Introduction
We will read and discuss in class one or two of the best papers from
the most recent top vision conferences. In this way, we'll be learning
together:
- How to read research papers
- About the latest in vision research
- What the community thinks is currently important
Candidates
Our candidates (listed in no particular order) are drawn from
CVPR 2012, CVPR 2011, CVPR 2012, ECCV 2012, ECCV 2010, and ICCV 2011. See
the list of papers below and read their abstracts.
-
A Simple Prior-free Method for Non-Rigid
Structure-from-Motion Factorization by Yuchao Dai, Hongdong
Li, Mingyi He (CVPR'12 Best paper)
-
Max-Margin Early Event Detectors by Minh Hoai and
Fernando De la Torre (CVPR '12 Best student paper)
-
Real-time
Human Pose Recognition in Parts from Single Depth Images,
Jamie Shotton, Andrew FItzgibbon, Mat Cook, Toby Sharp, Mark
Finocchio, Richard Moore, Alex Kipman, Andrew Blake (CVPR'11 Best paper)
-
Recognition Using Visual Phrases, Ali Farhadi,
Mohammad Amin Sadeghi (CVPR '11 Best student paper)
-
Visual Event Recognition in Videos by Learning from Web Data
Lixin Duan, Dong Xu, Wai-Hung Tsang, and Jiebo Luo (CVPR'10 Best paper)
-
Efficient Computation of Robust Low-Rank Matrix Approximations in the Presence of Missing Data using the L1 Norm
Anders Eriksson and Anton van den Hengel (CVPR '10 Best student paper)
-
Graph Cut based Inference with
Co-occurrence Statistics L. Laticky, C. Russell, P. Kohli and
P.H.S. Torr (ECCV'10 Best paper)
-
Ambrosio-Tortorelli Segmentation of Stochastic
Images T. Pätz and T. Preusser (ECCV'10 Best student paper)
-
Close the Loop: Joint Blind Image Restoration and
Recognition with Sparse Representation Prior Haichao Zhang,
Jianchao Yang, Yanning Zhang, Nasser M. Nasrabadi and Thomas
S. Huang (ICCV'11 Best student paper)
-
Relative Attributes Devi Parikh and Kristen Grauman
(ICCV'11 Marr prize)
-
Reconstructing the World's Museums
by Jianxiong Xiao and Yasutaka Furukawa (ECCV '12 Best student paper)
Voting
Please vote by emailing your RANKED TOP TWO choices (by paper number
above) to the instructor by NOON Wed Dec 5.
Responses
You will be required to submit a brief 225-275 word critical response to
the paper before class to help prepare you for the discussion. In
particular, you should note:
- What problem are they trying to solve?
- Why is the problem important?
- How does it currently get done and what are the limitations?
- What are the authors' goals?
- Does the paper have a scientific thesis? Is it falsifiable?
- What are the paper's claims?
- Are the claims substantiated (by theory or experiment)? If so, how?
- What are the limitations of the proposed approach?
- Are there ways to extend the method?
You should include at least two primary points that critique, dispute,
extend, or reinforce the paper.
Submit your responses (in PDF format only) via P-Web; they are due at the
beginnning of class on the day of discussion.
Acknowledgments
The questions above are inspired by and adapted from the following works.
- Fong, Philip W.L., "Reading a computer science research paper",
SIGCSE Bulletin 41, 2 (2009), pp. 138--140. doi:10.1145/1595453.1595493
- Keshav, S., "How to read a paper", SIGCOMM Computer
Communication Review 37, 3 (2007), pp. 83--84. doi:dx.doi.org/10.1145/1273445.1273458