TY  - CONF
AU  - Sounak Dey
AU  - Anjan Dutta
AU  - Suman Ghosh
AU  - Ernest Valveny
AU  - Josep Llados
AU  - Umapada Pal
A2  - ICPR
PY  - 2018//
TI  - Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch
BT  - 24th International Conference on Pattern Recognition
SP  - 916
EP  - 921
N2  - 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.
L1  - http://refbase.cvc.uab.es/files/DDG2018b.pdf
UR  - http://dx.doi.org/10.1109/ICPR.2018.8545452
N1  - DAG; 602.167; 602.168; 600.097; 600.084; 600.121; 600.129
ID  - Sounak Dey2018
ER  -