|Instructor: Kristen Grauman
Office location: GDC 4.726
Office hours: Tues 2:30-3:30 pm and by appointment
Office location: TA Station #4, GDC
Office hours: Mon 3:30-4:30 pm and Wed 9-10 am
TA: Kapil Krishnakumar
Office location: TA Stations
Office hours: Mon 4:30-5:30 pm and Fri 3-4 pm
TA: Shubham Sharma
Office location: TA Station #4 GDC 1.302
Office hours: Tues/Thurs 5-6 pm
Please use Piazza for assignment help.
I. Features and filters: low-level vision
II. Grouping and fitting: mid-level vision
- Linear filters
- Edges and contours
- Binary image analysis
- Background subtraction
- Motion and optical flow
III. Multiple views
- Segmentation and clustering algorithms
- Hough transform
- Fitting lines and curves
- Robust fitting, RANSAC
- Deformable contours
- Interactive segmentation
IV. Recognition: high-level vision
- Local invariant feature detection and description
- Image transformations and alignment
- Planar homography
- Epipolar geometry and stereo
- Object instance recognition
- Object/scene/activity categorization
- Object detection
- Supervised classification algorithms
- Probabilistic models for sequence data
- Visual attributes
- Active learning
- Dimensionality reduction
- Non-parametric methods and big data
- Deep learning, convolutional neural networks
- Other advanced topics as time permits
TextbookSchedule (cumulative to date)
The course textbook is:
Computer Vision: Algorithms and Applications, by Rick Szeliski.
It is freely available online or may be purchased in hardcopy. Course lecture slides will be posted below and are also a useful reference.
You may also find the following books useful.
- Computer Vision: A Modern Approach, David A. Forsyth and Jean Ponce
- Computer Vision, Linda G. Shapiro and George C. Stockman
- Introductory Techniques for 3-D Computer Vision, Emanuele Trucco and Alessandro Verri.
- Multiple View Geometry in Computer Vision, Richard Hartley and Andrew Zisserman.
- Pattern classification, Richard O. Duda, Peter E. Hart, and David G. Stork
- Pattern Recognition and Machine Learning. Christopher M. Bishop
- Visual Object Recognition. K. Grauman and B. Leibe
||Readings and links
UTCS account setup
Basic Matlab tutorial
Running Matlab at UT
out, due Tues Jan 23
See optional Latex info
|Tues Jan 23||Features and filters||Sec 3.1.1-2, 3.2||Linear filters
|Thurs Jan 25||Sec 3.2.3,
Seam carving paper
Seam carving video
out, due Fri Feb 9
See optional Latex templates
||Sec 3.3.2-4||Binary image analysis
|Thurs Feb 1||Sec 10.5
Texture synthesis by non-parametric sampling, Efros & Leung
Style transfer for video
Evaluating texture synthesis
|Tues Feb 6||Sec 8.4 (up until 8.4.1)
|Thurs Feb 8||Grouping and fitting||Sec 4.3.2
Hough transform line video
|Tues Feb 13||Hough transform
|Thurs Feb 15||Sec 5.1.1||Deformable contours
|A2 out, due Friday Mar 2
|Tues Feb 20||Sec 5.2-5.4||Segmentation
|Thurs Feb 22||Segmentation
talk by Katie Bouman, MIT: "Imaging the
Invisible". GDC auditorium, Tues Feb 27, 11 am.
|Tues Feb 27||Multiple views||Sec 4.1||Local invariant features:
|Thurs Mar 1||Lowe SIFT paper
Affine covariant features code
|Local invariant features:
description and matching
|Practice midterm handout in class|
|Tues Mar 6||Sec 2.1.1, 2.1.2, 6.1.1, 6.1.4
|Thurs Mar 8||Midterm exam|
|Tues Mar 20||Sec 3.6.1
HP frames video 1
HP frames video 2
|Homography and image warping
posted, Mar 19
Vision job talk, Tues 11 am in GDC auditorium, Shuran Song, Princeton, Seeing the Unseen: Data-Driven 3D Scene Understanding for Robot Vision
|Thurs Mar 22||Sec 11.1.1, 11.2-11.5||Stereo, part 1
|Tues Mar 27||Audio camera
Graph cuts stereo matching demo
Middlebury stereo database
DeepStereo, Flynn et al.
Object labeling in RGB-D videos, Lai et al.
Body shape and pose from RGBD - Bogo et al.
|Stereo, part 2
||Synthesis Ch 4, 5, 6 (pdf on
Video Google demo by Sivic et al., paper
David Lowe's SIFT and Generalized Hough approach (Lowe, IJCV 2004)
|Tues April 3||Stanford Mobile Visual Search Data Set,
Chandrasekhar et al.
Astrometry.net: Blind astrometric calibration of arbitrary astronomical images. Lang et al.
out, due April 17
Vision job talk: Saraubh Gupta, UC Berkeley, 11 am GDC auditorium; "Visual Perception and Navigation in 3D Scenes"
|Thurs April 5||Sequence to
sequence: video to text, Venugopalan et al.
||Guest lecture, Prof. Ray
Language + vision: Video captioning
|Tues April 10||Synthesis (pdf on Canvas)
Geometric Min-Hash, Chum et al.
|Mining for objects
|Thurs April 12
||Viola-Jones face detection paper||
Intro to category recognition
Face detection with boosting
|Tues April 17||Burges SVM tutorial
Dalal-Triggs pedestrian detection paper
A5 out, due May 1.
Vision job talk, Hanbyul Joo, CMU: Social signal processing: A computational approach to sensing, reconstructing, and understanding social interaction. 11 am in GDC auditorium.
|Thurs April 19||Burges SVM tutorial
Hays-Efros im2gps paper
Lazebnik et al. Spatial pyramids paper
Vondrick et al. Hoggles paper
Dalal-Triggs pedestrian detection paper
|Support vector machines
|Tues April 24
networks for visual recognition (Stanford)
Krizhevsky et al. Imagenet classification with deep convolutional neural networks paper
Assignments: Assignments will be given approximately every two weeks. The programming problems will provide hands-on experience working with techniques covered in or related to the lectures. All code and written responses must be completed individually. Most assignments will take significant time to complete. Please start early, and use Piazza and/or see us during office hours for help if needed. Please follow instructions in each assignment carefully regarding what to submit and how to submit it.
Extension policy: If you turn in your assignment late, expect points to be deducted. Extensions will be considered on a case-by-case basis, but in most cases they will not be granted. The greater the advance notice of a need for an extension, the greater the likelihood of leniency. For programming assignments, by default, 10 points (out of 100) will be deducted for lateness for each day late. We will use the submission program timestamp to determine time of submission. One day late = from 1 minute to 24 hours past the deadline. Two days late = from 24 hours and 1 minute to 48 hours past the deadline. We will not accept assignments more than 4 days late, or once solutions have been discussed in class, whichever is sooner.
Exams: There is an in-class midterm and a comprehensive final exam. Both exams will be offered at the listed time only. The registrar will set our final exam date, which according to the published UT academic calendar could be as late as May 15 this year. Please account for this when making your summer plans. Neither exam will be offered at a different time to accommodate personal travel plans, internship start dates, interviews, etc.
Participation/attendance: Regular attendance is expected. If for whatever reason you are absent, it is your responsibility to find out what you missed that day. Note that attendance does factor into the final grade. (See Section II of the UTCS Code of Conduct regarding attendance expectations.)
General responsibilities: Beyond the above, your responsibilities in the class are:
- Come to lecture on time.
- Check the class webpage for assignment files, notes, announcements etc.
- Use Piazza for class-related discussion and assignment help (no spoilers, please!)
- Complete the readings prior to lecture. The reading assignments listed on the schedule should be read before the associated class lecture.
- Please do not use a laptop, cell phone, tablet, etc. during class.
- Please read and follow the UTCS code of conduct.
Please note the following important dates and deadlines.
- A0 due Tues Jan 23
- A1 due Fri Feb 9
- A2 due Fri Mar 2 (tentative)
- Midterm exam Thurs Mar 8 (in class, tentative)
- A3 due
Fri Mar 30Tues April 3 (tentative)
- A4 due Tues April 17 (tentative)
- A5 due Tues May 1 (tentative)
- Last class meeting Thurs May 3
- Final exam: Thurs May 10, 2-5 pm. The exam is given during the normal final exam period and will be offered at that time only. See above.
Assignments are due about every two weeks. The assignment deadlines below are tentative and are provided to help your planning. They are subject to minor shifts if the lecture plan needs to be adjusted slightly according to our pace in class.
Grades will be determined as follows. You can check your current grades online using Canvas.
- Assignments (50%, equally weighted for A1-5; 1 point for A0)
- Midterm exam (15%)
- Final exam (25%)
- Class participation, including attendance (10%)
You are encouraged to discuss the readings and concepts with classmates. However, all written work and code must be your own. All work ideas, quotes, and code fragments that originate from elsewhere must be cited according to standard academic practice.
Students caught cheating will automatically fail the course. The case will also be reported to the Office of the Dean of Students, which may institute its own disciplinary measures. If in doubt, look at the departmental guidelines and/or ask.
about Students with Disabilities
The University of Texas at Austin provides upon request appropriate academic accommodations for qualified students with disabilities. To determine if you qualify, please contact the Dean of Students at 471-6529; 471-4641 TTY. If they certify your needs, I will work with you to make appropriate arrangements.
about Missed Work Due to Religious Holy Days
A student who misses an examination, work assignment, or other project due to the observance of a religious holy day will be given an opportunity to complete the work missed within a reasonable time after the absence, provided that he or she has properly notified the instructor. It is the policy of the University of Texas at Austin that the student must notify the instructor at least fourteen days prior to the classes scheduled on dates he or she will be absent to observe a religious holy day. For religious holy days that fall within the first two weeks of the semester, the notice should be given on the first day of the semester. The student will not be penalized for these excused absences, but the instructor may appropriately respond if the student fails to complete satisfactorily the missed assignment or examination within a reasonable time after the excused absence.
for Assignment Write-ups (Optional)
You may use any tool for preparing assignment write-ups that you like, so long as it is organized and clear. Typically we ask for a mix of descriptions/explanations as well as embedded figures composed of images and/or plots produced in Matlab.
Below we provide some info about using Overleaf, a free online editor for Latex. Overleaf provides various Latex templates and compiles your edited .tex files into a pdf automatically. The basics:
1) go to overleaf.com
2) sign up/sign in
3) click new project on the left
4) scroll down to "Homework Assignment" and click on "more homework assignment templates"
5) choose whichever template you feel comfortable with and click "open as template"
6) start editing
7) once you are done editing, click "PDF" in the panel above. A pdf file will be generated and downloaded automatically.
Here are instructions about inserting images.
How to position images.
Captioning, scaling, resizing.