EMNLP 2017, one of the best conferences in NLP, will be hosted on September 7~11, 2017 in Copenhagen, Denmark. The list of accepted papers and best papers of EMNLP 2017 is available now at their official website. There are 1509 submissions this year, which is a 40% increase from last year, including 836 long papers and 582 short papers. Out of those only 323 are accepted, including 216 long papers at the acceptance rate of 25.8, and 107short papers at the acceptance rate of 18.4%.
There is a recent work published in
CVPR, which utilizes neural network to help you convert 2D images to 3D objects. It starts by learning how we project 3D objects to 2D images and based on that, we revert the process to recover the 3D objects from 2D images.
CB Insights has released their reports on Aritifical Intelligence. Here is the table of contents:
Scholars from Sandong University have developed a new methods for 3D construction: . The benefits of this method, compared with current optical based method is that, it is able to reconstruct the 3D strucutre of invisible parts, e.g., inner space, concave region.
Google has open sourced
deeplearn.js to have you run deep learning in your browser.
There is a paper from Fudan University, Tongji University and CMU on proposing a method of generating AI character facial images via neural network.
Recently I got a task of checking whether the excel has some some wrong data. There are some conditions where some columns must meet. Using the
Excel filtering or equation is cumbersome, as the condition can be very complex.