Posts
1408
Following
142
Followers
867
I'm a bit of an eclectic mess 🙂 I've been a programmer, journalist, editor, TV producer, and a few other things.

I'm currently working on my second novel which is complete, but is in the edit stage. I wrote my first novel over 20 years ago but then didn't write much till now.

I post about #Coding, #Flutter, #Writing, #Movies and #TV. I'll also talk about #Technology, #Gadgets, #MachineLearning, #DeepLearning and a few other things as the fancy strikes ...

Lived in: 🇱🇰🇸🇦🇺🇸🇳🇿🇸🇬🇲🇾🇦🇪🇫🇷🇪🇸🇵🇹🇶🇦🇨🇦
f

Fahim Farook

"Scalable Diffusion Models with Transformers. (arXiv:2212.09748v2 [cs.CV] UPDATED)" — Creating diffusion models that use transformers instead UNets.

Paper: http://arxiv.org/abs/2212.09748
Code: https://github.com/facebookresearch/DiT

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Diffusion models with transform…
0
0
1
f
repeated
jongranskog@sigmoid.social

Jonathan Granskog

A few photos from autumn. Thanks for all the kind comments about the winter photos. 😌

0
1
0
f
repeated
soundwarrior20@ravenation.club

sound warrior

Hi everyone, I'm a totally blind electronic musician. Looking for a audio, developer fluent in C++ d to help me with a very special open source project to assist blind people with electronic music production. If you can help me, or know anyone in your network who can please reach out and get at me. Thanks very much everyone :-) music :-)

1
6
0
f

Fahim Farook

"Collage Diffusion. (arXiv:2303.00262v1 [cs.CV])" — Creating harmonious and cohesive output images based on a text prompt and a collection of images as input.

Paper: http://arxiv.org/abs/2303.00262

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Collage Diffusion creates globa…
0
0
1
f

Fahim Farook

"PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing. (arXiv:2303.00137v1 [cs.CV])" — Generating realistic shadows and reflections using 2D images and deep learning techniques.

Paper: http://arxiv.org/abs/2303.00137

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
PixHt-Lab renders realistic ref…
0
0
0
f

Fahim Farook

"Magic: Multi Art Genre Intelligent Choreography Dataset and Network for 3D Dance Generation. (arXiv:2212.03741v3 [cs.CV] UPDATED)" — A choreography dataset and a network for generating 3D dance segments based on a music clip as input.

Paper: http://arxiv.org/abs/2212.03741

Note: v3 of the paper is currently not available in PDF form on arXiv.

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
A conceptual overview of Magic.…
0
1
0
f

Fahim Farook

A total of 116 papers in the cs.CV category on arXiv.org today — 82 new, 34 updated.

Away we go to read some more!

#AI #CV #NewPapers #DeepLearning #MachineLearning
0
0
0
f

Fahim Farook

Reply to
@at Being rather obsessive compulsive, I used to push myself to finish every book and every movie I started even if I didn’t like it after reading/watching for a bit. Took me a long time to wean myself away from that habit … It’s rather freeing once you do 😛
0
0
0
f

Fahim Farook

Reply to @AngelaPreston@toot.site
Depression, Self-Recrimination, Reframing
Show content
@AngelaPreston I know (or possibly know) how you must feel since I am hard on myself if I don’t get certain things done. And then I’ll keep thinking about it and getting ever more anxious since it’s just not done and I wanted it done.

I tell myself when this happens that it’s OK since other stuff will come up. It doesn’t always help, but beating yourself up over it doesn’t help either since that’s time wasted. So better to just get on with it and that’s what I generally do. Not very helpful, but it works for me, at least in terms of handling the short-term anxiety over not getting it done 🙂

Longer term, I generally forget about it since there’s always so much stuff to do 😛
1
0
1
f
repeated
eyeinhand@fosstodon.org

EyeInHand

Variation on the Lotus theme.

Little lilypads from a walk along the river.



