@article{modellingvisualsemanticsviaimage,
  title = {Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection},
  year = {2024},
  eprint = {2408.02595},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.02595v1},
}