Original post on det.social

Vision-language models are impressive—until you ask them something simple.
A recent study shows that state-of-the-art systems struggle with basic visual tasks like counting shapes or detecting overlaps, achieving only ~58% accuracy on average—far below human performance
So what are they actually […]

ImageSpace — Visual Explorer

Check out my new software ImageSpace, a modern replacement for PixPlot for exploring image collections using AI. The output is a static site you can host anywhere: tinyurl.com/2zj4szkd

#DigitalHumanities #CulturalAnalytics #MachineLearning #ComputerVision #DHMakes #OpenSource #AcademicSky

Do you want to put your deep learning and computer vision skills to work on pressing real-world challenges in agriculture and plant breeding?

OPEN post-doc position: www.verwaltung.uni-halle.de/DEZERN3/AUSS...
📅 Apply by: 2026-04-10
#ComputerVision #DeepLearning #PostDoc #Phenotyping #PlantScience

Meta SAM 3.1 Pushes Real-Time Video Segmentation Past What a Single GPU Was Supposed to Handle Meta’s SAM 3.1, released March 27, 2026, fixes the one production bottleneck that made SAM 3’s multi-object video tracking impractical at scale. This isn’t a new model; it’s a surgical

Every tracked object sharing one forward pass. Meta's SAM 3.1 hits 32 fps on a single H100 and zero accuracy loss. Full breakdown of what multiplexing actually changes 🎯 #AdwaitX #MetaAI #SAM3 #ComputerVision

Meta SAM 3.1 - 7x Faster Multi-Object Video Tracking Meta releases SAM 3.1 with Object Multiplex, processing all tracked objects in one shared pass for 7x faster inference at 128 objects and improvements on 6 of 7 VOS benchmarks.

Meta SAM 3.1 - 7x Faster Multi-Object Video Tracking

awesomeagents.ai/news/meta-sam-3-1-object...

#Meta #ComputerVision #OpenSource

Meta SAM 3.1 - 7x Faster Multi-Object Video Tracking Meta releases SAM 3.1 with Object Multiplex, processing all tracked objects in one shared pass for 7x faster inference at 128 objects and improvements on 6 of 7 VOS benchmarks.

Meta SAM 3.1 - 7x Faster Multi-Object Video Tracking

awesomeagents.ai/news/meta-sam-3-1-object...

#Meta #ComputerVision #OpenSource

Apple's RubiCap AI Captions Images Better Than Models 10x Its Size Apple has developed RubiCap, an AI framework that trains compact models to generate image captions rivaling systems 10 times their size on key benchmarks.

winbuzzer.com/2026/03/26/a...

Apple's RubiCap AI Captions Images Better Than Models 10x Its Size

#AI #Apple #MachineLearning #AIResearch #ComputerVision #OnDeviceAI #GenerativeAI #Rubicap #ImageCaptioning

Learn how to reduce electrical noise, improve grounding, and protect signal integrity in industrial control panels.

Read here:
zurl.co/nD8qu

#SignalIntegrity #Grounding #ControlPanel #Smidnya #smidnyatechnologies #computervision #aivision #realtimeanalytics

Vecstore vs Imagga: We Tested Both Image Search APIs I wanted to understand how Imagga's visual search compares to ours, so I signed up, got API keys, and...

Vecstore vs Imagga: We Tested Both Image Search APIs I wanted to understand how Imagga's visual search compares to ours, so I signed up, got API keys, and tested both APIs against the same imag...

#vectordatabase #computervision

Origin | Interest | Match

Automated Optical Inspection System Market Size Forecast 2035 | Industry Share Analysis Automated Optical Inspection System Market Size is expected to grow at a 17.5% CAGR by 2035, Global AOI System Market Growth Analysis By Type, Component, Technology, Industry Vertical, and Region | Au...

