Modeling coverage with semantic embedding for image caption generation

Modeling coverage with semantic embedding for image caption generation This paper presents a coverage-based image caption generation model. The attention-based encoder–decoder framework has enhanced state-of-the-art image caption generation by learning where to attend of the visual field. However, there exists a problem that in some cases it ignores past attention information, which tends to lead to over-recognition and under-recognition. To solve this problem, a coverage mechanism is incorporated into attention-based image caption generation. A sequential updated coverage vector is applied to preserve the attention historical information. At each time step, the attention model takes the coverage vector as auxiliary input to focus more on unattended features. Besides, to maintain the semantics of an image, we propose semantic embedding as global guidance to coverage and attention model. With semantic embedding, the attention and coverage mechanisms consider more about features relevant to the semantics of an image. Experiments conducted on the three benchmark datasets, namely Flickr8k, Flickr30k and MSCOCO, demonstrate the effectiveness of our proposed approach. In addition to solve the over-recognition and under-recognition problems, it behaves better on long descriptions. Keywords Coverage model · Semantic embedding · Image caption generation · Attention-based model 1 Introduction machine translation [7] and speech recognition [8] to interac- tive animation generation [9]. Attention http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png The Visual Computer Springer Journals

Modeling coverage with semantic embedding for image caption generation

Loading next page...
 
/lp/springer_journal/modeling-coverage-with-semantic-embedding-for-image-caption-generation-m10kQxfia3
Publisher
Springer Berlin Heidelberg
Copyright
Copyright © 2018 by Springer-Verlag GmbH Germany, part of Springer Nature
Subject
Computer Science; Computer Graphics; Computer Science, general; Artificial Intelligence (incl. Robotics); Image Processing and Computer Vision
ISSN
0178-2789
eISSN
1432-2315
D.O.I.
10.1007/s00371-018-1565-z
Publisher site
See Article on Publisher Site

Abstract

This paper presents a coverage-based image caption generation model. The attention-based encoder–decoder framework has enhanced state-of-the-art image caption generation by learning where to attend of the visual field. However, there exists a problem that in some cases it ignores past attention information, which tends to lead to over-recognition and under-recognition. To solve this problem, a coverage mechanism is incorporated into attention-based image caption generation. A sequential updated coverage vector is applied to preserve the attention historical information. At each time step, the attention model takes the coverage vector as auxiliary input to focus more on unattended features. Besides, to maintain the semantics of an image, we propose semantic embedding as global guidance to coverage and attention model. With semantic embedding, the attention and coverage mechanisms consider more about features relevant to the semantics of an image. Experiments conducted on the three benchmark datasets, namely Flickr8k, Flickr30k and MSCOCO, demonstrate the effectiveness of our proposed approach. In addition to solve the over-recognition and under-recognition problems, it behaves better on long descriptions. Keywords Coverage model · Semantic embedding · Image caption generation · Attention-based model 1 Introduction machine translation [7] and speech recognition [8] to interac- tive animation generation [9]. Attention

Journal

The Visual ComputerSpringer Journals

Published: Jun 5, 2018

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off