Hamed Pirsiavash


Assistant Professor
Department of Computer Science and Electrical Engineering
University of Maryland, Baltimore County (UMBC)

Office: ITE 342
Email: hpirsiav AT umbc DOT edu

Curriculum Vitae

Google Scholar

Since fall 2015, I am an assistant professor at UMBC studying computer vision and machine learning. Prior to this, I was a postdoctoral research associate with Antonio Torralba at Massachusetts Institute of Technology (MIT). I graduated with a PhD in computer science from the University of California Irvine where I was advised by Deva Ramanan and co-advised by Ramesh Jain. I obtained my M.Sc. in electrical engineering at Sharif University of Technology in Tehran, Iran (map).

News

  • We have one paper accepted at ICCV 2017.
  • I will be an area chair for CVPR 2018.
  • We have one paper accepted at CVPR 2017.
  • I will be an area chair for CVPR 2017.
  • We have one paper accepted at 3DV 2016.
  • I will be an area chair for ICVGIP 2016.
  • We have one paper accepted at NIPS 2016.
  • Our work got some media coverage in Forbes, Wired, PopSci, CNN, NPR, Associated Press, and Stephen Colbert!
  • We have 4 papers accepted at CVPR 2016.
  • We have one paper accepted at IJCV.
  • I joined UMBC as an assistant professor.

    • Selected Publications

    Representation Learning by Learning to Count
    Mehdi Noroozi, Hamed Pirsiavash, Paolo Favaro
    International Conference on Computer Vision (ICCV) 2017 (oral).
    [PDF]

    Weakly Supervised Cascaded Convolutional Networks
    Ali Diba, Vivek Sharma, Ali Pazandeh, Hamed Pirsiavash, Luc Van Gool
    International Conference on Computer Vision and Pattern Recognition (CVPR) 2017.
    [PDF]

    Generating Videos with Scene Dynamics
    Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
    Neural Information Processing Systems (NIPS), 2016.
    [PDF] [Project page] [Code]
    Media coverage: NBC News, Scientific American, New Scientist, MIT News

    Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks
    Arsalan Mousavian, Hamed Pirsiavash, Jana Kosecka
    International Conference on 3DVision (3DV), 2016.
    [PDF]

    Anticipating Visual Representations From Unlabeled Video
    Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
    International Conference on Computer Vision and Pattern Recognition (CVPR) 2016 (spotlight).
    [PDF] [Project page]
    Media coverage: Forbes, Wired, PopSci, CNN, NPR, Associated Press, Late Show with Stephen Colbert, MIT News

    Learning Aligned Cross-Modal Representations from Weakly Aligned Data
    Lluís Castrejón, Yusuf Aytar, Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
    International Conference on Computer Vision and Pattern Recognition (CVPR) 2016.
    [PDF] [Project page] [Demo]

    Predicting Motivations of Actions by Leveraging Text
    Carl Vondrick, Deniz Oktay, Hamed Pirsiavash, Antonio Torralba
    International Conference on Computer Vision and Pattern Recognition (CVPR) 2016.
    [PDF] [Data]

    DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns
    Ali Diba, Ali Mohammad Pazandeh, Hamed Pirsiavash, Luc Van Gool
    International Conference on Computer Vision and Pattern Recognition (CVPR) 2016.
    [PDF]

    Visualizing Object Detection Features
    Carl Vondrick, Aditya Khosla, Hamed Pirsiavash, Tomasz Malisiewicz, Antonio Torralba
    International Journal of Computer Vision (IJCV) 2016.
    [PDF] [Project page]

    Learning Visual Biases from Human Imagination
    Carl Vondrick, Hamed Pirsiavash, Aude Oliva, Antonio Torralba
    Neural Information Processing Systems (NIPS), 2015.
    [PDF] [Project page]
    Media coverage: Technology Review

    Assessing the Quality of Actions
    Hamed Pirsiavash, Carl Vondrick, Antonio Torralba
    European Conference on Computer Vision (ECCV), 2014.
    [PDF] [Code + Dataset]

    Parsing Videos of Actions with Segmental Grammars
    Hamed Pirsiavash, Deva Ramanan
    International Conference on Computer Vision and Pattern Recognition (CVPR) 2014 (oral).
    [PDF] [Slides PPT (80MB)]
    Media coverage: NBC News, WIRED-UK, GIGAOM, ScienceDaily, Technology Review, MIT News

    Anticipating the Future by Watching Unlabeled Video
    Carl Vondrick, Hamed Pirsiavash, Antonio Torralba
    arXiv 2015.
    [PDF] [Project page]

    Inferring the Why in Images
    Hamed Pirsiavash*, Carl Vondrick*, Antonio Torralba *equal contribution
    arXiv 2014.
    [PDF] [Project page]

    Are All Training Examples Equally Valuable?
    Agata Lapedriza, Hamed Pirsiavash, Zoya Bylinskii, Antonio Torralba
    arXiv 2014.
    [PDF]

    Parsing IKEA Objects: Fine Pose Estimation
    Joseph Lim, Hamed Pirsiavash, Antonio Torralba
    International Conference on Computer Vision (ICCV) 2013.
    [PDF] [Data]

    Detecting Activities of Daily Living in First-person Camera Views
    Hamed Pirsiavash, Deva Ramanan
    International Conference on Computer Vision and Pattern Recognition (CVPR) 2012 (oral).
    [PDF] [Slides PPT (53MB)] [Poster PDF] [Code + Dataset]

    Steerable Part Models
    Hamed Pirsiavash, Deva Ramanan
    International Conference on Computer Vision and Pattern Recognition (CVPR) 2012.
    [PDF] [Slides PPT] [Poster PDF]

    Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects
    Hamed Pirsiavash, Deva Ramanan, Charless Fowlkes
    International Conference on Computer Vision and Pattern Recognition (CVPR) 2011.
    [PDF] [Code]

    A Large-scale Benchmark Dataset for Event Recognition in Surveillance Video
    Sangmin Oh et al.
    International Conference on Computer Vision and Pattern Recognition (CVPR) 2011.
    [PDF] [Project page]

    TalkMiner: A Lecture Webcast Search Engine
    John Adcock, Matthew Cooper, Laurent Denoue, Hamed Pirsiavash, Lawrence Rowe
    ACM Multimedia 2010.
    [PDF] [www.talkminer.com]

    Bilinear Classifiers for Visual Recognition
    Hamed Pirsiavash, Deva Ramanan, Charless Fowlkes
    Neural Information Processing Systems (NIPS 2009) (spotlight).
    [PDF] [Slides PPT] [slides PDF] [Poster PDF]

    Opti-Acoustic Stereo Imaging: On System Calibration and 3-D Target Reconstruction
    Shahriar Negahdaripour, Hicham Sekkati, Hamed Pirsiavash,
    IEEE Transactions on Image Processing, Vol 18, Issue 6, Jun 2009, PP: 1203-1214.
    [PDF]

    Towards Environment-to-Environment (E2E) Multimedia Communication Systems
    Vivek Singh, Hamed Pirsiavash, Ish Rishabh, Ramesh Jain
    Multimedia Tools and Applications Journal, Springer Netherlands, Vol 44, Num 3, pp 361-388, May 2009.
    [PDF]

    Opti-Acoustic Stereo Imaging, System Calibration and 3-D Reconstruction
    Shahriar Negahdaripour, Hicham Sekkati, Hamed Pirsiavash
    Workshops of CVPR 2007 - Beyond Multiview Geometry.(Best Paper Award)
    [PDF]


    Please check out the list of older publications.