Automated Optical Inspection System Market Size Forecast 2035 | Industry Share Analysis www.marketresearchfuture.com/reports/auto... #ComputerVision #AI #EdgeAI #Semiconductor #Automation #NextGenTech #Innovation #TechTrends

InGaAs Image Sensor Market by Type, Size, Growth and Analysis – 2035 InGaAs Image Sensor Market is set to grow at 8.70% CAGR by 2035, Global InGaAs Image Sensor Market Research Report by Type, by Application, by Vertical and by Region | InGaAs Image Sensor Industry

InGaAs Image Sensor Market by Type, Size, Growth and Analysis – 2035 www.marketresearchfuture.com/reports/inga...
#GamingTech #ImageSensor #ComputerVision #AI #EdgeAI #AIChips #Semiconductor #VisionTech #NextGenGaming #Innovation

Depth Sensing Market | Size, Share, Trends And Forecast 2035 Depth Sensing Market is expected to grow USD 18.61 Billion by 2035 by Component, Type, Technology, Vertical | Depth Sensing Industry

Depth Sensing Market | Size, Share, Trends And Forecast 2035 www.marketresearchfuture.com/reports/dept...
#GamingTech #AR #VR #DepthSensing #EdgeAI #AIChips #ComputerVision #ImmersiveTech #NextGenGaming #Innovation

Find specific moments in hours of dashcam footage by typing what you're looking for - 'red truck running stop sign' instantly returns the exact clip

https://github.com/ssrajadh/sentrysearch

#ComputerVision #SemanticSearch #VideoAnalysis

🚀 This week at #ELLIS Winter School: our #CVPR2026 paper Retrieve and Segment (RNS) is being presented by @tim-arav.bsky.social.

🎯 RNS shows how a few pixel-level annotated images can boost zero-shot Open Vocabulary Segmentation.

📝 arxiv.org/pdf/2602.23339

#ComputerVision #FoundationModels #OVS

This work was led by our amazing intern Oindrila Saha (UMass Amherst -- now at Adobe!), with Vojtech Krs, Radomir Mech, Kevin Blackburn-Matzen, and Subhransu Maji (UMass Amherst).

#ICLR2026 #ImageGeneration #ComputerVision

APPX Workshop @ CVPR 2026

Got a paper around appearance at CVPR 2026? Make the most of it at the AppX workshop! Submit by April 7:
appx-workshop.github.io

@elegarces.bsky.social
@iliyangeo.bsky.social
Giseppe Vecchio
Michael Fischer

#CVPR2026 #ComputerVision #NeuralRendering #AppearanceUnderstanding #AppX2026

Skeletonization
more info: scikit-image.org/doc...

#python #computervision

See the world through the lens of data. 🚀📸

I specialize in Custom Object Detection using state-of-the-art Machine Learning frameworks.

Deploy your computer vision model here:
go.fiverr.com/visit/?bta=2...

#MachineLearning #ComputerVision #ObjectDetection #YOLO #AI #Python #DeepLearning

Good morning everyone! Would somebody please #endorse me on cs.CV #ComputerVision and #PatternRecognition of #arXiv?

We are submitting an article for the first time! Link below ;)

arxiv.org/auth/endorse...

Or pls visit

arxiv.org/auth/endorse...

and enter Code: 9I4F67

Thanks in advance!! 😍

Original post on mastodon.social

The second is the Neuro N6, an STM32N6-powered Feather-format #microcontroller development board built with edge... err, computer vision in mind. Milliwatt-power CV on-board, its creators promise - all accessible via extension to the #Arduino IDE […]

Visioni X potenziate: creando immagini con l’AI.
Enhanced Vision X: creating images with AI.
#visioni #aiart #digitalart #raw_ai #arte #portrait #beauty #girl #love #amore #eros #nudo #nude
#corpi #body #computervision #digitalart #raw_ai #midjourneygallery #midjourney #bellezza #art

3D Camera Market is Transforming the Industry Landscape www.marketresearchfuture.com/reports/3d-c...
#3DCamera #ImagingTech #3DImaging #ComputerVision #CameraTech #ARVR #SmartDevices #Innovation

Vision Processing Unit Market Trends 2026: Advancements, Opportunities, and Forecast - News Release Explore the Vision Processing Unit Market Trends 2026 with insights on growth drivers, technological advancements, regional analysis, and key applications in AI, automotive, and consumer electronics.

