TY - GEN
T1 - Interpreting sports tactic based on latent context-free grammar
AU - Xu, Xingzhong
AU - Man, Hong
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/12/9
Y1 - 2015/12/9
N2 - In this paper, latent context-free grammar (LCFG) is proposed to probabilistically interpret high level tactic concepts in sports video. From domain knowledge, a sports concept typically consists of multiple levels of recursive or non-recursive sub-concepts. Conventional shallow models, e.g. HMMs, have difficulties in characterizing such complex semantics. On the other hand, a comprehensive Bayesian network may require detailed design and parameterization, which is frequently impractical. LCFG is introduced as an extension to stochastic context-free grammar (SCFG), which jointly uses a set of low level discriminative terminals from video analysis and a set of intermediate context-free rules from sports domain knowledge to model the complex athletes' behaviors and the underlying tactics. The classical 'pick-and-roll' tactic in basketball game is studied in our experimental work. The experimental results demonstrated the rich representation and interpretation powers of LCFG through its probabilistic parsing trees.
AB - In this paper, latent context-free grammar (LCFG) is proposed to probabilistically interpret high level tactic concepts in sports video. From domain knowledge, a sports concept typically consists of multiple levels of recursive or non-recursive sub-concepts. Conventional shallow models, e.g. HMMs, have difficulties in characterizing such complex semantics. On the other hand, a comprehensive Bayesian network may require detailed design and parameterization, which is frequently impractical. LCFG is introduced as an extension to stochastic context-free grammar (SCFG), which jointly uses a set of low level discriminative terminals from video analysis and a set of intermediate context-free rules from sports domain knowledge to model the complex athletes' behaviors and the underlying tactics. The classical 'pick-and-roll' tactic in basketball game is studied in our experimental work. The experimental results demonstrated the rich representation and interpretation powers of LCFG through its probabilistic parsing trees.
KW - semantic parsing
KW - sports video analysis
KW - stochastic context-free Grammar
UR - http://www.scopus.com/inward/record.url?scp=84956686367&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84956686367&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2015.7351571
DO - 10.1109/ICIP.2015.7351571
M3 - Conference contribution
AN - SCOPUS:84956686367
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 4072
EP - 4076
BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
T2 - IEEE International Conference on Image Processing, ICIP 2015
Y2 - 27 September 2015 through 30 September 2015
ER -