This week in AI & Machine Learning: automatic animation with computer vision, human-centered AI, Hugging Face acquires Gradio, measuring AI model uncertainty, how AI ethics affects your business, and more!
My Top AI Highlight:
Automatic Animation on Drawings with Computer Vision
Meta AI has shared a fascinating way to generate character animation from a single unique drawing.
The demonstration here shows how it can turn drawings from a child into fun entertainment, but you can imagine how this technique could be used to help anyone create interactive art for digital experiences, such as augmented and virtual reality.
Does your child love to draw? Ever wished that their characters could “come to life” and move around the page? Using AI, we’ve developed automatic animation that can bring children’s one-of-a-kind characters to life! Learn more and try it out here: https://t.co/uKDsSHI60H pic.twitter.com/K9KV942dXa— Meta AI (@MetaAI) December 16, 2021
Your content goes here. Edit or remove this text inline or in the module Content settings. You can also style every aspect of this content in the module Design settings and even apply custom CSS to this text in the module Advanced settings.
Read more about how Meta used computer vision and artificial intelligence to create these animations for these unique characters here.
🤖 Artificial Intelligence News:
- Human-centered AI can improve the patient experience
- Univ. of Washington AI protein folding discovery wins ‘Breakthrough of the Year’ award from Science
- Characters for good, created by artificial intelligence
- Artificial intelligence can create better lightning forecasts
- Audiobooks — An Under-Served Market For Artificial Intelligence Voice Text And Voice Solutions
- 3 big problems with datasets in AI and machine learning
- Machine learning speeds up vehicle routing
🛠️ Developer Tools & Education:
- Hugging Face Acquires Gradio
- Meta releases Bean Machine to help measure AI model uncertainty
- GAN Training Challenges: DCGAN for Color Images
- Generating Motion Capture Animation Without Hardware or Motion Data
- A Scalable Approach for Partially Local Federated Learning
- Training Machine Learning Models More Efficiently with Dataset Distillation
📅 Upcoming Online AI & Data Science Events:
- Intro to Computer Vision: Building Object Detection Models and Datasets (Jan 12–5:30 pm PST)
- Architectures of DataOps (Jan 18–5:00 pm PST)
- Maximizing Model Accuracy With Data-centric AI Practices (feb 8–5:00pm)
🎤 Interesting Podcasts & Interviews:
- How AI Ethics Affects Your Business
- AI Pioneer Kai-Fu Lee Discusses His New Work of Fiction
- Optimization, Machine Learning and Intelligent Experimentation with Michael McCourt
- Jupyter and the Evolution of ML Tooling with Brian Granger
- Data Science at the Command Line
- OpenAI and Hugging Face tooling
📄 Notable Research Papers:
- HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
- Human Hands as Probes for Interactive Object Understanding
- RegionCLIP: Region-based Language-Image Pretraining
🐘 About the Author & Plainsight:
- Sage Elliott is a Developer Evangelist at Plainsight & passionate about making AI more approachable. Connect with Sage on Twitter or LinkedIn.
- Plainsight’s vision AI platform streamlines the end-to-end machine learning process. From data annotation through deployment, customers quickly create and successfully operationalize their own vision AI applications to solve highly diverse business challenges. Join the conversation on Slack.