CSE 590V: Computer vision seminar

Fall 2013

Hand with Reflecting Sphere by M. C. Escher.
Recolored by xenomorph1138

Course description

CSE 590V is a seminar/reading group focused on recent work in computer vision. We will cover papers from recent and upcoming conferences related to computer vision (CVPR, ICCV, ECCV, NIPS, SIGGRAPH). The seminar is open to everyone. We especially encourage first year graduate students who may be considering research in computer vision or related areas to participate.


Time: Fridays 11am-12pm

Location: CSE 403

Organizers: Ezgi Mercan (ezgi @ cs washington edu) and Richard Newcombe (newcombe @ cs washington edu)

Class mailing list: cse590v @ cs washington edu (subscribe here)


Each week we will cover a recent topic in computer vision by reading and discussing one or more relevant papers. A person will lead the discussion by presenting the chosen paper(s) for the week. We encourage all attendees to read the paper(s) beforehand and to actively participate in the discussion.

Each registered student will attend all classes and prepare a presentation (duration to be determined) on a selected paper(s). We will assign topics/papers during the first week based on preferences.

Each presenter will meet with the organizers before the class date to discuss the upcoming presentation, show prepared slides, and resolve any questions.


Date Topic Presenters Papers Slides
Oct 11 3D Reconstruction Bryan Russell

  • Painting-to-3D Model Alignment Via Discriminative Visual Elements, M. Aubry, B. Russell and J. Sivic, INRIA Technical report, 2013. (PDF, website)

Oct 11 Low-Level
Ezgi Mercan

  • HOGgles: Visualizing Object Detection Features, C. Vondrick, A. Khosla, T. Malisiewicz, A. Torralba, ICCV, 2013. (PDF, website)

  • Supporting papers:
  • Histograms of oriented gradients for human detection, Dalal, N., Triggs, B., CVPR2005. (PDF, website)
  • Reconstructing an image from its local descriptors, Philippe Weinzaepfel, Hervé Jégou and Patrick Pérez, Proc. IEEE CVPR2011. (PDF, website)

Oct 18 Depth
from video
Peter Henry

  • Depth Extraction from Video Using Non-parametric Sampling, Kevin Karsch, Ce Liu, and Sing Bing Kang, ECCV2012. (PDF, website)


Oct 18 Reconstruction
from video
Evan Herbst

  • Dense Variational Reconstruction of Non-Rigid Surfaces from Monocular Video, Ravi Garg, Anastasios Roussos, Lourdes Agapito, CVPR2013. (PDF, website)


Oct 25 3D Face Shu Liang

  • 3D Shape Regression for Real-Time Facial Animation, Chen Cao, Yanlin Weng, Stephen Lin, Kun Zhou, SIGGRAPH2013. (PDF, website)
  • FaceWarehouse: a 3D Facial Expression Database for Visual Computing, Chen Cao, Yanlin Weng, Shun Zhou, Yiying Tong, Kun Zhou, IEEE TVCG2013. (PDF, website)


Oct 25 Human Pose Yao Lu

  • Pose Estimation and Segmentation of People in 3D Movies, Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev, ICCV2013. (PDF, website)


Nov 1 Localization Ricardo Martin

  • Cross-View Image Geolocalization, Tsung-Yi Lin, Serge Belongie, James Hays, CVPR2013. (PDF, website)
  • Graph-Based Discriminative Learning for Location Recognition, Song Cao, Noah Snavely, CVPR2013. (PDF, website)

  • Bonus:
  • Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization, Marcus A. Brubaker, Andreas Geiger, Raquel Urtasun, CVPR2013. (PDF, website)


Nov 8 Scene Semantics Robert Gens

  • Bringing Semantics into Focus Using Visual Abstraction, C. Lawrence Zitnick, Devi Parikh, CVPR2013. (PDF, website)


Nov 8 Scene
Brian Dolhansky

  • ImageSpirit: Verbal Guided Image Parsing. Ming-Ming Cheng, Shuai Zheng, Wen-Yan Lin, Jonathan Warrell, Vibhav Vineet, Paul Sturgess, Niloy Mitra, Nigel Crook, Philip Torr, ACM Transactions on Graphics (TOG), 2013. (PDF, website)


Nov 15 Automatic
Daniel Miller
Harley Montgomery

  • Blocks that Shout: Distinctive Parts for Scene Classification, M. Juneja, A. Vedaldi, C. V. Jawahar, A. Zisserman, CVPR2013. (PDF)

  • Mid-level Visual Element Discovery as Discriminative Mode Seeking, Carl Doersch, Abhinav Gupta, Alexei A Efros, NIPS2013. (PDF)


