Name
Abstract | ||
|---|---|---|
Recent captioning models are limited in their ability to describe concepts unseen in paired image-sentence pairs. This study presents a framework of multi-task learning for describing novel words not present in existing image-captioning datasets. The authors' framework takes advantage of external sources-labelled images from image classification datasets, and semantic knowledge extracted from the ... |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1049/iet-cvi.2018.5005 | IET Computer Vision |
Keywords | Field | DocType |
computer vision,image classification,image retrieval,image segmentation,knowledge acquisition,learning (artificial intelligence),natural language processing,text analysis | Semantic memory,Closed captioning,Multi-task learning,Pattern recognition,Inference,Natural language processing,Artificial intelligence,Contextual image classification,Language model,Mathematics | Journal |
Volume | Issue | ISSN |
13 | 3 | 1751-9632 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 | ||