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

A Pool of Deep Models for Event Recognition

Citation Author(s):
Mohamed Lamine Mekhalfi, Nicola Conci, Giulia Boato, Farid Megani, Francesco De Natale
Submitted by:
Kashif Ahmad
Last updated:
12 September 2017 - 11:01am
Document Type:
Poster
Document Year:
2017
Event:
Presenters:
F G B De Natale
Paper Code:
2084
 

This paper proposes a novel two-stage framework for event recognition in still images. First, for a generic event image, deep features, obtained via different pre-trained models, are fed into an ensemble of classifiers, whose posterior classification probabilities are thereafter fused by means of an order induced scheme, which penalizes the yielded scores according to their confidence in classifying the image at hand, and then averages them. Second, we combine the fusion results with a reverse matching paradigm in order to draw the final output of our proposed pipeline. We evaluate our approach on three challenging datasets and we show that better results can be attained, advancing recent leading works.

up
0 users have voted: