64 research outputs found
Facelift: Serialized Streetview image dataset with beauty ratings
No full textThe caffe models are trained on Street view images. These images are serialized into lmdb format for caffe.
This dataset contains the train and validation lmdb sets, with the images and their respective beauty ratings
Facelift Urban Scene Generator
No full textThis dataset contains the Urban scene generator trained on the Augmented streeview dataset. The model is trained in Caffe. The Model can be tested with the demo code seen here : https://github.com/sagarjoglekar/FaceliftGenerator
The dataset contains the caffemodel weights and the generator description in the prototext file
Replication Data for: Happy Singlehoods: Neighborhoods of the creative solo class
No full textThis dataset contains all the files required to replicate the plots and figures from the paper titled: Happy Singlehoods: Neighborhoods of the creative solo class.
The dataset contains three key files.
1) creative_solo.shp: Shapefile that contains information at ward level about creative solo scores, predicted solo population fraction among geo data required to plot these wards.
2) creative_solo.csv: If maps are not required, you can find all the necessary information in the csv format
3) ward_data.csv: Contains all the metrics used to compute creative solo scores at ward level
Facelift: Serialized Streetview image dataset with beauty ratings
No full textThe caffe models are trained on Street view images. These images are serialized into lmdb format for caffe.
This dataset contains the train and validation lmdb sets, with the images and their respective beauty ratings
Facelift Beauty Classifier (Binary)
No full textThis dataset contains the Beauty classifier models, trained in Caffe. The set contains the prototext definition, binaryproto mean image and the actual model weights
Facelift Beauty Classifier (Binary)
No full textThis dataset contains the Beauty classifier models, trained in Caffe. The set contains the prototext definition, binaryproto mean image and the actual model weights
Replication Data for: The Geography of Pain: Potential Savings for Opioid Prescribing in England
No full textThis dataset contains the data files required to replicate the plots and maps from the paper "The Geography of Pain: Potential Savings for Opioid Prescribing in England
Facelift Urban Scene Generator
No full textThis dataset contains the Urban scene generator trained on the Augmented streeview dataset. The model is trained in Caffe. The Model can be tested with the demo code seen here : https://github.com/sagarjoglekar/FaceliftGenerator
The dataset contains the caffemodel weights and the generator description in the prototext file
KAIROS
No full textSuccessful meetings create a safe environment for contribution; one that attendees feel engaged in and part of. Previous research has shown that meetings success depends not only on execution, but also on whether attendees feel psychologically safe. While this aspect is, to a great extent, partly observable through certain body cues during in-person meetings, they are often overlooked in virtual ones. To partly fix that, we developed "Kairos"-a system for multi-modal monitoring of virtual meetings that captures subtle body cues. We deployed it in 55 real-world corporate meetings and, upon six metrics for body cues, we built a model to predict a meeting's self-reported success, achieving an AUC as high as 79%. We found that certain body cues were more predictive of a meeting's success (defined as a linear combination of execution and psychological safety) than others (head movements, for example, were twice as predictive as hand movements), not least because they captured three typical meeting phases (its initiation, collective discussions, and turning points) whose presence (or absence) greatly mattered for success
Jane Jacobs in the Sky: Predicting Urban Vitality with Open Satellite Data
No full textThe presence of people in an urban area throughout the day-often called 'urban vitality'-is one of the qualities world-class cities aspire to the most, yet it is one of the hardest to achieve. Back in the 1970s, Jane Jacobs theorized urban vitality and found that there are four conditions required for the promotion of life in cities: diversity of land use, small block sizes, the mix of economic activities, and concentration of people. To build proxies for those four conditions and ultimately test Jane Jacobs's theory at scale, researchers have had to collect both private and public data from a variety of sources, and that took decades. Here we propose the use of one single source of data, which happens to be publicly available: Sentinel-2 satellite imagery. In particular, since the first two conditions (diversity of land use and small block sizes) are visible to the naked eye from satellite imagery, we tested whether we could automatically extract them with a state-of-the-art deep-learning framework and whether, in the end, the extracted features could predict vitality. In six Italian cities for which we had call data records, we found that our framework is able to explain on average 55% of the variance in urban vitality extracted from those records
- …
