The Many Shades of Negativity

Complex event detection has been progressively researched in recent years for the broad interest of video indexing and retrieval. To fulfill the purpose of event detection, one needs to train a classifier using both positive and negative examples. Current classifier training treats the negative vide...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia 2017-07, Vol.19 (7), p.1558-1568
Main Authors: Zhigang Ma, Xiaojun Chang, Yi Yang, Sebe, Nicu, Hauptmann, Alexander G.
Format: Article
Language:English
Subjects:
Animals
Attribute representation
attribute selection
complex event detection
Cues
Detectors
Effectiveness
Event detection
Exploitation
Feature extraction
Indexing
Labels
Learning
Neural networks
Optimization
Retrieval
selective fine-grained labeling
Semantics
Shades
State of the art
Support vector machines
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Complex event detection has been progressively researched in recent years for the broad interest of video indexing and retrieval. To fulfill the purpose of event detection, one needs to train a classifier using both positive and negative examples. Current classifier training treats the negative videos as equally negative. However, we notice that many negative videos resemble the positive videos in different degrees. Intuitively, we may capture more informative cues from the negative videos if we assign them fine-grained labels, thus benefiting the classifier learning. Aiming for this, we use a statistical method on both the positive and negative examples to get the decisive attributes of a specific event. Based on these decisive attributes, we assign the fine-grained labels to negative examples to treat them differently for more effective exploitation. The resulting fine-grained labels may be not optimal to capture the discriminative cues from the negative videos. Hence, we propose to jointly optimize the fine-grained labels with the classifier learning, which brings mutual reciprocality. Meanwhile, the labels of positive examples are supposed to remain unchanged. We thus additionally introduce a constraint for this purpose. On the other hand, the state-of-the-art deep convolutional neural network features are leveraged in our approach for event detection to further boost the performance. Extensive experiments on the challenging TRECVID MED 2014 dataset have validated the efficacy of our proposed approach.
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2017.2659221