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

facebooktwittermailshare

A HIERARCHICAL APPROACH TO EVENT DISCOVERY FROM SINGLE IMAGES USING MIL FRAMEWORK

Abstract: 

In this poster, we propose to face the problem of event detection from single images, by exploiting both background information often containing revealing contextual clues and details, which are salient for recognizing the event. Such details are visual objects critical to understand the underlying event depicted in the image and were recently defined in the literature as ”event-saliency”. Adopting the Multiple-Instance Learning (MIL) paradigm we propose a hierarchical approach analyzing first the entire picture and then refining the decision on the basis of the event-salient objects. Validation of the proposed method is carried out on two benchmarking datasets and it demonstrates the effectiveness of the proposed hierarchical approach to event discovery from single images.

up
0 users have voted:

Paper Details

Authors:
Kashif Ahmad, Francesco De Natale, Giulia Boato, Andrea Rosani
Submitted On:
7 December 2016 - 10:30am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Alain Malacarne
Paper Code:
UCD-P1.2
Document Year:
2016
Cite

Document Files

GlobalSIP - A HIERARCHICAL APPROACH TO EVENT DISCOVERY FROM SINGLE IMAGES USING MIL FRAMEWORK.pdf

(72 downloads)

Subscribe

[1] Kashif Ahmad, Francesco De Natale, Giulia Boato, Andrea Rosani, "A HIERARCHICAL APPROACH TO EVENT DISCOVERY FROM SINGLE IMAGES USING MIL FRAMEWORK", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1409. Accessed: Aug. 19, 2017.
@article{1409-16,
url = {http://sigport.org/1409},
author = {Kashif Ahmad; Francesco De Natale; Giulia Boato; Andrea Rosani },
publisher = {IEEE SigPort},
title = {A HIERARCHICAL APPROACH TO EVENT DISCOVERY FROM SINGLE IMAGES USING MIL FRAMEWORK},
year = {2016} }
TY - EJOUR
T1 - A HIERARCHICAL APPROACH TO EVENT DISCOVERY FROM SINGLE IMAGES USING MIL FRAMEWORK
AU - Kashif Ahmad; Francesco De Natale; Giulia Boato; Andrea Rosani
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1409
ER -
Kashif Ahmad, Francesco De Natale, Giulia Boato, Andrea Rosani. (2016). A HIERARCHICAL APPROACH TO EVENT DISCOVERY FROM SINGLE IMAGES USING MIL FRAMEWORK. IEEE SigPort. http://sigport.org/1409
Kashif Ahmad, Francesco De Natale, Giulia Boato, Andrea Rosani, 2016. A HIERARCHICAL APPROACH TO EVENT DISCOVERY FROM SINGLE IMAGES USING MIL FRAMEWORK. Available at: http://sigport.org/1409.
Kashif Ahmad, Francesco De Natale, Giulia Boato, Andrea Rosani. (2016). "A HIERARCHICAL APPROACH TO EVENT DISCOVERY FROM SINGLE IMAGES USING MIL FRAMEWORK." Web.
1. Kashif Ahmad, Francesco De Natale, Giulia Boato, Andrea Rosani. A HIERARCHICAL APPROACH TO EVENT DISCOVERY FROM SINGLE IMAGES USING MIL FRAMEWORK [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1409