Experimenting with super lightweight moving object detection No model,... just one pass through a 40x30 10fps monochrome video. Plenty easy for most MCUs to handleshow more

Moondream 3: world's best open-vocab object detection, packed in... a fast, open model.show more

Train a TensorFlow object detection model – then deploy... it on a robot 🤖 Iulia Feroli (Iulia Feroli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any project – though we demonstrate the deployment on (and assisted by!) the #ReachyMini, an open-source robot from Pollen Robotics. Built with PyCharm + Claude Code. 👉 Watch it in action:show more

E no go pass one Benin boy lavishing money... on her! Dem plenty for TTshow more

Real-time object detection will never be the same. Traditional... YOLO needs NMS to remove duplicate boxes; it's slow and inconsistent. YOLO26 skips it entirely: single-pass predictions, faster inference and up to 300 detections per image. Download model:show more

Pothole detection on the road in real time using... Ultralytics YOLO26! 🕳️ Manual road inspections are slow, costly, and hard to scale. With object detection, potholes can be identified directly from street-level images or video feeds, enabling faster and more consistent road condition monitoring. How I built this demo: ✅ Trained a segmentation model on a custom dataset. ✅ Generated mask contours for each pothole. ✅ Leveraged the onnx-exported model for faster processing. #Pothole #RoadDamage #AIshow more

Excited to share our ICRA’23 IEEE ICRA work by... Adithya Murali We scale up neural collision detection for object rearrangement with procedurally generated synthetic data. Project: Video: 🧵👇show more

SOTA object detection with powerful visual reasoning: "skateboarder wearing... checkered shirt".show more

Easy trick to secure a shovel handle with wire.

Most of the doors don't fit me, so I... go through walls instead. It's just too easy for me to break them, just one push, and I'm through. And you get to film behind your goddess before you sigh and call the insurance.show more

Nowadays it seems way too easy for someone to... alter a video subs and for everyone to just believe it, with NO ONE bothering to check the original source. So here is the real subs: Weverse live, July 23, 2025.show more

Meta's SAM 3 is a beast. before: collect data,... train custom object detector, use tracker to estimate object motion - days now: track anything with text prompt - seconds real-time object detection will never be the same.show more

Experimenting with claymation today Kling AI 2.1 handing it... like a champ. No prompt for this one I just put in the image to see where kling it would take it. More to come 😎👍show more

Experimenting with a multitouch Unity native plugin for the... Mac trackpad. I didn’t realize it could handle ten touch points.show more

Andrew Ng and his team introduced Agentic Object Detection!... No training needed, just describe an object, and AI thinks, plans, and finds it like OpenAI o1/o3. 6 examples (and how to try): 1. Detected occupied tableshow more

🚨 BREAKING: Video generation just got its biggest upgrade.... WAN 2.6 generates complete audiovisual experiences in one pass—no stitching, no external tools, no manual sync. First open-source model to do this. Here are 5 examples:show more

Seedance 2.0 is now live on invideo for Max,... Generative, and Team plan users. BytePlus's most advanced video model — and arguably the most controllable AI video model ever released. Multimodal input. Motion replication from reference videos. Native audio-video generation in one pass. Character consistency that actually holds. Director-level camera control. Real-world physics. This isn't prompt-and-pray. This is a production tool. Only available through business email verification for all regions except US and Japan.show more

Awesome week for computer vision Hugging Face🔥 Besides DINOv3... we added support for LLMDet, the SOTA for zero-shot object detection (#CVPR2025 '25 highlight) Detect instances in scenes just via prompting, no training involved.show more

Probably the most annoying thing for me in animations... / scrollable content is how easy it is to just clip the content. Even if there is no border around to clip it with, adding masks is a one-liner in css now. (slowed down transition)show more

I'm working on a new demo. detection of key... points on a soccer field. for now, I need to work through annotating the data I will use to train the model. I'll keep you posted.show more