Interactive Attention AI to translate low light photos to captions for night scene understanding in women safety

arxiv(2022)

引用 0|浏览6
暂无评分
摘要
There is amazing progress in Deep Learning based models for Image captioning and Low Light image enhancement. For the first time in literature, this paper develops a Deep Learning model that translates night scenes to sentences, opening new possibilities for AI applications in the safety of visually impaired women. Inspired by Image Captioning and Visual Question Answering, a novel Interactive Image Captioning is developed. A user can make the AI focus on any chosen person of interest by influencing the attention scoring. Attention context vectors are computed from CNN feature vectors and user-provided start word. The Encoder-Attention-Decoder neural network learns to produce captions from low brightness images. This paper demonstrates how women safety can be enabled by researching a novel AI capability in the Interactive Vision-Language model for perception of the environment in the night.
更多
查看译文
关键词
night scene understanding,captions,attention,low light photos
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要