IRUS Total

BreakingNews: article annotation by image and text processing

File Description SizeFormat 
top.pdfAccepted version4.59 MBAdobe PDFView/Open
Title: BreakingNews: article annotation by image and text processing
Authors: Ramisa, A
Yan, F
Moreno-Noguer, F
Mikolajczyk, K
Item Type: Journal Article
Abstract: Building upon recent Deep Neural Network architectures, current approaches lying in the intersection of Computer Vision and Natural Language Processing have achieved unprecedented breakthroughs in tasks like automatic captioning or image retrieval. Most of these learning methods, though, rely on large training sets of images associated with human annotations that specifically describe the visual content. In this paper we propose to go a step further and explore the more complex cases where textual descriptions are loosely related to the images. We focus on the particular domain of news articles in which the textual content often expresses connotative and ambiguous relations that are only suggested but not directly inferred from images. We introduce an adaptive CNN architecture that shares most of the structure for multiple tasks including source detection, article illustration and geolocation of articles. Deep Canonical Correlation Analysis is deployed for article illustration, and a new loss function based on Great Circle Distance is proposed for geolocation. Furthermore, we present BreakingNews, a novel dataset with approximately 100K news articles including images, text and captions, and enriched with heterogeneous meta-data (such as GPS coordinates and user comments). We show this dataset to be appropriate to explore all aforementioned problems, for which we provide a baseline performance using various Deep Learning architectures, and different representations of the textual and visual features. We report very promising results and bring to light several limitations of current state-of-the-art in this kind of domain, which we hope will help spur progress in the field.
Issue Date: 1-May-2018
Date of Acceptance: 3-May-2017
URI: http://hdl.handle.net/10044/1/52699
DOI: 10.1109/TPAMI.2017.2721945
ISSN: 0162-8828
Publisher: Institute of Electrical and Electronics Engineers
Start Page: 1072
End Page: 1085
Journal / Book Title: IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume: 40
Issue: 5
Copyright Statement: © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Engineering & Physical Science Research Council (E
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: EP/N007743/1
Keywords: Science & Technology
Computer Science, Artificial Intelligence
Engineering, Electrical & Electronic
Computer Science
News dataset
story illustration
caption generation
vision and text
0801 Artificial Intelligence and Image Processing
0806 Information Systems
0906 Electrical and Electronic Engineering
Artificial Intelligence & Image Processing
Publication Status: Published
Online Publication Date: 2017-06-29
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering