Loading video...

Video Failed to Load

Go Home

Real-time DEtection Transformer (RT-DETR) landed in Hugging Face transformers 🤩 with Apache 2.0 license 😍 do DETRs Beat YOLOs on Real-time Object Detection? keep reading 👀

mervenoyann's profile picture

merve

77,873 subscribers

155,222 views • 2 years ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

RF-DETR just landed to Hugging Face transformers 🥵🔥 sota real-time detection & segmentation models by Roboflow 💜 > play with our real-time demo > fine-tune the models on your use case with our tutorials (takes a toaster's VRAM) > or just hand them to your agents 😄
0:13

RF-DETR just landed to Hugging Face transformers 🥵🔥 sota real-time detection & segmentation models by Roboflow 💜 > play with our real-time demo > fine-tune the models on your use case with our tutorials (takes a toaster's VRAM) > or just hand them to your agents 😄

merve

56,967 views • 1 month ago

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.
0:15

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.

Akshay 🚀

31,412 views • 7 months ago

Arabic. Japanese. Turkish. Redacting clinical discharge summaries in real-time. 30+ new open-source PII models shipped today on Hugging Face. 30+ MLX variants as native Swift packages for macOS and iOS. OpenMed PII family: 1M+ downloads in 20 days. Apache 2.0.
0:15

Arabic. Japanese. Turkish. Redacting clinical discharge summaries in real-time. 30+ new open-source PII models shipped today on Hugging Face. 30+ MLX variants as native Swift packages for macOS and iOS. OpenMed PII family: 1M+ downloads in 20 days. Apache 2.0.

Maziyar PANAHI

20,541 views • 1 month ago

🔥Introducing VILA: The next-gen VLM for Video and inter-leaved image understanding with Apache-2.0 license! Is VILA the best in-class small VLM for edge-deployment? Keep reading🧵 👀
0:17

🔥Introducing VILA: The next-gen VLM for Video and inter-leaved image understanding with Apache-2.0 license! Is VILA the best in-class small VLM for edge-deployment? Keep reading🧵 👀

Gradio

51,694 views • 2 years ago

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:
0:17

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:

PyCharm, a JetBrains IDE

34,908 views • 2 months ago

Thanks for following us! We're excited to see what you all build with Gemma 4! In case you missed it, you can find all our checkpoints, with an Apache 2.0 License, on Hugging Face:
0:15

Thanks for following us! We're excited to see what you all build with Gemma 4! In case you missed it, you can find all our checkpoints, with an Apache 2.0 License, on Hugging Face:

Google Gemma

404,664 views • 3 months ago

The new AIOZ AI Featured Challenge drops TOMORROW! This time we’re taking AI to the streets… Real roads. Real mess. Real impact. Unlock safer cities with models - one detection at a time. The same hands-on learning practice! Who’s ready to fix what’s broken? Launch incoming. Stay locked in.
0:16

The new AIOZ AI Featured Challenge drops TOMORROW! This time we’re taking AI to the streets… Real roads. Real mess. Real impact. Unlock safer cities with models - one detection at a time. The same hands-on learning practice! Who’s ready to fix what’s broken? Launch incoming. Stay locked in.

AIOZ Network

173,249 views • 7 months ago

From parked cars to an Airbus A321 at cruising altitude. Same laptop. MLX & Torch. SAM3 segments every vehicle on the ground. Yes, just cars. RF-DETR spots the Austrian Airlines jet overhead. Real-time detection. Two open-source models running locally. No cloud. No API.
0:16

From parked cars to an Airbus A321 at cruising altitude. Same laptop. MLX & Torch. SAM3 segments every vehicle on the ground. Yes, just cars. RF-DETR spots the Austrian Airlines jet overhead. Real-time detection. Two open-source models running locally. No cloud. No API.

Maziyar PANAHI

46,612 views • 3 months ago

obfuscate reverse shells and watch the detection rate drop in real time 😈 this wont be in tomorrows video, this will be for the one after with the 2 other security tools im dropping
0:11

obfuscate reverse shells and watch the detection rate drop in real time 😈 this wont be in tomorrows video, this will be for the one after with the 2 other security tools im dropping

I am Jakoby

30,918 views • 4 months ago

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 #AI
0:15

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 #AI

Muhammad Rizwan Munawar

30,677 views • 3 months ago

it's open source time, with a real leap for world models 🎉 NVIDIA's SANA-WM: a camera-conditioned world model that fits on one GPU. 60s of 720p in 34s on a single 5090 - 2.6B params and Apache 2.0!
0:20

it's open source time, with a real leap for world models 🎉 NVIDIA's SANA-WM: a camera-conditioned world model that fits on one GPU. 60s of 720p in 34s on a single 5090 - 2.6B params and Apache 2.0!

Victor M

34,386 views • 1 month ago

Smart parking pipeline in real-time with Ultralytics YOLO26 🚗 🅿️ Over the weekend, I built a parking management system that monitors slot occupancy (occupied vs available). In busy parking areas where vehicles partially overlap slots or enter at angles, the system still maintains accurate detection and status updates in real time. More information 👇 #yolo26 #parkingproblem #machinelearning
0:16

Smart parking pipeline in real-time with Ultralytics YOLO26 🚗 🅿️ Over the weekend, I built a parking management system that monitors slot occupancy (occupied vs available). In busy parking areas where vehicles partially overlap slots or enter at angles, the system still maintains accurate detection and status updates in real time. More information 👇 #yolo26 #parkingproblem #machinelearning

