Paper Info
Title
Semantic pooling for complex event detection
Abstract
Complex event detection is very challenging in open source such as You-Tube videos, which usually comprise very diverse visual contents involving various object, scene and action concepts. Not all of them, however, are relevant to the event. In other words, a video may contain a lot of "junk" information which is harmful for recognition. Hence, we propose a semantic pooling approach to tackle this issue. Unlike the conventional pooling over the entire video or specific spatial regions of a video, we employ a discriminative approach to acquire abstract semantic "regions" for pooling. For this purpose, we first associate low-level visual words with semantic concepts via their co-occurrence relationship. We then pool the low-level features separately according to their semantic information. The proposed semantic pooling strategy also provides a new mechanism for incorporating semantic concepts for low-level feature based event recognition. We evaluate our approach on TRECVID MED [1] dataset and the results show that semantic pooling consistently improves the performance compared with conventional pooling strategies.
Year
DOI
Venue
2013
10.1145/2502081.2502191
ACM Multimedia 2001
Keywords
DocType
Citations 
abstract semantic,associate low-level visual word,you-tube video,complex event detection,proposed semantic,entire video,low-level feature,semantic information,discriminative approach,semantic concept
Conference
7
PageRank 
References 
Authors
0.51
10
5
Name
Order
Citations
PageRank
Qian Yu11218.17
Jingen Liu280734.41
Hui Cheng321517.34
Ajay Divakaran459850.83
Harpreet Sawhney526514.93