DRIV Meeting Organization, Fall 2008
Items for Discussion
(Please add or edit as you see fit.)
Purpose of the Meetings
- To exchange technical ideas about artificial intelligence, computer vision, machine learning, and computational economics
- To gain experience in conveying technical ideas
- To rehearse talks to be given in other venues
- To socialize
- To address issues of logistics and resources
Points Raised in Recent Email Survey
Each of the following points was raised by someone, but no point was raised by a majority:
- Venue, frequency, and enticements
- Biweekly meetings are sufficiently frequent
- We should hold meetings elsewhere occasionally: Twinnie's, lawn, Tyler's (Old Tobacco district), the Federal (across from Brightleaf Square), 3rd floor of North (the old CSEM), ...
- Staying in LSRC is better
- Some meetings could occur at lunch or dinner time
- Beer
- Milk
- Cookies
- Types of meeting
- Presenting someone else's papers is intimidating
- A reading-group style meeting is preferable
- We need outside speakers
- Some meetings could be allocated to brainstorming about a particular problem
- Paper-reading meetings
- Paper type
- Papers should be visual, have little math, and convey simple and interesting ideas
- Papers that appeal to the interests of a general audience, not be overly specialized
- Look at papers on the boundaries between our areas of interest
- Preparation for discussion
- Have two or three people give one-minute overviews of what they think the next paper should be, to get people interested
- Ditto with a good demo video, graphic, or some other nice display piece
- Have someone give a five-minute crash course on the topic of the following week's paper
- Send email with some background and key ideas (as short as possible) before the presentation
- Discussion format
- Start paper discussion by having everyone ask a question or make a comment about the paper
- Understand at least part of the paper really thoroughly
- Encourage discussion of how a paper fits within the literature of the field
- Paper type
Possible Upcoming Practice Talks, RIP Presentations, Defenses,...
- Practice talk by Mingyu Guo in December
- RIP talk by Mac Mason (date unknown)
- RIP talk by Gavin Taylor (date unknown)
- RIP talk by Josh Letchford (date unknown)
- Thesis defense by Jeff Phillips (November or December)
Dates for Informal Research Presentations
- Mid October: Mingyu Guo
- October or November: Rolando Estrada
- October 24st to November 14th: Seda Vural
- End of October/early November: Susanna Ricco
- Not on November 14 or 21: Zheng Li
- After mid November: Anthony Yan
- After mid November: Monika Schaeffer
- End of semester: Steve Gu
- End og semester: Sam Slee
Papers Suggested for Reading
- S. Gray and D. H. Reiley. Measuring the Benefits to Sniping on eBay. Evidence from a Field Experiment, 2007. PDF. Suggested by Mingyu Guo.
- A list of theoretical papers on electronic commerce. Suggested by Mingyu Guo.
- J. Ting et al. Predicting EMG Data from M1 Neurons with Variational Bayesian Least Squares, NIPS, 2005. Link. Suggested by Zheng Li. A Tutorial on variational Bayes methods may be needed as a prerequisite.
- Compressed sensing. Suggested by Anthony Yan.
- E. J. Candes and M. B. Wakin. An Introduction to Compressive Sampling. IEEE Signal Processing Magazine, 2008. Link.
- E. Candes and J. Romberg. Sparsity and Incoherence In Compressive Sampling. Inverse Problems, 23 (3), pp. 969-985, 2007. Link.
- See also Rice web site on compressed sensing.
- L. Fei-Fei and P. Perona. A Bayesian Hierarchical Model for Learning Natural Scene Categories. CVPR, 2005. Link. Suggested by Steve Gu.
- M. Rubinstein, A. Shamir and S. Avidan. Improved Seam Carving for Video Retargeting. SIGGRAPH, 2008. Link. Suggested by Steve Gu.
- A. A. Gooch, S. C. Olsen, J. Tumblin and B. Gooch. Color2Gray: Salience-Preserving Color Removal. SIGGRAPH, 2005. Link. Suggested by Steve Gu.
