VT Computer Vision and Machine Learning Reading Group
Usual Time: Fridays, 5:00PM - 6:30PM
Usual Location: Whittemore Hall 654

| Mailing List | | Presenter Order | | Previous Years | | Related Links | | FAQ | | About Us |

Image of CVMLRG members.


  • On 2015-11-20 at 5PM in Whittemore 654, Adarsh Kowdle, a Senior SDE at Microsoft, will be giving a talk (abstract on the schedule) about co-segmentation using multiple views.
  • On 2015-10-02 at 11AM in Whittemore 654, David Crandall, a professor at IU, will be giving a talk about egocentric vision.
  • We'll be starting our Fall 2015 meeting on September 11th, still at 5PM in Whittemore 654.
  • Due to the lack of members staying at VT over the summer, we will be suspending meetings until the Fall semester.
  • On 2015-02-13 (Friday), Katerina Fragkiadaki, a post-doc at Berkeley, will be giving a talk about her research on parsing videos in Kelly Hall 310 at 10:30AM.
  • On 2015-02-11 (Wednesday), Kurt Luther will be giving a talk about his research on social computing in Whittemore 654 at 5:45PM.
  • On 2015-02-05 (Thursday), Larry Zitnick will be giving a talk, titled "Commonsense, Vision and Language," in Kelly Hall (i.e., ICTAS) 310 at 2:00PM.
  • For the Spring semester (starting January 30th), we will be meeting at 5PM in Whittemore Hall 654 (Conference Room).
  • 2015 Schedule

