Graphics Group, Computer Science Department, The University of Auckland

Department of Computer Science | University of Auckland

----Update the Publication to GG database----

Category of Publication	Selct from the dropdown list

Year of Publication	Select from the dropdown list

Month of Publication	Selct from the dropdown list

Authors	List of authors, you can choose multiple authors by using "ctrl + mouse left clike" from the current and former members lists
	Current Member: Former Member:
Title	Just the publication title, used in the "basic" view. *No html tags please*
	Incorporating Primary Source Material into the Undergraduate Computer Vision Curriculum
Details	Give the full details here, eg authors, title, publication/conference name, page number, date, etc. Please use the standard "References" format. This is for the "detail" view. * You can use <b> and <i> here *
	Incorporating Primary Source Material into the Undergraduate Computer Vision Curriculum. Kevin Novins and Brendan McCane. International Journal of Pattern Recognition and Artificial Intelligence 15(5), pp. 775-787, August 2001.
All remaining fields are optional, but you should fill out as many as possible.
URL	Give the full* URL here, eg http://www.cs or ftp://ftp.cs*
	http://www.worldscinet.com/journals/ijprai/15/1505/S0218001401001143.html
Keywords	Keywords to help searching
	Teaching computer vision; primary source literature; problem-based learning.
Abstract	Use <p> to start each paragraph, plus <b>* and <i> for format*
	Computer vision is a very broad and rapidly changing field. A major challenge for teachers of this subject is to cover a large body of basic theory while at the same time giving a good sense of state-of-the-art research. Traditionally our fourth year undergraduate course in computer vision was taught using lectures and textbooks. We report on the results of two different alterations of the course, both of which focus on our students' own research into recent primary source literature. In the first alteration we used a seminar-based format. It was a qualified success. The students found the course interesting, gained a high-level understanding of the state-of-the-art in computer vision, and developed critical analysis skills. However, despite the fact that they worked hard, student learning of details of the techniques suffered. They were able to complete the course without a good understanding of the theoretical and mathematical foundations of computer vision. In response to this, our second alteration was to base the course around six problem-based learning units. The students benefitted from the reduced set of topics and higher level of practical work.
	Please check all the information you filled carefully before updating it.

webmaster Saturday, December 21st 2024

Anderson, C.
Cha, R
Chai, Kai
Chung, Jae
Cooksey, C.
Dansted, P.
Du, Lilin
Fong, Y.
Govender, Sashan
Gu, Simon
Halstead, M.
Hamer, Sam
Handley, S.
Hitchner, Lewis
Holmberg, Nathan
Huai, Yongjian
Huang, In-Tai
James, B.S.
Kao, Stephen
Kulka, Peter
Lawrence, Joshua
Lee, J.
Li, Bo
Manke, Felix
McCord, Glenn
Mcleod, K.
Meng, Mong
NG., G.
Nixon, Daniel
Novins, Kevin
Otte, Robin
Plumpton, D.
Poon, David
Roche, G.
Sanders, Michael
Schenke, Stefan
Shao, Parker
stu, a
Wang, Shyh-Chyu
Wells, K.
Wil, J
Willmott, A.
Wong, C.M.
Wylie, C.
Yang, Ting
Zhang, Rui