Toward Learning Mixture-of-Parts Pictorial Structures

author: Alan Fern, Oregon State University

Categories

Top: Computer Science: Computer Vision

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Toward Learning Mixture-of-Parts Pictorial Structures
0:34	Talk Objectives
2:04	The OSU Digital Scout Project
6:36	Raw Video Data
7:09	Registered Video Data
8:23	Problem: Formation Labelling
9:21	Challenges in Formation Labelling-part01
10:55	Challenges in Formation Labelling-part02
11:44	Problem Constraints-part01
12:36	Problem Constraints-part02
13:06	Previous Attempt
13:57	Structured Output Representations
17:29	Pictorial Structures
19:44	Matching pictorial structures
20:31	Efficient matching
21:47	Pictorial Structures for Football
22:34	Mixture of Parts Pictorial Structures (MoPPS)
23:23	MoPPS Inference
24:10	MoPPS Tree Representation
24:16	MoPPS Tree for Football
24:57	MoPPS Tree Inference
25:12	Branch-and-Bound Search
25:17	Lower Bound Computations
25:49	Upper Bound Computations
25:51	MoPPS Tree Parameters for Football
25:53	Background Model
25:56	Histogram-Based likelihood
25:58	Experiments
26:00	Results
26:01	Anytime Behavior: % Correct
26:34	Directions Learning MoPPS Models
28:19	Structure and Parameter Learning-part01
29:13	Structure and Parameter Learning-part02
30:09	Speedup Learning
31:19	Active Model Calibration
32:24	Summary and Future Work
33:03	The OSU

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.