Загрузка видео...

Не удалось загрузить видео

На главную

BREAKING: The future of object detection is here! Meet YOLO-NAS, open-sourced YOLO-based architecture redefining state-of-the-art in object detection.

Saboo_Shubham_'s profile picture

Shubham Saboo

118,663 subscribers

726,480 просмотров • 3 лет назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Shubham Saboo
Shubham Saboo3 лет назад

What makes YOLO-NAS so special? 1. Enhanced small object detection 2. Hybrid quantization 3. Improved localization 4. Performance-per-compute ratio 5. Optimized for real-time edge-devices

Фото профиля Shubham Saboo
Shubham Saboo3 лет назад

What are you waiting for? 😱 Head over to GitHub, 🌟 SuperGradients, and check out the starter notebook to experience YOLO-NAS in action! GitHub Repo - Starter Notebook -

Фото профиля Shubham Saboo
Shubham Saboo3 лет назад

That's a wrap! If you liked this, like and RT to share it with your friends. I share daily content around AI updates, follow me → @Saboo_Shubham_ to receive daily updates directly in your feed. For weekly summary of AI updates, subscribe to my FREE AI newsletter -

Фото профиля Nemanja Stojanovic
Nemanja Stojanovic3 лет назад

Supreme choice for a demo video.

Фото профиля Shubham Saboo
Shubham Saboo3 лет назад

Thank you!

Фото профиля Jaydeep
Jaydeep3 лет назад

I am a simple man, I see a reference to 'The Office' I retweet and like ;)

Фото профиля Shubham Saboo
Shubham Saboo3 лет назад

Haha, good one man!! I like it :)

Фото профиля jacopo
jacopo3 лет назад

accurate

Фото профиля Probably Human
Probably Human3 лет назад

wish this had sound.

Фото профиля Shubham Saboo
Shubham Saboo3 лет назад

Hahaha!

Похожие видео

⚡️Did you know YOLOv8 is an anchor-free object detection model, and YOLOv5 is an anchor-based object detection model? We conduct an in-depth comparison between them and carry out inference for detection and segmentation. #yolo #yolov8 #yolov5 #ai
0:23

⚡️Did you know YOLOv8 is an anchor-free object detection model, and YOLOv5 is an anchor-based object detection model? We conduct an in-depth comparison between them and carry out inference for detection and segmentation. #yolo #yolov8 #yolov5 #ai

Satya Mallick

84,454 просмотров • 3 лет назад

Camouflage no longer works with YOLO. The detection of the hays here is impressive. YOLO can identify an hay which has mostly the same color of the background.
0:26

Camouflage no longer works with YOLO. The detection of the hays here is impressive. YOLO can identify an hay which has mostly the same color of the background.

Marco Franzon

149,570 просмотров • 4 месяцев назад

we are introducing a state-of-the-art real-time object detection model, RF-DETR RF-DETR outperforms all existing object detection models on real world datasets and is the first real-time model to achieve 60+ Average Precision on COCO talked w/ NVIDIA about it at GTC:
2:31

we are introducing a state-of-the-art real-time object detection model, RF-DETR RF-DETR outperforms all existing object detection models on real world datasets and is the first real-time model to achieve 60+ Average Precision on COCO talked w/ NVIDIA about it at GTC:

Joseph Nelson

18,231 просмотров • 1 год назад

Check out our #ECCV2026 paper "Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention", where we make linear attention sparse in space, recurrent in time, and parallel in training, enabling the first purely-linear-attention-based neural network for asynchronous object detection with #EventCameras, outperforming the previous best asynchronous method with 20x less computation with truly event-by-event inference on CPU! Code released! Paper: Code: Video: Event cameras promise extremely low-latency vision, but to fully exploit them, the neural network must be low-latency too. We introduce #SpatiallySparseLinearAttention (#SSLA) for asynchronous object detection directly from raw events. Linear attention is particularly appealing for event cameras: it can be trained efficiently in parallel on long event sequences, while at inference it operates recurrently, updating its prediction every time a new event arrives. The problem is that conventional linear attention updates its entire state for every event. For object detection, where fine spatial resolution matters, this quickly becomes expensive. Our key idea is simple: an event only carries information about a small spatial region, so why update the entire spatial state? SSLA updates only the relevant parts of the state, enabling fine-grained spatial representations while keeping per-event computation low. We achieve: - >20× lower per-event computation than the strongest prior asynchronous baseline - State-of-the-art accuracy among asynchronous object detection methods - Truly event-by-event inference on CPU, designed to preserve the latency advantage of event cameras Come to our poster on Friday September 11, 2026 from 4-6pm at ExHall #389 Reference: Haiqing Hao, Zhipeng Sui, Rong Zou, Zijia Dai, Nikola Zubić, Davide Scaramuzza, Wenhui Wang Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention ECCV, 2026 Prophesee SynSense University of Zurich UZH Science European Research Council (ERC) UZHai UZH IfI Tesla BYD #EventCameras #ComputerVision #Robotics #DeepLearning #NeuromorphicVision #AI
2:40

