2021/02/05 by Hong Chen, Yifei Huang, Chen, Hong +5 · 2 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Artificial intelligence #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #FOS: Computer and information sciences #Graph #Image (mathematics) #Information retrieval #Machine learning #Margin (machine learning) #Multimodal Machine Learning Applications #Narrative #Natural language processing #Relevance (law) #Selection (genetic algorithm) #Sequence (biology) #Set (abstract data type) #Storytelling #Task (project management) #Theoretical computer science #Video Analysis and Summarization #cs.CL #cs.CV
paper · pdf · doi:10.48550/arxiv.2102.02963
Accepted by AAAI2021
arxiv created 2021/02/05 · openalex publication_date 2021/02/05 · arxiv updated 2021/02/08 · openalex created_date 2021/07/05 · openalex updated_date 2026/07/28
Visual storytelling is a task of generating relevant and interesting stories for given image sequences. In this work we aim at increasing the diversity of the generated stories while preserving the informative content from the images. We propose to foster the diversity and informativeness of a generated story by using a concept selection module that suggests a set of concept candidates. Then, we utilize a large scale pre-trained model to convert concepts and images into full stories. To enrich the candidate concepts, a commonsense knowledge graph is created for each image sequence from which the concept candidates are proposed. To obtain appropriate concepts from the graph, we propose two novel modules that consider the correlation among candidate concepts and the image-concept correlation. Extensive automatic and human evaluation results demonstrate that our model can produce reasonable concepts. This enables our model to outperform the previous models by a large margin on the diversity and informativeness of the story, while retaining the relevance of the story to the image sequence.