Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION

Abstract: 

Videos of complex events are difficult to represent solely as
bags of low level features. Increasingly, supervised concepts
or attributes are being employed as the intermediate representation
of such videos. We propose a probabilistic framework
that models the conditional relationships between the
concepts and events and devise an approximate yet tractable
solution to infer the posterior distribution to perform event
classification. Using noisy outputs of pre-trained concept detectors,
we learn semantic and visual dependencies between
event and concept pairs. The co-occurrence between concept
pairs is also learned as a marginal over training samples. The
proposed method then employs the learned prior, as well as
the probabilities of occurrence of specific concepts in a test
video to infer the probability of each event using weighted average
one-dependence estimation. The evaluation shows that
our method improves event classification compared to recent
literature on the TRECVID data set

up
0 users have voted:

Paper Details

Authors:
Submitted On:
15 September 2017 - 8:46pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Somayeh Keshavarz
Paper Code:
3052
Document Year:
2017
Cite

Document Files

Recovered File 2.pdf

(28)

Subscribe

[1] , "EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2164. Accessed: Oct. 20, 2019.
@article{2164-17,
url = {http://sigport.org/2164},
author = { },
publisher = {IEEE SigPort},
title = {EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION},
year = {2017} }
TY - EJOUR
T1 - EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2164
ER -
. (2017). EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION. IEEE SigPort. http://sigport.org/2164
, 2017. EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION. Available at: http://sigport.org/2164.
. (2017). "EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION." Web.
1. . EXPLOITING PROBABILISTIC RELATIONSHIPS BETWEEN ACTION CONCEPTS FOR COMPLEX EVENT CLASSIFICATION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2164