Audio
Vector-Quantized Contrastive Predictive Coding for Template-based Music Generation
https://sonycslparis.github.io/vqcpc-bach/
https://arxiv.org/pdf/2004.10120.pdf
https://sonycslparis.github.io/vqcpc-bach/
https://arxiv.org/pdf/2004.10120.pdf
Combinatorial 3D Shape Generation
via Sequential Assembly
https://arxiv.org/pdf/2004.07414.pdf
https://arxiv.org/abs/2004.07414
via Sequential Assembly
https://arxiv.org/pdf/2004.07414.pdf
https://arxiv.org/abs/2004.07414
This media is not supported in your browser
VIEW IN TELEGRAM
Exploring Evolutionary Meta-Learning in Robotics
https://ai.googleblog.com/2020/04/exploring-evolutionary-meta-learning-in.html
https://ai.googleblog.com/2020/04/exploring-evolutionary-meta-learning-in.html
Stanford's CS229 2018 course is finally on YouTube
https://www.youtube.com/playlist?list=PLoROMvodv4rMiGQp3WXShtMGgzqpfVfbU
https://www.youtube.com/playlist?list=PLoROMvodv4rMiGQp3WXShtMGgzqpfVfbU
This media is not supported in your browser
VIEW IN TELEGRAM
AvatarMe
Realistically Renderable 3D Facial Reconstruction "in-the-wild"
https://github.com/lattas/AvatarMe
Realistically Renderable 3D Facial Reconstruction "in-the-wild"
https://github.com/lattas/AvatarMe
Computers Do Not Make Art, People Do
https://cacm.acm.org/magazines/2020/5/244330-computers-do-not-make-art-people-do/fulltext
https://cacm.acm.org/magazines/2020/5/244330-computers-do-not-make-art-people-do/fulltext
This media is not supported in your browser
VIEW IN TELEGRAM
Single-View View Synthesis with Multiplane Images
pdf: https://arxiv.org/pdf/2004.11364.pdf
abs: https://arxiv.org/abs/2004.11364
project page: https://single-view-mpi.github.io
video: https://youtu.be/XOYE-OkjVSI
pdf: https://arxiv.org/pdf/2004.11364.pdf
abs: https://arxiv.org/abs/2004.11364
project page: https://single-view-mpi.github.io
video: https://youtu.be/XOYE-OkjVSI
GANSynth: Making music with GANs
"In this post, we introduce GANSynth, a method for generating high-fidelity audio with Generative Adversarial Networks (GANs)..."
https://magenta.tensorflow.org/gansynth
"In this post, we introduce GANSynth, a method for generating high-fidelity audio with Generative Adversarial Networks (GANs)..."
https://magenta.tensorflow.org/gansynth
This media is not supported in your browser
VIEW IN TELEGRAM
AI and Architecture
This film was shot during the opening of the exhibition “AI and Architecture” at the @pavillonarsenal in Paris on 27 Feb.
This film was shot during the opening of the exhibition “AI and Architecture” at the @pavillonarsenal in Paris on 27 Feb.
The Super Duper NLP Repo
Database of over 100 Colab notebooks for the NLP developer to experiment with
https://notebooks.quantumstat.com/
Database of over 100 Colab notebooks for the NLP developer to experiment with
https://notebooks.quantumstat.com/
This media is not supported in your browser
VIEW IN TELEGRAM
New open source AI+AR demo ⚡️
Doodle face masks right from the browser with #TensorflowJS and #FaceMesh
Demo: https://cyrildiagne.github.io/ar-facedoodle
Code: https://github.com/cyrildiagne/ar-facedoodle
Doodle face masks right from the browser with #TensorflowJS and #FaceMesh
Demo: https://cyrildiagne.github.io/ar-facedoodle
Code: https://github.com/cyrildiagne/ar-facedoodle
Using Cell Phone Pictures of Sheet Music To Retrieve MIDI Passages
pdf: https://arxiv.org/pdf/2004.11724.pdf
abs: https://arxiv.org/abs/2004.11724
github: https://github.com/tjtsai/SheetMidiRetrieval
pdf: https://arxiv.org/pdf/2004.11724.pdf
abs: https://arxiv.org/abs/2004.11724
github: https://github.com/tjtsai/SheetMidiRetrieval
Architecture as a Graph
A Computational Approach
https://towardsdatascience.com/architecture-as-a-graph-6a835d46f918
A Computational Approach
https://towardsdatascience.com/architecture-as-a-graph-6a835d46f918
Face Detection, Recognition and Emotion Detection in 8 lines of code!
https://towardsdatascience.com/face-detection-recognition-and-emotion-detection-in-8-lines-of-code-b2ce32d4d5de
https://towardsdatascience.com/face-detection-recognition-and-emotion-detection-in-8-lines-of-code-b2ce32d4d5de
Medium
Face Detection, Recognition and Emotion Detection in 8 lines of code!
Doing cool things with data!