0
1
0
f

Fahim Farook

Reply to @hue@sigmoid.social
@hue Unfortunately, people generally tend to take the easy way out. And they will also generally not bother to tell you their reasoning (which might have given you context) since that’s just too much work 😛

Based on what you said, I assumed you were not Iranian. So I did the same thing. We all do it in one form or another. The best we can hope for is to learn from it and possibly adjust our expectations? At least, that’s what I do since hoping that everybody else will change is too much to ask for 🙂
0
0
1
f

Fahim Farook

Reply to @hue@sigmoid.social
@hue That’s a different thing and understandable (in a way) 🙂 I’m a Sri Lankan and I’d prefer not to work with (most) Sri Lankans due to cultural issues which inevitably come up at some point or another, but if I simply said “I don’t want to work with Sri Lankans”, people might not get what I’m talking about …

So, just wondering if the people in question knew the history/backstory or not when they warned you?
1
0
1
f

Fahim Farook

Reply to @hue@sigmoid.social
@hue Pardon me for jumping into a conversation that might have been intended to be private, and do let me know if you’d rather not have my opinion 🙂 But without any context, when I see the words “I don’t like to work with Iranians”, I see it as a prejudiced statement …

Perhaps, there’s context behind it, but to classify a whole race as people you’d not want to work with, instead of individuals seems a bit strange to me. Would you feel OK if I said “I will not work with white people” or “I will not work with Americans”?

This might have been the reason for warning perhaps? Just my thoughts, (which is totally your prerogative to tell me not to bother you with 😛)

@at
1
0
0
f
repeated
hackerhorse@infosec.exchange

Rain

I give up.
I'm officially desperate.
If you need a security person you can get me at bargain basement cost because I'm gonna be super fucked here in a bit if I don't find SOMETHING.
I've been out of work 8 months.
I can't afford to keep going.

This is my resume
You tell me how I don't have a job yet

3
2
0
f

Fahim Farook

Despite the large number of new papers in the cs.CV category on arXiv.org today (136), I only boosted 5 papers out of the lot since those were the ones I found interesting 🙂

Reading done. On to other stuff!

#AI #CV #NewPapers #DeepLearning #MachineLearning
0
0
1
f
repeated
DriftlessRoots@scicomm.xyz

DriftlessRoots

This is why I let the dill go to seed. It's one of the food plants of Black Swallowtail caterpillars like this one from last summer. Currently it is in diapause out in the garage and will be released in the same garden this spring when it emerges.

2
2
0
f

Fahim Farook

"Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning. (arXiv:2302.14794v1 [cs.CV])" — Rather than using a frozen language model to communicate visual concepts, this method uses a meta -mapper to act as a bridge between large-scale visiona and language models.

Paper: http://arxiv.org/abs/2302.14794

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Multimodal few-shot meta-learni…
0
0
1
f

Fahim Farook

"TextIR: A Simple Framework for Text-based Editable Image Restoration. (arXiv:2302.14736v1 [cs.CV])" — Using text input to restore damaged images by specifying how to fill in the damage areas by way of text descriptions.

Paper: http://arxiv.org/abs/2302.14736

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Overview of image restoration r…
0
0
0
f

Fahim Farook

"Towards Enhanced Controllability of Diffusion Models. (arXiv:2302.14368v1 [cs.CV])" — Creating a diffusion model that is easier to edit/style based on input images by conditioning the model on a spatial content mask and a flattened style embedding.

Paper: http://arxiv.org/abs/2302.14368

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Comparison of the proposed mode…
0
0
0
f

Fahim Farook

"One-Shot Video Inpainting. (arXiv:2302.14362v1 [cs.CV])" — A method to inpaint videos where instead of having to provide masks for each frame, you only need to provide the object mask for the initial frame in the video sequence.

Paper: http://arxiv.org/abs/2302.14362

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too 🙂>>
Qualitative comparison between …
0
1
1
Show older
About The Farooks

Terms of Service

This is a placeholder, overwrite this by putting a file at 

$STATIC_DIR/static/terms-of-service.html

See the Static Directory docs for more info.