16 papers posted out of 55 total in the cs.CV category on arXiv.org and that concludes the reading of the papers for another week!

See y'all next week 🙂

#AI #CV #NewPapers #DeepLearning #MachineLearning

@f Impressive! Do you keep notes or compile some sort of indexing or ranking of the papers you read? Is Mastodon your #notebook? ;-)

#reading #research #ComputerVision #AI #GenerativeArt

@f just realized your Toot stream is like a mini paperswithcode.com page.

@hobs Don’t know if you want all the details (and this kind of evolved over time) but I originally created a system which would get the RSS feed for the cs.CV category on arXiv and use ML to summarize it for me.

But I didn’t like the summaries since they didn’t really tell me much 😛 So, I modified the system to download the PDF papers and to give me an overview of the papers each day. From that, I went to adding a form to the paper view so that I can post a summary and a page screen grab to Mastodon.

The posting system kind of fell by the wayside (I post manually now) due to various issues, but I also added a system which tracks the papers I skip and the ones I post about so that I can track things. That’s where it stands since I now post daily about new papers in the cs.CV category since some people seem to find that useful 🙂

@hobs Yep, most of my posts tend to be either boost, or papers for the day that I found interesting 🙂 I do warn people about this in my profile page but most people just see one or two papers I’ve posted about and assume that they were my papers …

@f I love it!

@f very very cool. Seems like it a great way to gamify your brain training and keep up with the latest cs.cv trends

@f one last question. Is any time f the software for you arxiv reading list tooter open source? I would love to use it for myself and maybe contribute and recruit learners in my NLP and CS circle.

#NLP #VirtualAssistant #Summarizer #FOSS

@hobs The original code that did the summarization is on GitHub:

https://github.com/FahimF/summarizer/

I don’t believe I updated the repo with the later code which added the Mastodon posting and stats and stuff to it though since that didn’t gel with the original #MachineLearning approach 🙂 But if you are interested, I can send you the latest source as a ZIP file?

Or I guess I should set up a separate repo if you are interested in contributing to the code. I’ve kind of hit all my targets for features (except for a stats screen and the ability to view old papers … but too busy with Mastodon clients at the moment to get that done). Let me know …

@f Thank you! I'll dig into the summarizer and start there and once I've got my head around in it, maybe ask for the zip for the tooter.