# machinicsituatedness cultural aiart ai european american generative creativecoding coronavirusdataset sarscov2 covid19 sars socialdistance anime superresolution romanlipksi creativeai lidar climatedatastore sst cds arknights ptilopsis 明日方舟 白面鸮 アークナイツ フィリオプシス dataviz visualization datavizsociety fires data

First up-the series where i explore the underpinnings of grounding the in a broader view of visual culture beyond and themes that generally emerge in due to most artists and datasets being from those regions.

1 4
2020-06-26

🦠Fight Covid-19 with BERT💊:
I am happy to announce the release of two BERTs further pre-trained on the CORD-19 dataset (https://t.co/ezDmtSieBX), namely ClinicalCovidBERT and BioCovidBERT. Both models are on . More info on the repo (https://t.co/bhldkv77pT)

19 53
2020-06-08

Abstract hands

GAN generated hands, trained on a dataset of images from subway-hands Instagram account

1 6
2020-05-10

Major update to our now featuring >2,200 molecular interactions involving proteins from / virus, and other members of the Coronaviridae family. Over 40 new publications added since our first release: https://t.co/CO7H2qGqIm

16 24
2020-05-05

Someone used the planimetrics dataset of sidewalk polygons to determine approximate widths and suggest where there is not enough room to maintain in NYC. Well done.

https://t.co/OiTbyUVSiZ

119 320
2020-04-22

Two points re these two images:
1. If you think all generative art looks the same, you're following the wrong generative artists.
2. Architecture matters! These were created with the exact same dataset, yet they have radically different styles.

3 11
2020-04-09

We've also put all the specimens that inspired the
collection into dataset
https://t.co/75DsS7uISm
Click 'go to resource' to view each insect.

5 15
2020-04-03

I have trained custom DenseNet like lightweight model the increases the size of image by the factor of 2. I trained my model on an anime episode and used it on faces dataset. Here is comparison between bilinear interpolation and my super-resolution.

5 12
2020-03-24

Our article on and , AI artists using their own paintings and drawings as datasets, is finally up on 🤖🎨

Written together with Alex Estorick

Read it here: https://t.co/1P6bUJfMIm

16 41
2020-03-18

Free structured template for radiologists reporting suspected CT scans courtesy of

With widespread use of this template we could create a labelled dataset for further research.

https://t.co/b82WV3d8ei

62 112
2020-03-16

Two new datasets now avail from OpenTopography: Palmerston North, Manawatu-Whanganui, NZ 2018; Christchurch & Ashley River, Canterbury, NZ 2018 - 1100 sq km of data: https://t.co/Gjfy0DIZiT 📷 1: wind turbines in motion; 📷 2: lidar intensity, Waimakariri River

12 37
2020-03-10

IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning. https://t.co/Eyb6z2mArd

2 4
2020-03-10

Daily sea surface temperatures from the Group for High Resolution Sea Surface Temperature () for 1981-2016 are now available in the This dataset was produced by the Climate Change Initiative team.

➡️https://t.co/qcbEnKKq0K

26 49
2020-03-03

Currently working on a sketch coloriser using Deoldify, using Danbooru dataset. Current results. pretty good so far!

4 15
2020-02-22

IBM decided to use a mathematical approach to quantifying “diversity” and “evenness,” so that a consistent measure of evenness exists throughout the dataset for every feature quantified.

0 0
2020-02-14

We have just published WFDE5, a bias-adjusted ERA5 reanalysis dataset. It was developed solely within our Toolbox!

WFDE5 will contribute to ISIMIP to adjust GCMs & to evaluate & drive a wide range of impact models.

Try for yourself➡️https://t.co/bqIh5VIUaK

55 96
2020-02-12

DiverseDepth predicts depth in a broader range of scenes, with more detail, than most depth models do in their best dataset. So they made a harder dataset.

DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data

abs: https://t.co/wvy4FOzNsR

15 55
2020-02-09

白面鸮头像生成器。 🦉
StyleGAN2の フィリオプシス画像生成
StyleGan2 finetune test。

It's hard to find a 4 GPU machine to run the algorithm：3。
Thx 2 for u dataset ，and anime portraits by 。

11 43
2020-01-20

Some of the diversity in MUNIT samples (because of the dataset I use, some end up slightly blurry—not shown here)

0 1
2020-01-13

For my End of Decade Challenge, given that there is an increasing number of fires lately, I decided to visualize fires based on NASA's FIRMS data, focusing on MODIS's active fire dataset: https://t.co/W8OQTt6bRx

3 26
2020-01-05