Announcement 1 (9/23): The first class will be in Herrin T195 on Thursday, September 24 at 3:15pm.
Announcement 2 (9/30): The class schedule has changed. Individual group meetings will be held on Thursday, October 1 between 3:15pm and 5:00pm. If you have not received a timeslot, please email us.
Announcement 3 (10/25): Daphne's office hours this week will be 3-4pm on Tuesday (10/27).

One of the original goals of computer vision was to fully understand a natural scene. This involves reasoning about several aspects of the scene including: 3D geometry and scale, location (indoors vs. outdoors), category (beach, urban, rural), boundaries between salient regions, objects and their pose, and activities. While great progress has been made in tackling many of these problems in isolation, only recently have researchers again considered the difficult task of solving these tasks together to produce a consistent description of an image.

In this class, our goal will be to develop a series of computer vision models that can work within a unified framework (representation) for holistic understanding of the scene. In particular, we hope that these models will eventually be integrated into a single probabilistic model that allows us to answer many interesting questions about the scene (such as providing a description of the objects and the relationships between them). For example, we would like to take an image like the one to the left below and produce a labeling such as the one on the right.

  

Another example may involve producing a 3d reconstruction of the scene by understanding the semantic components. Click on the image below to see a video of results from some early work along these lines.

As a student in CS294A, you will help spearhead advances towards this ambitious goal. You will be in charge of a particular sub-task within an integrated scene understanding system.

If you are unable to attend the first meeting but would like to take CS294A, please email cs294a-qa@cs.stanford.edu to let us know.

Teaching Staff

Instructor: Daphne Koller
Office: Gates 142
Office hours: Tuesdays 11am-12pm
email: koller@cs.stanford.edu
Phone: (650) 723-6598

TA: Stephen Gould
Office: Gates 126
Office hours: Wednesdays 3-4pm
email: sgould@cs.stanford.edu
Phone: (650) 725-8784

TA: Tianshi Gao
Office: Gates 252
Office hours: Mondays 4-5pm
email: tianshig@cs.stanford.edu
Phone: (650) 723-8444

Course Schedule

Date	Meeting	Room	Milestone
Thursday, September 24th	Introduction to Class; Object Detection; Image Segmentation	Herrin T195	Email completed questionnaire to TAs
Thursday, October 1st	Individual group meetings	Gates 142
Thursday, October 8th	Scene Understanding; Group presentations	Gates 159	Project proposals
Thursday, October 15th	Group presentations	Gates 159	Baseline results
Thursday, October 22nd	Individual group meetings	Gates 200
Thursday, October 29th	Group presentations	Gates 2A	Preliminary results
Thursday, November 5th	No class (tentative)
Thursday, November 12th	Group presentations	Gates 2A	Main results
Thursday, November 19th	Individual group meetings	TBD
Thursday, November 26th	Thanksgiving Break
Thursday, December 3rd	Final presentations	Gates 2A	Final results

• Course Questionnaire
• Project Descriptions
• Reading List and Other Resources
• Students with Disabilities