For students who are enrolled in this course: You need to join the google group and be signed in to access the full version of this website.

Title:         Topics: Object Recognition
Course number: 91.550
Instructor:    Kate Saenko,
Location:      Olsen Hall, Room 410
Meeting Time:  Mondays 4:30-7:00
Office Hours:  Mon/Thu 9:30-11:00 Olsen 223 (subject to change), and by appointment

Course Description   

Recognition of objects and activities in images and video has wide applications, including robotics, content based retrieval, security and healthcare. Recent increases in processing power, availability of large training corpora, and machine learning methods such as deep learning have together significantly advanced the state of the art in this field.


This course will not follow a textbook, but will based exclusively on readings from the recent literature in computer vision, robotics, machine learning and AI conferences. Students will read and present papers in class.

Recommended supplemental computer vision textbooks: 
Recommended supplemental machine learning textbooks:

Software and Hardware

The course will make extensive use of research software that the paper authors have made available. Most of the code will be in Matlab; the Octave scientific programming environment is a free version of Matlab. For the project, any language or library is okay to use, however I encourage you to make use of the implementations we cover during the semester.

Syllabus Overview

See Schedule.

Deliverables/Graded work

Students will be evaluated based on the following graded work:

  • participation in in-class discussions (20%)
  • in-class paper presentations (40%)
  • final project write-up (20%)
  • final project in-class presentation (20%)

Late Policy

  • presentation materials are due 3 hours before class
  • 20% off per day
  • up to 4 days


Permission of instructor. This is a graduate course. Students should be familiar with

  • Calculus, Linear Algebra, Probability and Statistics
  • some Computer Vision or Pattern Recognition
  • some Machine Learning/Data Mining/Artificial Intelligence

Academic Honesty Policy: Students are expected to honor all CS department and UMass Lowell policies related to academic honesty and integrity. Violators risk failing the course in addition to any actions taken by university administration. The default CS department policy is that a student who cheats will fail the course. The University's policy is described here. A definition of plagiarism is here. All work on exams must be the student's own work. All work on homework assignments must also be the student's own work, with the following exceptions: 1) hints provided by the instructor or TA may be used but must be acknowledged in writing in the student's work; 2) high-level hints from another student may also be used if a student is unable to make progress on an assignment problem on his/her own; this type of hint must also be acknowledged in writing in the student's work. Detailed collaboration among students on homework assignments is not permitted. Students cannot obtain homework answers from web sites. 

Religious Observance: UMass Lowell respects the religous observances of students. If religious obligations conflict with course due dates and/or examinations, students should notify the professor in writing well in advance of the due date.