- D. Dolgov and S. Thrun. Detection of Principle Directions in Unknown Environments for Autonomous Navigation. Robotics: Science and Systems, 2008. Link. Suggested by Mac Mason.
- C. Vallespi-Gonzalez and T. Stentz. Prior Data and Kernel Conditional Random Fields for Obstacle Detection. Robotics: Science and Systems IV, 2008. Link. Suggested by Mac Mason.
- Rosenhahn et al.. Markerless motion capture of man-machine interaction, CVPR, 2008. Link. Suggested by Susanna Ricco.
- Laptev et al.. Learning realistic human actions from movies. CVPR, 2008. Link. Suggested by Susanna Ricco.
- T. Joachims. Transductive Inference for Text Classification using Support Vector Machines. ICML, pages 200-209, 1999. Link. Suggested by Seda Vural.
- R. Fergus, P. Perona, and A. Zisserman. A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition. CVPR, pages 380-387, 2005. Link. Suggested by Seda Vural.
- P. Duygulu, K. Barnard, N. Freitas, D. Forsyth. Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary. ECCV 2002, pages 97-112, 2002. Link. Suggested by Seda Vural.
- J. Reisinger, P. Stone, and R. Miikkulainen . Online Kernel Selection for Bayesian Reinforcement Learning. ICML, 2008. Link. Suggested by Gavin Taylor.
- R. Fitch and Z. Butler. Million Module March: Scalable Locomotion for Large Self-Reconfiguring Robots. International Journal of Robotics Research. 27(3-4):331-343, 2008. Link. Suggested by Sam Slee.
- Latent Dirichlet allocation. Suggested by Ying Zheng.
- D. M. Blei, A. Y. Ng, M. I. Jordan. Latent Dirichlet Allocation. Journal of Machine Learning Research, 2003. Link.
- X. Wang and E. Grimson. Spatial Latent Dirichlet Allocation. NIPS, 2007. Link.
- D. Newman ``et al. Distributed Inference for Latent Dirichlet Allocation. NIPS'', 2007. Link.
- H. Kashima, K. Tsuda, and A. Inokuchi. Marginalized Kernels between Labeled Graphs. ICML, 2003. Link.
- M. A. Carreira-Perpinan, R. J. Lister, and G. J. Goodhill. A Computational Model for the Development of Multiple Maps in Primary Visual Cortex. Cerebral Cortex 15:1222-1233., 2005. Link. Suggested by Rolando Estrada.
- S. M. Kakade, A. T. Kalai, and K. Ligett. Playing games with approximation algorithms. ``STOC'', 2007. Link. Suggested by Josh Letchford.
- M. Pollefeys and L. Van Gool. From Images to 3D Models. CACM, July 45(7):50-55, 2002. Link. Suggested by Monika Schaeffer.
- Y. Baryshnikov and R. Ghrist. Target enumeration via integration over planar sensor networks, To appear in Proc. Robotics Systems & Science, 2008. Preprint. Suggested by Jeff Phillips.
- D. Katz, J. Kenney, and O. Brock. How Can Robots Succeed in Unstructured Environments? Robot Manipulation, 2008. Link. Suggested by Jeff Phillips.
- Overview of WAFR papers. Suggested by Jeff Phillips.
- B. Glocker et al. Inter and Intra-modal Deformable Registration: Continuous Deformations Meet Efficient Optimal Linear Programming. Information Processing in Medical Imaging, 2007. Link. Suggested by Carlo Tomasi.
- R. M. Rustamov. Laplace-Beltrami Eigenfunctions for Deformation Invariant Shape Representation. Eurographics symposium on Geometry processing, 2007. Link. Suggested by Carlo Tomasi.
Action Items
- Appoint two or three DRIV Meeting coordinators, ideally one from each group. Coordinators have complete freedom of choice for their own participation, but they must keep the schedule running
- Are we meeting on September 19 (grad student retreat)?
- Next meeting