Skip to content
Smart Scholars🛡 Scholar Shield🏛 Research Integrity Desk🧩 Portfolio Console📰 Journals🔧 DOI MembersTools🔎 Journal AuditGI GetIndexedDr DOI Doctor

Cite this DOI

10.46243/jst.2019.v4.i06.pp42-50 · BREAKING NEWS ARTICLE ANNOTATION USING IMAGE AND TEXT PROCESSING

APA (7th edition)

U.GAYATHRI, & M.V.BALARAM (2019). BREAKING NEWS ARTICLE ANNOTATION USING IMAGE AND TEXT PROCESSING. *Journal of Science & Technology*, *04*(06), 42–50. https://doi.org/10.46243/jst.2019.v4.i06.pp42-50

⬇ text Italics are shown as *asterisks* in plain text — the journal or book title and the volume.

BibTeX

@article{ugayathri2019breaking,
  author    = {U.GAYATHRI and M.V.BALARAM},
  title     = {{BREAKING NEWS ARTICLE ANNOTATION USING IMAGE AND TEXT PROCESSING}},
  journal   = {Journal of Science \& Technology},
  year      = {2019},
  volume    = {04},
  number    = {06},
  pages     = {42--50},
  publisher = {Longman Publishers},
  issn      = {2456-5660},
  doi       = {10.46243/jst.2019.v4.i06.pp42-50},
  url       = {https://doi.org/10.46243/jst.2019.v4.i06.pp42-50},
  language  = {en},
  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.}
}

⬇ .bib

RIS (EndNote, Zotero, Mendeley)

TY  - JOUR
TI  - BREAKING NEWS ARTICLE ANNOTATION USING IMAGE AND TEXT PROCESSING
AU  - U.GAYATHRI
AU  - M.V.BALARAM
JO  - Journal of Science & Technology
PY  - 2019
DA  - 2019///
VL  - 04
IS  - 06
SP  - 42
EP  - 50
PB  - Longman Publishers
SN  - 2456-5660
LA  - en
AB  - 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.
DO  - 10.46243/jst.2019.v4.i06.pp42-50
UR  - https://doi.org/10.46243/jst.2019.v4.i06.pp42-50
ER  -

⬇ .ris

CSL-JSON

{
    "type": "article-journal",
    "id": "10.46243/jst.2019.v4.i06.pp42-50",
    "DOI": "10.46243/jst.2019.v4.i06.pp42-50",
    "URL": "https://doi.org/10.46243/jst.2019.v4.i06.pp42-50",
    "title": "BREAKING NEWS ARTICLE ANNOTATION USING IMAGE AND TEXT PROCESSING",
    "source": "Smart Scholars Registry",
    "container-title": "Journal of Science & Technology",
    "author": [
        {
            "family": "U.GAYATHRI"
        },
        {
            "family": "M.V.BALARAM"
        }
    ],
    "issued": {
        "date-parts": [
            [
                2019
            ]
        ]
    },
    "volume": "04",
    "issue": "06",
    "page": "42-50",
    "publisher": "Longman Publishers",
    "language": "en",
    "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.",
    "ISSN": "2456-5660"
}

⬇ .json What citeproc and reference managers read; the DOI system hands it out for Accept: application/vnd.citationstyles.csl+json, and so does this registry's resolver.

From the record as registered (version 2) — the record and its history. Programs: https://registry.smartscholars.in/api.php?action=cite&doi=10.46243%2Fjst.2019.v4.i06.pp42-50 gives all four in one JSON answer.

Share this page

Share this page

Ask AI about this page

Everything Smart Scholars runs

Nine sites, one account. A journal starts at the audit; an author starts at Scholar Shield.

What we do: DOIs registered from what a journal already has · Crossref records completed — references, abstracts, licences, ORCID iDs, affiliations and ROR IDs, funding · DOIs that resolve · articles preserved · journals rated on the public record · see everything we do →

Book a free call

For journals & publishers

Start with the audit — ₹4,999 per journal, and the gate to everything else.

DOI care

Every service on one journal profile — each previews first and acts only on your approval.

  • DOI Doctor — check & repairevery DOI tested at doi.org and Crossref; dead links, abstracts, licences, ORCIDs
  • Smart Deposita new DOI from your PDF, Word file, article page, JATS XML or spreadsheet — every value shown with its source, deposited once you confirm it
  • DOI census (Excel)site against Crossref, both directions, with a copy-paste fix per article
  • Backfile DOIsDOIs for older articles that never had one — no per-DOI fee of ours
  • DOIs for conference proceedingsthe conference, the volume and every paper — registered in the organiser's own name
  • Scopus indexing guidethe minimum criteria, the 14 CSAB criteria and how a title is suggested — from Elsevier's own page
  • Embase indexing guidewhat Embase asks of a biomedical journal and how to suggest it
  • Write DOIs into OJSthe verified DOIs pushed onto your article pages through your own API
  • Silent-failure monitorweekly checks of site, OAI-PMH, Scholar tags, ISSN, preservation, hijack lists
  • Journal Radarevery journal, every day: SSL, DNS, redirects, robots.txt, OJS, DOIs, Crossref metadata, broken links — what broke since yesterday first
  • Verified metrics & badgesa public, dated, source-linked metrics page and a "cited by" badge
  • Quality dossier (PDF)one PDF for universities, authors and reviewers
  • Author citation enginethe citation steps emailed to each author from the journal's own mailbox
  • JATS XMLmachine-readable JATS per article
  • Duplicate articlesthe same paper published twice — you choose which copy stays

For authors & researchers

Free to use. Nothing you check is shared with the journal.

For institutions, sponsors & DOI operators

Smart Scholars

Mon–Sat, 10:00–19:00 IST. The Ask AI button on every page answers about our services at any hour.

News

Policies

What we can register a DOI for

20 kinds of record, one account, one place. Every one gets a DOI that resolves, metadata that indexes read, and a record that stays correct afterwards.

Journals

  • Journal articles
  • Journal titles
  • Pending publications
  • Peer reviews
  • Preprints & posted content

Books & conferences

  • Books
  • Book chapters
  • Book series
  • Book sets
  • Conference proceedings
  • Proceedings series
  • Conference papers

Other research output

  • Theses & dissertations
  • Reports & working papers
  • Report series
  • Standards
  • Databases
  • Datasets
  • Figures, tables & supplements

Funding

  • Grants & funding awards

Elsewhere

The same company, in the places our publishers already read.
Add Smart Scholars as a preferred source on GoogleSee more of our newsroom in Google’s Top Stories.
Smart Scholars · Every service on one pageNewsroom posts CC BY 4.0 · DOI metadata CC0 · everything else ©Data from OpenAlex (openalex.org), CC0 · Crossref · ISSN Portal · DOAJContact
WhatsApp