• Login
    View Item 
    •   Home
    • Research
    • Preprints
    • View Item
    •   Home
    • Research
    • Preprints
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of KAUSTCommunitiesIssue DateSubmit DateThis CollectionIssue DateSubmit Date

    My Account

    Login

    Quick Links

    Open Access PolicyORCID LibguideTheses and Dissertations LibguideSubmit an Item

    Statistics

    Display statistics

    It is Okay to Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    2204.07660 (1).pdf
    Size:
    6.823Mb
    Format:
    PDF
    Description:
    Preprint
    Download
    Type
    Preprint
    Authors
    Mohamed, Youssef
    Khan, Faizan Farooq
    Haydarov, Kilichbek cc
    Elhoseiny, Mohamed cc
    KAUST Department
    Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division
    KAUST Grant Number
    BAS/1/1685-01-01
    Date
    2022-04-15
    Permanent link to this record
    http://hdl.handle.net/10754/676618
    
    Metadata
    Show full item record
    Abstract
    Datasets that capture the connection between vision, language, and affection are limited, causing a lack of understanding of the emotional aspect of human intelligence. As a step in this direction, the ArtEmis dataset was recently introduced as a large-scale dataset of emotional reactions to images along with language explanations of these chosen emotions. We observed a significant emotional bias towards instance-rich emotions, making trained neural speakers less accurate in describing under-represented emotions. We show that collecting new data, in the same way, is not effective in mitigating this emotional bias. To remedy this problem, we propose a contrastive data collection approach to balance ArtEmis with a new complementary dataset such that a pair of similar images have contrasting emotions (one positive and one negative). We collected 260,533 instances using the proposed method, we combine them with ArtEmis, creating a second iteration of the dataset. The new combined dataset, dubbed ArtEmis v2.0, has a balanced distribution of emotions with explanations revealing more fine details in the associated painting. Our experiments show that neural speakers trained on the new dataset improve CIDEr and METEOR evaluation metrics by 20% and 7%, respectively, compared to the biased dataset. Finally, we also show that the performance per emotion of neural speakers is improved across all the emotion categories, significantly on under-represented emotions.
    Sponsors
    Supported by KAUST, under Award No. BAS/1/1685-01-01
    Publisher
    arXiv
    arXiv
    2204.07660
    Additional Links
    https://arxiv.org/pdf/2204.07660.pdf
    Collections
    Preprints; Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division

    entitlement

     
    DSpace software copyright © 2002-2022  DuraSpace
    Quick Guide | Contact Us | KAUST University Library
    Open Repository is a service hosted by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items. For anonymous users the allowed maximum amount is 50 search results.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.