Corpus ID: 209405147

DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog

@article{Chen2019DMRMAD,
  title={DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog},
  author={Feilong Chen and Fandong Meng and Jiaming Xu and Peng Li and Bo Xu and Jie Zhou},
  journal={ArXiv},
  year={2019},
  volume={abs/1912.08360}
}
  • Feilong Chen, Fandong Meng, +3 authors Jie Zhou
  • Published in AAAI 2019
  • Computer Science
  • Visual Dialog is a vision-language task that requires an AI agent to engage in a conversation with humans grounded in an image. It remains a challenging task since it requires the agent to fully understand a given question before making an appropriate response not only from the textual dialog history, but also from the visually-grounded information. While previous models typically leverage single-hop reasoning or single-channel reasoning to deal with this complex multimodal reasoning task… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES

    Visual Dialog

    VIEW 15 EXCERPTS
    HIGHLY INFLUENTIAL

    MUREL: Multimodal Relational Reasoning for Visual Question Answering

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Recursive Visual Attention in Visual Dialog

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Are You Talking to Me? Reasoned Visual Dialog Generation Through Adversarial Learning

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL