Automatic Understanding of Image and Video Advertisements

  title={Automatic Understanding of Image and Video Advertisements},
  author={Zaeem Hussain and Mingda Zhang and X. Zhang and Keren Ye and C. Thomas and Zuha Agha and Nathan Ong and Adriana Kovashka},
  journal={2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Zaeem Hussain, Mingda Zhang, +5 authors Adriana Kovashka
  • Published 2017
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • There is more to images than their objective physical content: for example, advertisements are created to persuade a viewer to take a certain action. We propose the novel problem of automatic advertisement understanding. To enable research on this problem, we create two datasets: an image dataset of 64,832 image ads, and a video dataset of 3,477 ads. Our data contains rich annotations encompassing the topic and sentiment of the ads, questions and answers describing what actions the viewer is… CONTINUE READING
    58 Citations

    Figures, Tables, and Topics from this paper.

    Interpreting the Rhetoric of Visual Advertisements.
    • 2
    • PDF
    Content-based Effectiveness Prediction of Video Advertisements
    • 2
    • PDF
    Content-Based Effectiveness Prediction of Video Advertisements
    Automatic synthesis of advertising images according to a specified style
    Symbolic VQA on Visual Advertisements with SymViSe Networks
    • 1
    • PDF
    Look, Read and Feel: Benchmarking Ads Understanding with Multimodal Multitask Learning
    • 2
    • Highly Influenced
    • PDF
    Story Understanding in Video Advertisements
    • 4
    • PDF
    Persuasive Faces: Generating Faces in Advertisements
    • 3
    • PDF
    Learning Subjective Attributes of Images from Auxiliary Sources
    • 1
    • PDF


    ImageSense: Towards contextual image advertising
    • 32
    Visual Persuasion: Inferring Communicative Intents of Images
    • 57
    • PDF
    Every Picture Tells a Story: Generating Sentences from Images
    • 837
    • PDF
    Affective image classification using features inspired by psychology and art theory
    • 544
    • PDF
    Recognizing Image Style
    • 307
    • PDF
    Visual appearance of display ads and its effect on click through rate
    • 16
    Predicting Ad Liking and Purchase Intent: Large-Scale Analysis of Facial Responses to Ads
    • 75
    • PDF
    Show and tell: A neural image caption generator
    • 3,523
    • PDF
    CAVVA: Computational Affective Video-in-Video Advertising
    • 46
    • PDF
    WhittleSearch: Interactive Image Search with Relative Attribute Feedback
    • 66
    • PDF