Image-guided Story Ending Generation
5 papers with code • 2 benchmarks • 2 datasets
Image-guided Story Ending Generation (IgSEG) aims to generate a story ending for a given multi-sentence story plot and an ending-related image.
Libraries
Use these libraries to find Image-guided Story Ending Generation models and implementationsMost implemented papers
Attention Is All You Need
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.
Effective Approaches to Attention-based Neural Machine Translation
Our ensemble model using different attention architectures has established a new state-of-the-art result in the WMT'15 English to German translation task with 25. 9 BLEU points, an improvement of 1. 0 BLEU points over the existing best system backed by NMT and an n-gram reranker.
Story Ending Generation with Incremental Encoding and Commonsense Knowledge
This task requires not only to understand the context clues which play an important role in planning the plot but also to handle implicit knowledge to make a reasonable, coherent story.
MMT: Image-guided Story Ending Generation with Multimodal Memory Transformer
Finally, a multimodal transformer decoder constructs attention among multimodal features to learn the story dependency and generates informative, reasonable, and coherent story endings.
A Survey on Interpretable Cross-modal Reasoning
In recent years, cross-modal reasoning (CMR), the process of understanding and reasoning across different modalities, has emerged as a pivotal area with applications spanning from multimedia analysis to healthcare diagnostics.