Nov 22 Scene SIRFS Edward Zhang

  • Intrinsic Scene Properties from a Single RGB-D Image, Jonathan T. Barron, Jitendra Malik, CVPR2013. (PDF, website)

  • A Simple Model for Intrinsic Image Decomposition with Depth Cues, Qifeng Chen and Vladlen Koltun, ICCV2013. (PDF, website)

(Coming soon)

Nov 22 Computational
Supasorn Suwajanakorn

  • WYSIWYG Computational Photography via Viewfinder Editing, Baek, Jongmin and Pajak, Dawid and Kim, Kihwan and Pulli, Kari and Levoy, Marc, ACM Trans. Graph., 2013. (PDF, website)

(Coming soon)

Paper List

1. Geometric Scene Understanding (reconstruction/recognition/segmentation)

  • People Watching: Human Actions as a Cue for Single View Geometry
    David F. Fouhey, Vincent Delaitre, Abhinav Gupta, Alexei A. Efros, Ivan Laptev, and Josef Sivic
    ECCV2012 PDF

  • Indoor Segmentation and Support Inference from RGBD Images
    Nathan Silberman, Derek Hoiem, Pushmeet Kohli, and Rob Fergus
    ECCV2012 PDF

  • Multiple View Object Cosegmentation Using Appearance and Stereo Cues
    Adarsh Kowdle, Sudipta N. Sinha, and Richard Szeliski
    ECCV2012 PDF

  • Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images
    Saurabh Gupta, Pablo Arbelaez, and Jitendra Malik
    CVPR2013 PDF

  • Analyzing 3D Objects in Cluttered Images
    M. Hejrati, D. Ramanan
    NIPS2012 PDF

  • Intrinsic Scene Properties from a Single RGB-D Image
    Jonathan T. Barron, Jitendra Malik
    CVPR2013 PDF

  • Joint 3D Scene Reconstruction and Class Segmentation
    Christian Häne, Christopher Zach, Andrea Cohen, Roland Angst, Marc Pollefeys
    CVPR2013 PDF

  • Understanding Indoor Scenes Using 3D Geometric Phrases
    W. Choi, Y. -W. Chao, C. Pantofaru, S. Savarese
    CVPR2013 PDF

  • Photometric Ambient Occlusion
    Daniel Hauagge, Scott Wehrwein, Kavita Bala, Noah Snavely
    CVPR2013 PDF

2. Semantics/Scene understanding

  • Bringing Semantics into Focus Using Visual Abstraction
    C. Lawrence Zitnick, Devi Parikh
    CVPR2013 PDF

  • A Sentence is Worth a Thousand Pixels
    S. Fidler, A. Sharma and R. Urtasun
    CVPR2013 PDF

3. Localization and camera tracking

  • Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization
    Marcus A. Brubaker, Andreas Geiger, Raquel Urtasun
    CVPR2013 PDF

  • Cross-View Image Geolocalization
    Tsung-Yi Lin, Serge Belongie, James Hays
    CVPR2013 PDF

  • Graph-Based Discriminative Learning for Location Recognition
    Song Cao, Noah Snavely
    CVPR2013 PDF

  • Learning and calibrating per-location classifiers for visual place recognition
    Petr Gronat, G. Obozinski, Josef Sivic, Tomas Pajdla
    CVPR2013 PDF

  • Scene coordinate regression forests for camera relocalization in RGB-D images
    J. Shotton, B. Glocker, C. Zach, S. Izadi, A. Criminisi, A. Fitzgibbon
    CVPR2013 PDF

4. Reconstruction/Depth estimation

  • Reconstructing the World's Museums
    Jianxiong Xiao and Yasutaka Furukawa
    ECCV2012 PDF

  • Megastereo: Constructing High-Resolution Stereo Panoramas
    Christian Richardt, Yael Pritch, Henning Zimmer, Alexander Sorkine-Hornung
    CVPR2013 PDF

  • Dense Scene Reconstruction with Points of Interest
    Qian-Yi Zhou and Vladlen Koltun

Coming soon (newer updates to work will replace older works):

  • Elastic Fragments for Dense Scene Reconstruction
    Qian-Yi Zhou, Stephen Miller, and Vladlen Koltun
    ICCV2013 PDF

5. Automatic Object/part discovery

  • Clustering by Composition for Unsupervised Discovery of Image Categories
    Alon Faktor and Michal Irani
    ECCV2012 PDF

  • Blocks that Shout: Distinctive Parts for Scene Classification
    M. Juneja, A. Vedaldi, C. V. Jawahar, A. Zisserman
    CVPR2013 PDF

6. Machine Learning and Big Data

  • Learning Graphs to Match
    M. Cho, K. Alahari, and J. Ponce
    ICCV2013 PDF

  • Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost
    Thomas Mensink, Jakob Verbeek, Florent Perronnin, and Gabriela Csurka
    ECCV2012 PDF

  • Segmentation Propagation in ImageNet
    Daniel Kuettel, Matthieu Guillaumin, and Vittorio Ferrari
    ECCV2012 PDF

  • Fast, Accurate Detection of 100,000 Object Classes on a Single Machine
    Thomas Dean, Jay Yagnik, Mark Ruzon, Mark Segal, Jonathon Shlens, Sudheendra Vijayanarasimhan
    CVPR2013 PDF

  • Query Adaptive Similarity for Large Scale Object Retrieval
    Danfeng Qin, Christian Wengert, Luc Van Gool
    CVPR2013 PDF

  • OpenSurfaces
    Sean Bell, Paul Upchurch, Noah Snavely, Kavita Bala

7. Object Detection/Recognition

  • Diagnosing Error in Object Detectors
    Derek Hoiem, Yodsawalai Chodpathumwan, and Qieyun Dai
    ECCV2012 PDF

  • Fine-Grained Crowdsourcing for Fine-Grained Recognition
    Jia Deng, Jonathan Krause, Li Fei-Fei
    CVPR2013 PDF

  • Finding Things: Image Parsing with Regions and Per-Exemplar Detectors
    Joseph Tighe, Svetlana Lazebnik
    CVPR2013 PDF

8. Face

  • Online Modeling For Realtime Facial Animation
    S.Bouaziz, Y.Wang, M.Pauly

  • Realtime Facial Animation with On-the-fly Correctives
    Hao Li, Jihun Yu, Yuting Ye, Chris Bregler

  • Supervised Descent Method and Its Applications to Face Alignment
    Xuehan Xiong, Fernando De la Torre
    CVPR2013 PDF

  • Detecting and Aligning Faces by Image Retrieval
    Xiaohui Shen, Zhe Lin, Jonathan Brandt, Ying Wu
    CVPR2013 PDF

9. Pose

  • Articulated Pose Estimation using Discriminative Armlet Classifiers
    Georgia Gkioxari, Pablo Arbelaez, Lubomir Bourdev and Jitendra Malik
    CVPR2013 PDF

  • Poselet Conditioned Pictorial Structures
    Leonid Pishchulin, Mykhaylo Andriluka, Peter Gehler, Bernt Schiele
    CVPR2013 PDF

10. Attributes

  • Attributes for Classifier Feedback
    Amar Parkash and Devi Parikh
    ECCV2012 PDF

  • Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes
    Abhinav Shrivastava, Saurabh Singh, and Abhinav Gupta
    ECCV2012 PDF

11. Action Recognition

  • Action Recognition with Exemplar Based 2.5D Graph Matching
    Bangpeng Yao and Li Fei-Fei
    ECCV2012 PDF

  • Activity Forecasting
    Kris M. Kitani, Brian D. Ziebart, James Andrew Bagnell, and Martial Hebert
    ECCV2012 PDF

  • A Unified Framework for Multi-target Tracking and Collective Activity Recognition
    Wongun Choi and Silvio Savarese
    ECCV2012 PDF

  • Expanded Parts Model for Human Attribute and Action Recognition in Still Images
    Gaurav Sharma, Frédéric Jurie, Cordelia Schmid
    CVPR2013 PDF

12. Computational Photography

  • Good Regions to Deblur
    Zhe Hu and Ming-Hsuan Yang
    ECCV2012 PDF

13. Low level/descriptors/template tracking

  • FasT-Match: Fast Affine Template Matching
    Simon Korman, Daniel Reichman, Gilad Tsur, Shai Avidan
    CVPR2013 PDF

  • All About VLAD
    Relja Arandjelovic, Andrew Zisserman
    CVPR2013 PDF

14. Applications

  • Leafsnap: A Computer Vision System for Automatic Plant Species Identification
    Neeraj Kumar, Peter N. Belhumeur, Arijit Biswas, David W. Jacobs, W. John Kress, Ida C. Lopez, and João V.B. Soares
    ECCV2012 PDF

  • Motion Capture of Hands in Action Using Discriminative Salient Points
    Luca Ballan, Aparna Taneja, Jürgen Gall, Luc Van Gool, and Marc Pollefeys
    ECCV2012 PDF

  • Jointly Aligning and Segmenting Multiple Web Photo Streams for the Inference of Collective Photo Storylines
    Gunhee Kim, Eric P. Xing
    CVPR2013 PDF

  • City-Scale Change Detection in Cadastral 3D Models Using Images
    Aparna Taneja, Luca Ballan, Marc Pollefeys
    CVPR2013 PDF