Procedings of the British Machine Vision Conference 2013 2013
DOI: 10.5244/c.27.64
|View full text |Cite
|
Sign up to set email alerts
|

A Topic Model Approach to Representing and Classifying Football Plays

Abstract: We address the problem of modeling and classifying American Football offense teams' plays in video, a challenging example of group activity analysis. Automatic play classification will allow coaches to infer patterns and tendencies of opponents more efficiently, resulting in better strategy planning in a game. We define a football play as a unique combination of player trajectories. We develop a framework that uses player trajectories as inputs to MedLDA, a supervised topic model. The joint maximization of bot… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
2
0
1

Year Published

2014
2014
2020
2020

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 18 publications
0
2
0
1
Order By: Relevance
“…[ [13][14][15][16][17] [ 13-15] [16, 17] [ [13][14][15] 91 [16,17] [16] [17] [16] [17] [ 18,19] [18]…”
Section: Gnssunclassified
“…[ [13][14][15][16][17] [ 13-15] [16, 17] [ [13][14][15] 91 [16,17] [16] [17] [16] [17] [ 18,19] [18]…”
Section: Gnssunclassified
“…However, previous work has demonstrated that successful tracking of football players under accurate video registration is still notoriously difficult [8,6]. Recent work seeks to relax the mentioned requirements for feature extraction [1,16], however they rely on several crucial assumptions that do not reliably hold in our web-service setting. A key part of their approach is video registration and background subtraction.…”
Section: Related Workmentioning
confidence: 99%
“…After extracting relevant video features, existing methods typically employ probabilistic generative models for play-type recognition, including a Bayesian network [9], non-stationary Hidden Markov Model [15], topic model [16], and mixture of pictorial-structure model [7]. These models are typically used for each video in isolation.…”
Section: Related Workmentioning
confidence: 99%