Vision Processing Unit Market Trends 2026: Advancements, Opportunities, and Forecast - News Release www.prnewsreleaser.com/news/239499
#VPU #AIChips #ComputerVision #EdgeAI #Semiconductor #SmartDevices #Innovation #DeepLearning #ChipTech #Tech

Automatic Number Plate Recognition Market Trends 2026: Growth, Opportunities, and Forecast - News Release Explore the Automatic Number Plate Recognition Market Trends 2026, including market size, growth factors, technological advancements, key companies, and opportunities in security, surveillance…

Automatic Number Plate Recognition Market Trends 2026: Growth, Opportunities, and Forecast - News Release www.prnewsreleaser.com/news/239497
#ANPR #SmartTraffic #AI #ComputerVision #SmartCities #Surveillance #IoT #TransportationTech #Innovation #Security

AI-driven Spreadsheet Processing Services Streamline your spreadsheet workflows with AI-powered data processing services. Using (Un)Perplexed Spready and Perplexity AI, we specialize in data extraction, categorization, annotation, and labelin...

📱 Got product images? Our AI "sees" them! Extract product names, features, colors & prices from photos automatically. Transform visual data into structured spreadsheets. Image-to-data conversion at your fingertips! matasoft.hr/qtrendcontro... #ComputerVision #ImageProcessing #AI

👋 Hello #ScienceSky!

I'm Minh, an incoming CS PhD student at the University of Utah 🏔️. Moving to SLC this fall to dive deeper into Embodied AI and Robotics.

Looking to connect with the #Robotics, #ComputerVision, #NLP, and #AI communities! 🦾

(1/3) 🧵

🎥 DFRWS EU 2026 | Multimedia Forensics Join us at the Linköping University (LiU) for our new #DFRWSEU2026 Track debuting this year! 👉 Program (Friday): https://buff.ly/GwzBlHL 🧿 Register: https://buff.ly/O5gA8U6

🎥 DFRWS EU 2026 | Multimedia Forensics 🔍

Join us at the Linköping University (LiU) for our new #DFRWSEU2026 Track debuting this year!

👉 Program (Friday): buff.ly/GwzBlHL
🧿 Register: buff.ly/O5gA8U6

#MultimediaForensics #DeepfakeDetection
#ImageForensics #ComputerVision #AIGenerated

Promotional poster. On the right, an image of squids swimming in the ocean. On the left text: CVPR-FGVC 13 Workshop call for participation. FathomNet26 Positive-Unlabeled Object Detection in Marine Images. End of competition May 7.

Tag someone who should join the FathomNetCLEF data challenge! 🤖🌊🐙

@sarameghanbeery.bsky.social @jbhaurum.bsky.social @oisinmacaodha.bsky.social @nicolang.bsky.social @fgvcworkshop.bsky.social @mbarinews.bsky.social @kaggle.com #CVPR #LifeCLEF #Kaggle #CV4Ecology #ComputerVision #MachineLearning

FathomNetCLEF2026 @ LifeCLEF & CVPR-FGVC Positive-Unlabeled Object Detection in Marine Images

We have a major problem. Many of the annotated images in the #FathomNetDatabase have sparse coverage–only 1 or some of the animals are labeled. We’re asking the #ComputerVision community for help to develop better object detectors.

Promotional event poster with the face of the speaker, Murtaza Hassan, and the title of the event Live Programming a Line-Follower Drone

On this week's episode we welcome back Murtaza Hassan of Murtaza's workshop, a popular YT channel focused on AI, robotics, and drones. Murtaza will be live-coding and simulating a line-follower drone, and taking questions from the audience. A brave live demo! #OpenCV #ComputerVision #AI