Big Visual Data Computing, Image Retrieval and Deep Learning, Smart Cropping, Aesthetic Scoring, Portrait Photography, Computer Vision and Pattern Recognition, Distributed and Parallel Systems, Network Security
Unbelievable and heartbreaking! Our role model since elementary school dies at 40! I still remember the days I was struggling to learn her book written for young math lovers to prepare for math Olympiad. She was ahead of us as a senior but she passed all the elevation steps very fast, and soon she became Stanford professor while she had a little girl.
Her milestone completed when she won Fields Medal in Math (the most prestigious award equivalent to Nobel prize). As a woman, her accomplishment is not only inspiring for all Iranians but also specially for all women in fundamental sciences. Definitely her work helps the other mathematicians in the field, but her humble character wasn’t self-explanatory.
Unfortunately her life was short but fruitful for all of us not only from scientific aspects but also other societal aspects as a public figure like Galois, Ramanujan, and Riemann. May she rest in peace.
ABSTRACT: Retrieving photography ideas corresponding to a given location facilitates the usage of smart cameras, where there is a high interest among amateurs and enthusiasts to take astonishing photos at anytime and in any location. Existing research captures some aesthetic techniques such as the rule of thirds, triangle, and perspectiveness, and retrieves useful feedbacks based on one technique. However, they are restricted to a particular technique and the retrieved results have room to improve as they can be limited to the quality of the query. There is a lack of a holistic framework to capture important aspects of a given scene and give a novice photographer informative feedback to take a better shot in his/her photography adventure. This work proposes an intelligent framework of portrait composition using our deep-learned models and image retrieval methods. A highly-rated web-crawled portrait dataset is exploited for retrieval purposes. Our framework detects and extracts ingredients of a given scene representing as a correlated hierarchical model. It then matches extracted semantics with the dataset of aesthetically composed photos to investigate a ranked list of photography ideas, and gradually optimizes the human pose and other artistic aspects of the composed scene supposed to be captured. The conducted user study demonstrates that our approach is more helpful than the other constructed feedback retrieval systems.