TY  - CONF
AU  - Mohammed Al Rawi
AU  - Ernest Valveny
A2  - ICCVW
PY  - 2019//
TI  - Compact and Efficient Multitask Learning in Vision, Language and Speech
BT  - IEEE International Conference on Computer Vision Workshops
SP  - 2933
EP  - 2942
N2  - Across-domain multitask learning is a challenging area of computer vision and machine learning due to the intra-similarities among class distributions. Addressing this problem to cope with the human cognition system by considering inter and intra-class categorization and recognition complicates the problem even further. We propose in this work an effective holistic and hierarchical learning by using a text embedding layer on top of a deep learning model. We also propose a novel sensory discriminator approach to resolve the collisions between different tasks and domains. We then train the model concurrently on textual sentiment analysis, speech recognition, image classification, action recognition from video, and handwriting word spotting of two different scripts (Arabic and English). The model we propose successfully learned different tasks across multiple domains.
UR  - https://ieeexplore.ieee.org/document/9022188
L1  - http://refbase.cvc.uab.es/files/RaV2019.pdf
UR  - http://dx.doi.org/10.1109/ICCVW.2019.00355
N1  - DAG; 600.121; 600.129
ID  - Mohammed Al Rawi2019
ER  -