Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch
2018 24th International Conference on Pattern Recognition (ICPR)(2018)
摘要
In this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query. A cross-modal deep network architecture is formulated to jointly model the sketch and text input modalities as well as the the image output modality, learning a common embedding between text and images and between sketches and images. In addition, an attention model is used to selectively focus the attention on the different objects of the image, allowing for retrieval with multiple objects in the query. Experiments show that the proposed method performs the best in both single and multiple object image retrieval in standard datasets.
更多查看译文
关键词
cross-modal deep network architecture,image output modality,image retrieval system,learning cross-modal deep embeddings
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络