    Jump to next talk
    (the highlighted row)
    Date Location Presenter Description
    2015-01-30 Whittemore Hall 654 Peng Zhang Knowing a Good HOG Filter When You See It: Efficient Selection of Filters for Detection.
    E. Ahmed, G. Shakhnarovich, S. Maji. ECCV 2014.
    2015-02-06 Whittemore Hall 654 Shrenik Lad Face Detection without Bells and Whistles.
    M. Mathias, R. Benenson, M. Pedersoli, L. Van Gool. ECCV 2014.
    2015-02-13 Whittemore Hall 654 Rama Vedantam A brief review of recent advances in image captions, based on the following (read the first one if you only have time for one):
    Learning a Recurrent Visual Representation for Image Caption Generation.
    X. Chen, C.L. Zitnick. arXiv 2014.
    Long-term Recurrent Convolutional Networks for Visual Recognition and Description.
    J. Donahue, L.A. Hendricks, S. Guadarrama, M. Rohrbach, S. Venugopalan, K. Saenko, T. Darrell. arXiv 2014.
    Show and Tell: A Neural Image Caption Generator.
    O. Vinyals, A. Toshev, S. Bengio, D. Erhan. arXiv 2014.
    Deep Visual-Semantic Alignments for Generating Image Description.
    A. Karpathy, L. Fei-Fei. arXiv 2014.
    Translating Videos to Natural Language Using Deep Recurrent Neural Networks.
    S. Venugopalan, H. Xu, J. Donahue, M. Rohrbach, R. Mooney, K. Saenko. arXiv 2014.
    From Captions to Visual Concepts and Back.
    H. Fang, S. Gupta, F. Iandola, R. Srivastava, L. Deng, P. Dollar, J. Gao, X. He, M. Mitchell, J.C. Platt, C.L. Zitnick, G. Zweig. arXiv 2014.
    2015-02-20 Whittemore Hall 654 Prakriti Banik An Active Search Strategy for Efficient Object Detection.
    A. Gonzalez-Garcia, A. Vezhnevets, V. Ferrari. arXiv 2014.
    2015-02-27 Whittemore Hall 654 Gordon Christie Main Paper
    Unfolding an Indoor Origami World. [Project Page]
    D. Fouhey, A. Gupta, M. Hebert. ECCV 2014.
    Background Paper
    Data-Driven 3D Primitives for Single Image Understanding. [Project Page]
    D. Fouhey, A. Gupta, M. Hebert. ICCV 2013.
    2015-03-06 N/A N/A No meeting because of MACV 2015 at UNC.
    2015-03-13 N/A N/A No meeting because of Spring Break.
    2015-03-20 Whittemore Hall 654 Qing Sun Structured Low-rank Matrix Factorization: Optimality, Algorithm, and Applications to Image Processing.
    B. Haeffele, E. Young, R. Vidal. ICML 2014.
    2015-03-27 Whittemore Hall 654 Michael Cogswell Understanding Deep Image Representations by Inverting Them.
    A. Mahendran, A. Vedaldi. CVPR 2015.
    2015-04-03 Whittemore Hall 654 Clint Solomon Clint will be giving a tutorial on Recurrent Neural Networks (RNNs).
    2015-04-10 N/A N/A No meeting because of the ICCV 2015 deadline.
    2015-04-17 N/A N/A No meeting because of the ICCV 2015 deadline.
    2015-04-24 Whittemore Hall 654 Harsh Agrawal Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks.
    J. Weston, A. Bordes, S. Chopra, T. Mikolov. arXiv 2015.
    2015-05-01 Whittemore Hall 654 Harsh Agrawal Harsh will be finishing up his presentation from last week. In particular, briefly going over Memory Networks.
    2015-05-08 Whittemore Hall 654 Tanmay Batra Book2Movie: Aligning Video Scenes with Book Chapters.
    M. Tapaswi, M. Bauml, R. Stiefelhagen. CVPR 2015.
    2015 Summer N/A N/A Due to the lack of members staying at VT over the summer, we will be suspending meetings until the Fall semester.
    2015-09-11 Whittemore Hall 654 Aroma Mahendru Image Segmentation in Twenty Questions.
    C. Rupprecht, L. Peter, N. Navab. CVPR 2015.
    2015-09-18 N/A N/A Canceled due to presenter illness.
    2015-09-25 N/A N/A Canceled due to Dhruv being away and not wanting to miss Aishwarya's presentation.
    2015-10-02 (starts at 5:30PM) Whittemore Hall 654 Aishwarya Agrawal Main Paper
    Learning Deep Structured Semantic Models for Web Search using Clickthrough Data.
    P-S Huang, X. He, J. Gao, L. Deng, A. Acero, L. Heck. CIKM 2013.
    Additional Papers
    A Latent Semantic Model with Convolutional-Pooling Structure for Information Retrieval.
    Y. Shen, X. He, J. Gao, L. Deng, G. Mesnil. CIKM 2014.
    Semantic Parsing for Single-Relation Question Answering.
    W-T Yih, X. He, C. Meek. ACL 2014.
    2015-10-09 N/A N/A Last minute cancelation due to VT closing early.
    2015-10-16 Whittemore Hall 654 Aishwarya Agrawal Finishing up Aishwarya's tutorial on DSSM.
    2015-10-23 Whittemore Hall 654 Latha Pemula The Application of Two-level Attention Models in Deep Convolutional Neural Networks for Fine-grained Image Classification.
    T. Xiao, Y. Xu, K. Yang, J. Zhang, Y. Peng, Z. Zhang. CVPR 2015.
    2015-10-30 N/A N/A No meeting because of the CVPR 2016 deadline.
    2015-11-06 N/A N/A No meeting because of the CVPR 2016 deadline.
    2015-11-13 Whittemore Hall 654 Stanislaw Antol Main Paper
    Learning Like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions. [Project Page]
    J. Mao, W. Xu, Y. Yang, J. Wang, Z. Huang, A. Yuille. ICCV 2015.
    Background Paper
    Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN). [Project Page]
    J. Mao, W. Xu, Y. Yang, J. Wang, Z. Huang, A. Yuille. ICLR 2015.
    2015-11-20 Whittemore Hall 654 Guest Speaker:
    Adarsh Kowdle
    Title: Multiple View Object Co-segmentation and Image-based Modeling

