So, once I got the CoreData stuff out of the way, implementing List filtering for Tusker turned out to be very simple 🙂

Now, I can create multiple lists, add users I follow to those lists and then have the posts and boost by list members be filtered out from my home timline. I tell you, it feels great already 😀

There are a few gotchas — I have unread post counts implemented for the home timeline and that doesn’t take the filtered posts into account. So I have to fix that. And there is the possibility that replies to people on lists might still appear on the home timeline. But both of those should hopefully be easy to fix …

So, once all that is done and working fine, if anybody would like to try out this flavour of Tusker and you are on iOS/macOS let me know and I’ll put up build somewhere? TestFlight maybe?

#Swift #macOS #FediClient #Filtering

Some history from my state:

"Junius Groves and his wife Matilda were potato farmers near Edwardsville in Wyandotte County. The potatoes were shipped all over the country by rail and Union Pacific Railroad even put a spur line on the Groves farm to make it easier to load the produce. Junius became known as the “potato king of the world” because he grew more potatoes per acre than anyone else. He built a golf course for African-Americans and served as a trustee for Western University in Quindaro."
(source and more information)

And that’s it for today 🙂 A total of 8 papers boosted — 5 in the cs.CV category and 3 outside from 115 new and updated papers on arXiv.org today.

#AI #CV #NewPapers #DeepLearning #MachineLearning

"Learning 3D Photography Videos via Self-supervised Diffusion on Single Images. (arXiv:2302.10781v1 [cs.CV])" — Transforming static images into videos with additional effects using a diffusion model to handle the inpainting.

Paper: http://arxiv.org/abs/2302.10781

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
llustration of the proposed out…

"On Calibrating Diffusion Probabilistic Models. (arXiv:2302.10688v1 [cs.LG])" — Calibrating Diffusion Probabilistic Models (DPM) to reduce the score matching loss.

Paper: http://arxiv.org/abs/2302.10688
Code: https://github.com/thudzj/Calibrated-DPMs

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>

"Theoretical limits of Virtual Reality" — Exploring the question of whether it is possible to deceive the mind to the point of not being able to recognize whether the perceived reality is real or simulated.

Paper: https://arxiv.org/abs/2302.10190

#NewPaper #HumanComputerInteraction #VR #Simulation

"Diagnosis of Covid-19 Via Patient Breath Data Using Artificial Intelligence" — Using machine learning to detect COVID-19 based on breath analysis by detecting volatile organic compounds (VOC).

Paper: https://arxiv.org/abs/2302.10180

Note: I don’t know the accuracy of the medical theory behind this paper nor how practical it is. Please see the note about the paper on arXiv as well.

#AI #NewPaper #DeepLearning #MachineLearning

"Uncertainty-Aware Reward-based Deep Reinforcement Learning for Intent Analysis of Social Media Information" — Using deep learning techniques to identify the intent behind fake news.

Paper: https://arxiv.org/abs/2302.10195

#AI #NewPaper #DeepLearning #MachineLearning #Language

"RealFusion: 360{\deg} Reconstruction of Any Object from a Single Image. (arXiv:2302.10663v1 [cs.CV])" — Creating a 360-degree photographic model of an object from a single image of it by fitting a neural radiance field to the image.

Paper: http://arxiv.org/abs/2302.10663

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
RealFusion generates a full 360…

"Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels. (arXiv:2302.10586v1 [cs.CV])" — A three-stage training strategy for conditional image generation and classification in semi-supervised learning.

Paper: http://arxiv.org/abs/2302.10586

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
An overview of DPT. First, a (s…

"A Comparative Analysis of CNN-Based Pretrained Models for the Detection and Prediction of Monkeypox. (arXiv:2302.10277v1 [cs.CV])" — Using Convolutional Neural Networks (CNN) to detect monkeypox since it's difficult to diagnose early due to its similarity to other diseases like chickenpox and measles.

Paper: http://arxiv.org/abs/2302.10277

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Chart showing confirmed monkeyp…

A total of 115 papers in the cs.CV category on arXiv.org today — 95 new, 20 updated.

Looks as if this week’s going to be lots of papers all the way? 🙂

#AI #CV #NewPapers #DeepLearning #MachineLearning

Lost about several hours messing around with CoreData yesterday trying to get the List filtering working for Tusker. I think this is why I prefer my own SQLite abstraction layer since then I know what the heck is going on ...

CoreData just gives cryptic error messages and while you’ll probably know what is going on if you work with CoreData all the time, for somebody who messes with it occasionally, it’s all a bit too much.

I was on the verge of adding my changes as JSON files since my changes wouldn’t have added a lot of data when I finally figured out what was going on with CoreData. Whew!

Now I need to actually implement the list filtering and we might be done?

#Swift #CoreData #Apple #FediLists

Open source maintainership is about to become a whole lot more annoying.

I've been trying out leonardo.ai with a bunch of new prompts since yesterday.

The following are the best results for: "Burning the cradle at both ends" ... and no "cradle" wasn't a typo, that was the prompt I wanted 😛

#AIArt #StableDiffusion #DeepLearning #MachineLearning #CV #AI
Prompt: “Burning the cradle at …
Prompt: “Burning the cradle at …
Prompt: “Burning the cradle at …
Prompt: “Burning the cradle at …

Boosted 5 papers in the cs.CV category out of a total of 91 new (or updated) papers on arXiv.org today.

The reading of the papers is done for today and off I go to do other things 🙂

#AI #CV #NewPapers #DeepLearning #MachineLearning

I’ve been talking about trying to create a smaller, quieter home timeline and yet be able to follow interesting accounts with a large number of posts/boosts. I tried unfollowing some of these accounts and putting them into a list and, as should have been obvious, it seemed to fail since you do need to be following the accounts.

And yet, my list kept showing new posts but not at the volume that I would have expected from the users I added to the list. And only posts from some users.

I was puzzled about this and was wondering what was going on. I think I might have an answer — it looks as if you don’t need to be following the user to get their posts *as long as you follow somebody else who follows that user*. If the user and you have nobody else in common, then you won’t see any of their posts in your list.

So still not the ideal outcome, but maybe a workaround (albeit one which can have privacy implications) in case you want to go that route, I guess?

I think I’ll simply go back to my original idea of implementing homeline filtering for list members. But that’ll take a bit longer given the stuff I’m working on at the moment 😞

#Mastodon #Fediverse #Lists #Filtering

"A Picture May Be Worth a Thousand Lives: An Interpretable Artificial Intelligence Strategy for Predictions of Suicide Risk from Social Media Images. (arXiv:2302.09488v1 [cs.AI])" — Predicting suicide risk by evaluating non-verbal inputs such as social media images.

Paper: http://arxiv.org/abs/2302.09488

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>

"Vulnerability analysis of captcha using Deep learning. (arXiv:2302.09389v1 [cs.CR])" — Using a Convolutional Neural Network (CNN) model to predict text-based CAPTCHAs to examine the flaws inherent in the system and to create more resilient CAPTCHAs.

Paper: http://arxiv.org/abs/2302.09389

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Examples of different alphanume…

"Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension. (arXiv:2302.09301v1 [cs.CL])" — An investigation into the basic geometric properties induced by prompts in Stable Diffusion and how this impact depends on the layer being considered.

Paper: http://arxiv.org/abs/2302.09301

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
The output of the model at the …