1. Stanford CS223B Computer Vision, Winter 2005 Final Project Presentations + Papers Sebastian Thrun, Stanford Rick Szeliski, Microsoft Hendrik Dahlkamp and Dan Morris, Stanford

2. © sebastian thrun, CMU, 20002 Final Project Presentations Tue March 8  P16: Road surface type estimation for DARPA Grand Challenge  P09: Finding Objects in 3d Point Clouds of Urban Environments  IP5: Tracking of Multiple RC Cars  P15: Shadow detection and removal for DARPA Grand Challenge  P18: Gesture recognition for HCI (Human-Car-Interaction)  P04: Smilifying Images  IP4: Analysis of Parking Patterns  P07: Change detection from multiple camera images  P06: 3D SFM with an IMU  P12: Shape Through Smog Thu Mar 10  P11: Learning Optical Flow from Control Commands of a Mobile Robot  P03: Identifying Cell Components  IP7: Mineral identification from MER Pancam images  P13: Aligning Images of Flies  IP8: Real-Time Feature-Based Mosaicking  P17: Displaying high dynamic range video  IP3: Age Classification  P10: Terrain and Object Matching in Off-road Scenes  IP6: Depth Estimation from Single Images  IP1: Single View Corridor Reconstruction  P02: Improved Speech Recognition through Vision Localization  P01: Autonomous Helicopter Pose and Landing

3. © sebastian thrun, CMU, 20003 Project Presentations  Use MS Powerpoint  Mail to cs223b@gmail.com by 12am at the day of your presentation PPT file All animations/videos (links please)  You have 6 minutes (sorry, this is a big class).  WE WILL STRICTLY ENFORCE THE TIME LIMITS

4. © sebastian thrun, CMU, 20004 Final Project Slides Sorry this has to fit into 6 minutes  1 Slide with title + team member names  1 Slide with problem statement and data samples  1 slide with your approach (keep it short!)  2-3 slides with results, animations?  (hidden slide: list percentages of who in your team did what, e.g.: Dave did 80% of the work, Mike and Ron each 10%)

5. Example Presentation (Dan Gindikin, CS223b 2004)

6. © sebastian thrun, CMU, 20006 Problem: Matching Images to Aerial Maps

7. © sebastian thrun, CMU, 20007 Approach: SIFT Level 2 Level 3 Level 4

8. © sebastian thrun, CMU, 20008 Results 7690 features 968 features

9. © sebastian thrun, CMU, 20009 Your Final Project Paper On-A-Slide  Abstract (short is sweet!) Problem, gap, approach, key results  Introduction Broad problem and impact “scientific gap” (what technical aspects have not yet been solved) summary approach (should include reference to technical gap) key results  Approach Background tutorial (if necessary) Your technical innovation (might be multiple pages/sections, with repeated reference to scientific gap)  Results Main questions that are being investigated in experiments, ref to gap possibly with main results highlighted Data sets, simulator, implementation details Empirical results (might be multiple pages)  Related Work Don’t just say what’s been done. Point out how prior work relates to yours and to the scientific gap you set forth in the intro.  Summary/Discussions/Conclusion Summary problem, approach, result, in past tense Discuss open questions, promising research directions  References

10. © sebastian thrun, CMU, 200010 Lesson # 1  Put yourself into the position of the reader!

11. © sebastian thrun, CMU, 200011 Lesson # 2  Motivate your problem Why does it matter? Why is it not solved yet? What impact would a solution have? What contribution did you make?

12. © sebastian thrun, CMU, 200012 Lesson # 3  It doesn’t matter how you got there “We tried A, it didn’t work, therefore we tried B” “B works. To see, let us consider an obvious alternative A, and show A does not work”  Document your progress, not just achievement “B works” “B improves over A (current techniques) by X, which is important because of …”

13. © sebastian thrun, CMU, 200013 Lesson #4  Resist the temptation to say everything you know. A good paper makes one point, not two A good paragraph makes one point, not two (most points are only made in one paragraph, not too)

14. © sebastian thrun, CMU, 200014 Completeness and Conciseness Reviewers may not be familiar with your area: Provide Problem motivation Describe Significant application domains Introduce the State of the art / background material Use Consistent Notation Make sure your experiments match your claims Describe and motivate your measures for evaluation

15. © sebastian thrun, CMU, 200015 Conference Reviewers are Overworked Don't expect them to pay attention to details Don't expect them to read small fonts Motivate problem, explain why open, why interesting Present one idea, not two, three,... Pick informative title A picture is worth 1000 words Be concise! Get to the point! Run a spell and grammar checker Use terminology consistently Define abbreviations, avoid them if possible Convince reader that experiments fit claims/problem Make sure the paper “flows”