iCap: Interactive Image Captioning with Predictive Text

  title={iCap: Interactive Image Captioning with Predictive Text},
  author={Zhengxiong Jia and Xirong Li},
  journal={Proceedings of the 2020 International Conference on Multimedia Retrieval},
  • Zhengxiong Jia, Xirong Li
  • Published 2020
  • Computer Science
  • Proceedings of the 2020 International Conference on Multimedia Retrieval
  • In this paper we study a brand new topic of interactive image captioning with human in the loop. Different from automated image captioning where a given test image is the sole input in the inference stage, we have access to both the test image and a sequence of (incomplete) user-input sentences in the interactive scenario. We formulate the problem as Visually Conditioned Sentence Completion (VCSC). For VCSC, we propose ABD-Cap, asynchronous bidirectional decoding for image caption completion… CONTINUE READING

    Figures, Tables, and Topics from this paper.


    Show and tell: A neural image caption generator
    • 3,523
    • Highly Influential
    • PDF
    Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
    • 39
    • Highly Influential
    • PDF
    Long Short-Term Memory
    • 32,962
    • Highly Influential
    • PDF
    Binary codes capable of correcting deletions, insertions, and reversals
    • 9,629
    • Highly Influential
    E‚ective Approaches to AŠentionbased Neural Machine Translation
    • 2015
    Microso‰ COCO captions: Data collection and evaluation
    • 2015