—————— ConvNeXt ——————


Facebook propose ConvNeXt, a pure ConvNet model constructed entirely from standard ConvNet modules. ConvNeXt is accurate, efficient, scalable and very simple in design.

Github: https://github.com/facebookresearch/ConvNeXt

Paper: https://arxiv.org/pdf/2201.03545

Team
@data_enthusiasts
@OpenArchiveBooks

#crosspost

Recruiters, how much does a candidate's Kaggle profile matter while hiring?

For example if a guy is Kaggle Master, would that boost his chances of getting selected. I just wanna know if a Kaggle profile of a candidate matters or not. If yes then how much?

View the full redit post: https://redd.it/shsq5a


#DS #Kaggle

Team
@data_enthusiasts
@OpenArchiveBooks

📎 When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism

Github: https://github.com/microsoft/SPACH

Paper: https://arxiv.org/abs/2201.10801v1

Dataset: https://paperswithcode.com/dataset/coco

Team
@data_enthusiasts
@OpenArchiveBooks

Some helpful advice to Beginners

#beginners #advice


Team
@data_enthusiasts
@OpenArchiveBooks

📹 VRT: A Video Restoration Transformer

Github: https://github.com/jingyunliang/vrt

Paper: https://arxiv.org/abs/2201.12288

Dataset: https://paperswithcode.com/dataset/gopro

Team
@data_enthusiasts
@OpenArchiveBooks

P DeepETA: How Uber Predicts Arrival Times Using Deep Learning

Link to blog post

Geospatial data for deep learning seems to be difficult and often overlooked, but interest seems to be increasing. It's nice to see an attempt at a more modern, general-purpose ETA tool like this, especially the way they use geospatial embeddings and linear transformer.

Team
@data_enthusiasts
@OpenArchiveBooks

🎬 FILM: Frame Interpolation for Large Scene Motion

Github: https://github.com/google-research/frame-interpolation

Research Paper: https://arxiv.org/pdf/2202.04901.pdf

Video: https://www.youtube.com/watch?v=OAD-BieIjH4

Project: https://film-net.github.io/

Team
@data_enthusiasts
@OpenArchiveBooks

🗣 Facebook’s textless-lib: a Library for Textless Spoken Language Processing

Github: https://github.com/facebookresearch/textlesslib

Code examples: https://github.com/facebookresearch/textlesslib/tree/main/examples

Paper: https://arxiv.org/pdf/2202.07359v1

Dataset: https://paperswithcode.com/dataset/librispeech

Team
@data_enthusiasts
@OpenArchiveBooks

Graph Theory and Linear Algebra

Team
@data_enthusiasts
@OpenArchiveBooks

One-shot Affordance Detection

Github: https://github.com/lhc1224/OSAD_Net

Paper: https://arxiv.org/pdf/2202.12076v1

Dataset: https://paperswithcode.com/dataset/pad

Team
@data_enthusiasts
@OpenArchiveBooks

Detection of COVID-19 using multimodal data from a wearable device: results from the first TemPredict Study


• Some time ago in a different world one of the channel editors shared permmission to use data from sleep & activity tracker Oura Ring to develop an algorithm for COVID-19 prediction.

• Results of this study continue to arrive. Today team shared the second manuscript from the first TemPredict Study in Nature Scientific Reports. This manuscript details an algorithm designed to detect COVID-19 using data from the Oura Ring. Alogirthm publication: www.nature.com/articles/s41598-022-07314-0 

• The first publication from the first TemPredict Study will continue to be available online for you to access at any time, at this link: https://www.nature.com/articles/s41598-020-78355-6

• The first publication from the second TemPredict Study (correlations between data from the Oura Ring and data from a LabCorp antibody blood test) will also continue to be available online for you to access at any time, at this link: https://www.mdpi.com/2076-393X/10/2/264

That's the power of the international collaboration 💪

#oura #covid #biolearning #medical #health

Team
@data_enthusiasts
@OpenArchiveBooks