Muhammad Rizwan Munawar

37,625 views • 2 months ago

🚨 Meta introduces Segment Anything Model 2 (SAM 2) — the first unified model for real-time, promptable object segmentation in images & videos. 🚀SAM 2 is available today under Apache 2.0 so that anyone can use it to build their own experiences ➡️
0:13

🚨 Meta introduces Segment Anything Model 2 (SAM 2) — the first unified model for real-time, promptable object segmentation in images & videos. 🚀SAM 2 is available today under Apache 2.0 so that anyone can use it to build their own experiences ➡️

Zhengzhong Tu

181,288 views • 1 year ago

Car parts detection running on the SiMa.ai DevKit 3.0 😍 I recently had the opportunity to test YOLO11 for car parts detection on the devkit to see how well the model performs on edge hardware. The system processes frames in real time while maintaining efficient resource usage, making it a great fit for applications where low latency and reliability are critical. Additional details👇 #carparts #manufacturing #edgeai
0:16

Car parts detection running on the SiMa.ai DevKit 3.0 😍 I recently had the opportunity to test YOLO11 for car parts detection on the devkit to see how well the model performs on edge hardware. The system processes frames in real time while maintaining efficient resource usage, making it a great fit for applications where low latency and reliability are critical. Additional details👇 #carparts #manufacturing #edgeai

Muhammad Rizwan Munawar

14,040 views • 3 months ago

Editing facial expressions in real time now on Hugging Face Spaces 👨‍🎤🔀 A Grog converted Cog image to Gradio running a ComfyUI backend - magic of open source 🤝 ▶️
0:10

Editing facial expressions in real time now on Hugging Face Spaces 👨‍🎤🔀 A Grog converted Cog image to Gradio running a ComfyUI backend - magic of open source 🤝 ▶️

apolinario (poli)

71,701 views • 1 year ago

🚀 Real-time AI Tornado Detection Today we're introducing Tornado ID (Beta), an advanced artificial intelligence (AI) designed to analyze weather radar data in real time and identify tornadoes. Rather than only looking for clear tornado signatures, it also flags storms that are tornadic in general - storms exhibiting signatures that can lead them to develop into tornadoes. Key features: - Realtime AI detection - Confidence scoring - Available for Radar and MRMS (CONUS) Composite Available to Pro subscribers and the US (NEXRAD) weather radar network. Available now on: iOS: Android: Browser:
0:13

🚀 Real-time AI Tornado Detection Today we're introducing Tornado ID (Beta), an advanced artificial intelligence (AI) designed to analyze weather radar data in real time and identify tornadoes. Rather than only looking for clear tornado signatures, it also flags storms that are tornadic in general - storms exhibiting signatures that can lead them to develop into tornadoes. Key features: - Realtime AI detection - Confidence scoring - Available for Radar and MRMS (CONUS) Composite Available to Pro subscribers and the US (NEXRAD) weather radar network. Available now on: iOS: Android: Browser:

WeatherWise.app

48,250 views • 3 months ago

NEW: VERITAS × RUGCHECK × SOLSNIFFER Veritas Explorer protection expanded to Solana with Rugcheck & Solanasniffer integration. ✅ Token risk analysis ✅ On-chain data metrics ✅ Impartial scoring system ✅ Real-time scam detection Available now under Rug Pull tab. Check any Solana token at
0:14

NEW: VERITAS × RUGCHECK × SOLSNIFFER Veritas Explorer protection expanded to Solana with Rugcheck & Solanasniffer integration. ✅ Token risk analysis ✅ On-chain data metrics ✅ Impartial scoring system ✅ Real-time scam detection Available now under Rug Pull tab. Check any Solana token at

VERITAS PROTOCOL

25,068 views • 1 year ago

This #CVPR2026 paper from our research team is trending #1 on Hugging Face 🤗 Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act. Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection. Project page:
0:16

This #CVPR2026 paper from our research team is trending #1 on Hugging Face 🤗 Meet LocateAnything: a vision-language detection model that rethinks bounding box prediction. For AI agents and robots, “seeing” is only useful if a model can pinpoint where something is fast enough to act. Trained on 138M high-quality samples, LocateAnything decodes bounding boxes in parallel instead of one coordinate at a time, improving localization accuracy while dramatically increasing throughput for visual grounding and detection. Project page:

NVIDIA AI

335,546 views • 1 month ago

.Cetus🐳 is now secured by Blockaid. - Cetus processes the highest volume and trading demand on Sui. - Blockaid protects it with real-time onchain threat detection. - Threats like price manipulation, liquidity pool anomalies, and unauthorized ownership changes are stopped before they escalate. That gives their team actionable intelligence in the moments that matter most and will continue to grow over time as new attack surfaces emerge.
0:15

.Cetus🐳 is now secured by Blockaid. - Cetus processes the highest volume and trading demand on Sui. - Blockaid protects it with real-time onchain threat detection. - Threats like price manipulation, liquidity pool anomalies, and unauthorized ownership changes are stopped before they escalate. That gives their team actionable intelligence in the moments that matter most and will continue to grow over time as new attack surfaces emerge.

Blockaid

23,000 views • 11 months ago

Still can't believe what the Real-Time Caustics can do in Shaders Plus! Development sometimes takes forever, cause I'm stuck just playing around with stuff like this for hours🤪😍 If you're curious about these Real-Time Caustics: #blender #b3d #blender3d
0:12

Still can't believe what the Real-Time Caustics can do in Shaders Plus! Development sometimes takes forever, cause I'm stuck just playing around with stuff like this for hours🤪😍 If you're curious about these Real-Time Caustics: #blender #b3d #blender3d

SMOUSE 🔸 🏳️‍🌈🏳️‍⚧️

128,272 views • 1 year ago