Szymon Kowalewski · @SkSzymon
0 followers · 16 posts · Server me.dm

SportsSloMo: Nowosc w branży analizy sportowej!

* SportsSloMo jest największym benchmarkiem do tej pory, o wysokiej rozdzielczości i skoncentrowanym na scenariuszach opartym na ludziach.
* SportsSloMo zawiera więcej dużych przemieszczeń w porównaniu z powszechnie używanymi datasetami VFI.
* SportsSloMo obejmuje 22 różne kategorie sportów o różnej zawartości i wzorcach ruchu, w tym hokej, baseball, łyżwiarstwo, koszykówkę, bieganie, siatkówkę itp.

#computervision #artificialintelligence #sport

Last updated 1 year ago

Rene Schulte · @rschu
596 followers · 290 posts · Server arvr.social

LLMs like ChatGPT are based on Transformer AI models introduced 2017. Transformer was later also applied for computer vision with the introduction of self-supervised Vision Transformers.

If you want to know how ViTs work and what the uses cases are 👉 reply.com/en/artificial-intell

#llm #chatgpt #gpt #ai #deeplearning #visiontransformer #computervision #cv

Last updated 1 year ago

IT News · @itnewsbot
3710 followers · 272577 posts · Server schleuss.online

Vision AI: Prevent Fire and Smoke Hazards in the Workplace - Fire hazards are a global scourge, indiscriminately wreaking havoc on homes, busin... - readwrite.com/vision-ai-a-smar

#ai #tech #smartai #security #computervision #smokeandfiredetection

Last updated 1 year ago

IT News · @itnewsbot
3707 followers · 272476 posts · Server schleuss.online

Entertain Your Cats Automatically with LazerPaw - Most of us would agree that kittens are very cute, but require lots of attention i... - hackaday.com/2023/09/05/entert

#cat #lazer #homehacks #laserhacks #computervision

Last updated 1 year ago

hlfshell · @hlfshell
73 followers · 323 posts · Server hachyderm.io

In this modern era, you need to create an object detector of reasonable FPS for a robot.

Do you still reach for a YOLO variant? Or is there something better / newer I should be eyeing?

The goal is to identify and then estimate location of object for contextual room mapping ("hey, there's an oven in this room. It's probably a kitchen")

#robotics #computervision #cv #deeplearning

Last updated 1 year ago

Nicole Hennig · @nic221
348 followers · 1766 posts · Server techhub.social

Announcing the commercial relicensing and expansion of DINOv2, plus the introduction of FACET ai.meta.com/blog/dinov2-facet-

#AI #computervision

Last updated 1 year ago

Nicole Hennig · @nic221
348 followers · 1766 posts · Server techhub.social

DINOv2: State-of-the-art computer vision models with self-supervised learning ai.meta.com/blog/dino-v2-compu

#AI #computervision #opensource

Last updated 1 year ago

Rene Schulte · @rschu
594 followers · 287 posts · Server arvr.social

Vision Transformers are a game changer for computer vision. More and more ViT models are popping up like DINO v2, SAM, CLIP, etc. setting new records for CV benchmarks. 👀

We wrote a white paper about ViTs giving an introduction, showing practical business use cases and also covering our experience with ViTs in combination with Boston Dynamics Spot. 🤖

More details including an AI explainer video and the paper here. For free. 👉

reply.com/en/artificial-intell

#ai #deeplearning #cv #computervision

Last updated 1 year ago

Calle Börstell · @c_borstell
175 followers · 40 posts · Server fediscience.org

4-year postdoc job opportunity!

Research on sign language non-manuals at the University of Bergen 🇳🇴. Requirements: knowledge of computer vision methods and experience with sign language/gesture data.

Deadline: 20 Sept 2023!

Please share!

jobbnorge.no/en/available-jobs

#SignLanguages #computervision #linguistics

Last updated 1 year ago

Urs Waldmann · @ursNwaldmann
17 followers · 46 posts · Server sigmoid.social

Check out our latest pre-print on sciencecast.org/casts/8g1z2dov

We present 3D-MuPPET, a framework to estimate and track 3D poses of up to 10 at interactive speed. We show that 3D-MuPPET also works in natural environments without model fine-tuning on additional annotations.

#arxiv #pigeons #muppet #PoseEstimation #3dpose #tracking #computervision #CollectiveBehaviour #uniKonstanz #cbehav #cv4animals

Last updated 1 year ago

raimoncoding · @raimoncoding
34 followers · 97 posts · Server techhub.social
Emmanuel Chateau-Dutier · @emchateau
255 followers · 527 posts · Server mamot.fr

CFP « Ekphrasis and Artificial Intelligence: Text-to-Image Generation in Theory and Practice » CAA Chicago 2024 .amitiés caa.confex.com/caa/2024/webpro

#digitalarthistory #digitalhu #computervision #ia

Last updated 1 year ago

IT News · @itnewsbot
3660 followers · 271301 posts · Server schleuss.online
Shawn M. Jones, PhD · @shawnmjones
459 followers · 3836 posts · Server hachyderm.io

Elon is planning to effectively kill social cards on . Social cards were a big part of my dissertation work. I published a few papers about generating them via , , and because they make for nice bits of document and . Now Musk wants them gone to force journalists to write articles directly on Twitter.

Ref (paywall): fortune.com/2023/08/21/elon-mu
Ref (article about paywalled article): 9to5mac.com/2023/08/21/twitter

#Twitter #computervision #nlp #machinelearning #summarization #storytelling #twittermigration

Last updated 1 year ago

deadprogram · @deadprogram
638 followers · 325 posts · Server social.tinygo.org

GoCV 0.34 was just released!

Support for Go 1.21 and OpenCV 4.8 is what you need, and we've got it.

github.com/hybridgroup/gocv/re

#golang #opencv #gocv #computervision

Last updated 1 year ago

IT News · @itnewsbot
3643 followers · 270857 posts · Server schleuss.online
Urs Waldmann · @ursNwaldmann
17 followers · 49 posts · Server sigmoid.social
Chris Offner · @chrisoffner3d
364 followers · 1366 posts · Server sigmoid.social

3D Gaussian Splatting goes dynamic in "Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis".

They model dynamic scenes by allowing their 3D Gaussians to move and rotate over time while enforcing that they have persistent color, opacity, and size.

dynamic3dgaussians.github.io/

#nerf #computervision #computergraphics #3dvision #gaussian

Last updated 1 year ago

Jake Coppinger · @jake
440 followers · 51 posts · Server mastodon.jakecoppinger.com

Does anyone know of open source projects that use AI to segment orthorectified imagery and try to categorise bicycle paths or other cycling infrastructure, and check if they’re missing from OpenStreetMap?

I’m thinking of whether it would be possible to run Meta’s Segment Anything model over suitably licensed aerial imagery to find infra missing on OSM. Any thoughts/comments very welcome!

#openstreetmap #meta #segmentanything #ai #computervision #geospatial #gis #cycling #bikes #bicycles

Last updated 1 year ago

Martin Trapp · @trappmartin
626 followers · 465 posts · Server ellis.social

The list of accepted papers of our workshop on for is out!

Check out: uncv2023.github.io/papers/

#iccv #uncertaintyquantification #computervision

Last updated 1 year ago