
    Georgia Gkioxari*, Bharath Hariharan*, Ross Girshick, Jitendra Malik
    CVPR, 2014.
    *equal contribution
    pdf    bib    abstract    code
  • Discriminative decorrelation for clustering and classification
    Bharath Hariharan, Jitendra Malik, Deva Ramanan
    ECCV, 2012.
    pdf    bib    abstract
  • Semantic segmentation using regions and parts
    Pablo Arbeláez, Bharath Hariharan, Chunhui Gu, Saurabh Gupta, Lubomir Bourdev, Jitendra Malik
    CVPR, 2012.
    pdf    bib    abstract
  • Efficient max-margin multi-label classification with applications to zero-shot learning
    Bharath Hariharan, S. V. N. Vishwanathan, Manik Varma
    Machine Learning, 2012.
    pdf    bib    abstract
  • Semantic contours from inverse detectors
    Bharath Hariharan, Pablo Arbeláez, Lubomir Bourdev, Subhransu Maji, Jitendra Malik
    ICCV, 2011.
    pdf    bib    abstract    dataset
  • Large scale max-margin multi-label classification with priors
    Bharath Hariharan, Lihi Zelnik-Manor, S. V. N. Vishwanathan, Manik Varma
    ICML, 2010.
    pdf    bib    abstract    code

Machine Learning Applications

  • New Selecting the Best VM across Multiple Public Clouds: A Data-Driven Performance Modeling Approach
    Neeraja J. Yadwadkar, Bharath Hariharan, Joseph E Gonzalez, Burton Smith, Randy Katz
    SoCC, 2017 (To appear).
  • Multi-Task Learning for Straggler Avoiding Predictive Job Scheduling
    Neeraja J. Yadwadkar, Bharath Hariharan, Joseph Gonzales, Randy Katz
    JMLR, 2016.
    pdf    bib    abstract
  • Faster Jobs in Distributed Data Processing using Multi-Task Learning
    Neeraja J. Yadwadkar, Bharath Hariharan, Joseph Gonzalez, Randy Katz
    SDM, 2015.
    pdf
  • Verification as learning geometric concepts
    Rahul Sharma, Saurabh Gupta, Bharath Hariharan, Alex Aiken, Aditya Nori
    Static Analysis Symposium (SAS), 2013.
    pdf
  • A Data Driven Approach for Algebraic Loop Invariants
    Rahul Sharma, Saurabh Gupta, Bharath Hariharan, Alex Aiken, Percy Liang, Aditya Nori
    European Symposium on Programming (ESOP), 2013. pdf