Posts
1589
Following
139
Followers
883
I'm a bit of an eclectic mess πŸ™‚ 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: πŸ‡±πŸ‡°πŸ‡ΈπŸ‡¦πŸ‡ΊπŸ‡ΈπŸ‡³πŸ‡ΏπŸ‡ΈπŸ‡¬πŸ‡²πŸ‡ΎπŸ‡¦πŸ‡ͺπŸ‡«πŸ‡·πŸ‡ͺπŸ‡ΈπŸ‡΅πŸ‡ΉπŸ‡ΆπŸ‡¦πŸ‡¨πŸ‡¦

1, 1844
Eduard Strasburger, - & , is born.

In 1882, he coined the terms β€œβ€ and β€œ.”

Six years later, he was the first person to observe , and he did it using the glorious imperialis or the .

What a gorgeous subject for such an important discovery!

0
2
0

My Keith Hammett dahlia Protegee has just started flowering, and it's absolutely stunning. The bees are all over the flowers.

0
2
0

Every day I transfer one of my digital illustrations into coloured pencil drawings. This time:

Dr. Blue Eye ging nie ohne FrΓΌhstΓΌck ins Institut /
Dr Blue Eye never went to the Institute without breakfast

1
2
0

Leon Derczynski πŸ”οΈβœπŸ»πŸŒ²β˜€οΈ

Hi there πŸ‘‹ I'm a prof at ITU currently at in .

πŸ”­ My research is on and . Specifically:

πŸ›‘οΈ Online harms: , , etc
🌱 machine learning: efficient models, friendly ML, efficiency

I guess I try to keep my profile here dry & work-related, but reality might creep in here and there :)

5
1
0

An abandoned house in Portugal. I venture up the creaking spiral staircase into the attic. The corridor ahead isn't too photogenic, I then back around to face then stairs. A beautiful pattern of radiating shadows cast by the balustrade πŸ–€

0
4
1

Some fun for your Tuesday! I present a trio of sheepy bums! I saw these three fuzz butts while hiking to Kvernafoss waterfall in Iceland. I couldn't resist snapping a pic! 😁 πŸ‘

Prints and products available!
https://kristia-adams.pixels.com/featured/trio-of-icelandic-sheepy-bums-kristia-adams.html

0
7
1

columnifera, upright prairie coneflower.

0
3
1

π•Ώπ–—π–Žπ–‹π–‘π–Žπ–“π–Œπ•Ώπ–—π–Šπ–Šβ“

A chest in an old abandoned attic full of strange things from the Future
Midjourney 4 AI Art

0
1
0

π•Ώπ–—π–Žπ–‹π–‘π–Žπ–“π–Œπ•Ώπ–—π–Šπ–Šβ“

Starship Scorpion πŸ¦‚
Midjourney 4 AI Art

0
1
0

π•Ώπ–—π–Žπ–‹π–‘π–Žπ–“π–Œπ•Ώπ–—π–Šπ–Šβ“

Interior Mars habitat designed by Leonardo Da Vinci
Midjourney 4 AI Art
Β Β  ​

0
1
0

π•Ώπ–—π–Žπ–‹π–‘π–Žπ–“π–Œπ•Ώπ–—π–Šπ–Šβ“

Mars habitat designed by Leonardo Da Vinci
These are not as impressive as I had hoped
Midjourney 4 AI Art
Β Β  ​

0
1
0

Oh my goodness. These are as visually brilliant IRL as in these pics.

I couldn’t walk past these without taking photos and sharing.

The purples bleeding into white and the subtle yellows within the centre ovary section of each flower is quite amazing.

It was a bit of a wow moment discovering this.

4
3
0

Fahim Farook

And that's 13 papers in the cs.CV category (and one outside) posted today out of a total of 89 papers in the cs.CV category on arXiv.

That's all for today πŸ™‚

#AI #CV #NewPapers #DeepLearning #MachineLearning
0
0
1

Fahim Farook

"Video Influencers: Unboxing the Mystique. (arXiv:2012.12311v2 [cs.LG] UPDATED)" β€” A study and analysis of YouTube influencers and their unstructured video data across text, audio and images using a novel "interpretable deep learning" framework to determine the effectiveness of their constituent elements in explaining video engagement.

Paper: http://arxiv.org/abs/2012.12311

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too πŸ™‚>>
Gradient heat map in video fram…
0
1
0

Fahim Farook

"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models. (arXiv:2301.13826v1 [cs.CV])" β€” A process which intervenes in the generative process of diffusion models on the fly during inference time to improve the faithfulness of the generated images to guide the model to refine the cross-attention units to attend to all subject tokens in the text prompt and strengthen - or excite - their activations, encouraging the model to generate all subjects described in the text prompt.

Paper: http://arxiv.org/abs/2301.13826
Code: https://github.com/AttendAndExcite/Attend-and-Excite

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too πŸ™‚>>
Given a pre-trained text-to-ima…
0
1
0

Fahim Farook

"Grounding Language Models to Images for Multimodal Generation. (arXiv:2301.13823v1 [cs.CL])" β€” An efficient method to ground pretrained text-only language models to the visual domain, enabling them to process and generate arbitrarily interleaved image-and-text data. This approach apparently works with any off-the-shelf language model.

Paper: http://arxiv.org/abs/2301.13823

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too πŸ™‚>>
Our method grounds a language m…
1
1
0

Fahim Farook

"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers. (arXiv:2301.13741v1 [cs.CV])" β€” A universal vison-language Transformer compression framework which can handle multiple generative and discriminative vision-language tasks such as Visual Reasoning, Image Caption, Visual Question Answer, Image-Text Retrieval, Text-Image Retrieval, and Image Classification.

Paper: http://arxiv.org/abs/2301.13741

#AI #CV #NewPaper #DeepLearning #MachineLearning

<<Find this useful? Please boost so that others can benefit too πŸ™‚>>
Comparison between the Mask-bas…
0
2
1
Show older