    Abstract: The task of co-segmentation refers to obtaining a pixel-wise segmentation of the common foreground object from a group of topically-related images. This task in its most general form is fairly unconstrained. However, a variant of this task focuses on performing co-segmentation on images of a specific object of interest captured from multiple viewpoint or multiple view object co-segmentation. By leveraging the rich 3D information from the scene we can jointly solve the problem of co-segmentation and recover the 3D structure from the 2D images (image-based modeling).
    2015-11-27 N/A N/A No meeting because of Thanksgiving Break.
    2015-12-04 Whittemore Hall 654 Mostafa Arefiyan Spotlight the Negatives: A Generalized Discriminative Latent Model.
    H. Azizpour, M. Arefiyan, S. N. Parizi, S. Carlsson. BMVC 2015.
    2015-12-11 N/A N/A Start of winter break.

    Suggested Papers

    Below we have included some papers/pointers for people that are not able to find something that they would like to share.

    You can check out what some other reading groups at other universities are reading (see Related Links).
    TechTalks has some oral presentations from conferences, e.g., ICML 2014, CVPR 2014, CVPR 2015.
    VideoLectures also has some oral presentations from conferences, e.g., ECCV 2014.

  • Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks. I.J. Goodfellow, Y. Bulatov, J. Ibarz, S. Arnoud, V. Shet. arXiv.
  • Lifting 3D Manhattan Lines from a Single Image. S. Ramalingam, M. Brand. ICCV 2013.
  • Active MAP Inference in CRFs for Efficient Semantic Segmentation. G. Roig, X. Boix, S. Ramos, R. de Nijs, L. Van Gool. ICCV 2013.
  • Weighted Sums of Random Kitchen Sinks: Replacing Minimization with Randomization in Learning. A. Rahimi, B. Recht. NIPS 2008.
  • Nearest Neighbor-based Label Transfer for Weakly Supervised Multiclass Video Segmentation. X. Liu, D. Tao, M. Song, Y. Ruan, C. Chen, J. Bu. CVPR 2014.
  • Decorrelating Semantic Visual Attributes by Resisting the Urge to Share. D. Jayaraman, F. Sha, K. Grauman. CVPR 2014.
  • Fine-Grained Visual Comparisons with Local Learning. A. Yu, K. Grauman. CVPR 2014.
  • Beyond Comparing Image Pairs: Setwise Active Learning for Relative Attributes. L. Liang, K. Grauman. CVPR 2014.
  • Microsoft COCO: Common Objects in Context. T.Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollar, C.L. Zitnick. arXiv 2014.
  • Associative Embeddings for Large-scale Knowledge Transfer with Self-assessment. A. Vezhnevets, V. Ferrari. CVPR 2014.
  • Learning Everything about Anything: Webly-Supervised Visual Concept Learning. S.K. Divvala, A. Farhadi, C. Guestrin. CVPR 2014.
  • Reasoning About Object Affordances in a Knowledge Base Representation. Y. Zhu, A. Fathi, and L. Fei-Fei. ECCV 2014.
  • Part-Pair Representation for Part Localization. J. Liu, Y. Li, P.N. Belhumeur. ECCV 2014.
  • ReferItGame: Referring to Objects in Photographs of Natural Scenes. S. Kazemzadeh, V. Ordonez, M. Matten, T. Berg. EMNLP 2014.
  • Meetings in Previous Years

    Related Links


    1. How is the presenters' order generated?
    The presenters' order is generated from the presenters' list in a FIFO manner (but the list is initially generated randomly).

    2. Who is responsible if I can not present at the scheduled time?

    3. What should I do if I can not present at the scheduled time?
    As early as possible, let the group organizer (santol -at- vt.edu) know about your situation. Also contact other presenters to see if they are willing to swap dates with you.

    4. What if I have more questions about the discussion papers?
    We have a Google Group Forum for encouraging further discussion.

    5. I have a question not listed here...
    Then ask by sending an e-mail to the mailing list (cvmlreadinggroup-g -at- vt.edu).