Check out our #ECCV2026 paper "Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention", where we make linear attention sparse in space, recurrent in time, and parallel in training, enabling the first purely-linear-attention-based neural network for asynchronous object detection with #EventCameras, outperforming the previous best asynchronous method with 20x less computation with truly event-by-event inference on CPU! Code released! Paper: Code: Video: Event cameras promise extremely low-latency vision, but to fully exploit them, the neural network must be low-latency too. We introduce #SpatiallySparseLinearAttention (#SSLA) for asynchronous object detection directly from raw events. Linear attention is particularly appealing for event cameras: it can be trained efficiently in parallel on long event sequences, while at inference it operates recurrently, updating its prediction every time a new event arrives. The problem is that conventional linear attention updates its entire state for every event. For object detection, where fine spatial resolution matters, this quickly becomes expensive. Our key idea is simple: an event only carries information about a small spatial region, so why update the entire spatial state? SSLA updates only the relevant parts of the state, enabling fine-grained spatial representations while keeping per-event computation low. We achieve: - >20× lower per-event computation than the strongest prior asynchronous baseline - State-of-the-art accuracy among asynchronous object detection methods - Truly event-by-event inference on CPU, designed to preserve the latency advantage of event cameras Come to our poster on Friday September 11, 2026 from 4-6pm at ExHall #389 Reference: Haiqing Hao, Zhipeng Sui, Rong Zou, Zijia Dai, Nikola Zubić, Davide Scaramuzza, Wenhui Wang Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention ECCV, 2026 Prophesee SynSense University of Zurich UZH Science European Research Council (ERC) UZHai UZH IfI Tesla BYD #EventCameras #ComputerVision #Robotics #DeepLearning #NeuromorphicVision #AI

Davide Scaramuzza

51,571 просмотров • 6 дней назад

TIPS: Besides 3D wallpaper, the latest XR Animator also improves the performance of some Transformers-based AI models. For example, object detection AI based on Transformers is slower but more accurate, and this update makes these models more usable💨
0:29

TIPS: Besides 3D wallpaper, the latest XR Animator also improves the performance of some Transformers-based AI models. For example, object detection AI based on Transformers is slower but more accurate, and this update makes these models more usable💨

Butz Yung

23,997 просмотров • 9 месяцев назад

RF-DETR, the state-of-the-art model series for real-time object detection, can now run 100% locally in your browser on WebGPU with 🤗 Transformers.js v4! The models are Apache-2.0 licensed, making them a perfect fit for both personal and commercial applications. Try the demo 👇
0:42

RF-DETR, the state-of-the-art model series for real-time object detection, can now run 100% locally in your browser on WebGPU with 🤗 Transformers.js v4! The models are Apache-2.0 licensed, making them a perfect fit for both personal and commercial applications. Try the demo 👇

Xenova

77,179 просмотров • 6 месяцев назад

Releasing METAGENE-1: In collaboration with researchers from USC, we're open-sourcing a state-of-the-art 7B parameter Metagenomic Foundation Model. Enabling planetary-scale pathogen detection and reducing the risk of pandemics in the age of exponential biology.
2:03

Releasing METAGENE-1: In collaboration with researchers from USC, we're open-sourcing a state-of-the-art 7B parameter Metagenomic Foundation Model. Enabling planetary-scale pathogen detection and reducing the risk of pandemics in the age of exponential biology.

Prime Intellect

622,547 просмотров • 1 год назад

NASDAQ:$MYNZ 📈 Discover the Future of Cancer Detection!
1:35

NASDAQ:$MYNZ 📈 Discover the Future of Cancer Detection!

Mainz BioMed (NASDAQ: MYNZ)

193,080,446 просмотров • 7 месяцев назад

📺 we're taking a quick commercial break cult 👀 $yolo just got a new upgrade! 🤖 our state of the art robot by PAAL AI 🧠🤖 is waiting for you in our telegram 🎯 many people still don't understand $yolo cult... this starters pack is the perfect gift for them
0:48

📺 we're taking a quick commercial break cult 👀 $yolo just got a new upgrade! 🤖 our state of the art robot by PAAL AI 🧠🤖 is waiting for you in our telegram 🎯 many people still don't understand $yolo cult... this starters pack is the perfect gift for them

yolo

14,250 просмотров • 1 год назад

The future of decentralized object storage is here. AIOZ W3S brings highly versatile object storage infrastructure to Web3. Try W3S Today: - S3 Compatible - Highly Scalable - Built-In CDN - Affordable - Private - Fast $AIOZ
0:21

The future of decentralized object storage is here. AIOZ W3S brings highly versatile object storage infrastructure to Web3. Try W3S Today: - S3 Compatible - Highly Scalable - Built-In CDN - Affordable - Private - Fast $AIOZ

AIOZ Network

47,383 просмотров • 2 лет назад

This is huge for video AI. Stream dropped Vision Agents, an open-source framework that lets AI watch and understand live video in real-time. - Sports coaching - Real-time threat detection - Live meeting assistants Combines YOLO, Gemini, OpenAI. Free. Open-source 🧵👇
0:21

This is huge for video AI. Stream dropped Vision Agents, an open-source framework that lets AI watch and understand live video in real-time. - Sports coaching - Real-time threat detection - Live meeting assistants Combines YOLO, Gemini, OpenAI. Free. Open-source 🧵👇

Alvaro Cintas

85,488 просмотров • 7 месяцев назад

#BREAKING UFO IN THE TIJUANA SKIES WITH AIRPLANE FLYING INFRONT OF OBJECT!! This is REAL!!!
0:29

#BREAKING UFO IN THE TIJUANA SKIES WITH AIRPLANE FLYING INFRONT OF OBJECT!! This is REAL!!!

Jon Stewart

207,506 просмотров • 14 дней назад

Today we're releasing WildDet3D—an open model for monocular 3D object detection in the wild. It works with text, clicks, or 2D boxes, and on zero-shot evals it nearly doubles the best prior scores. 🧵
0:57

Today we're releasing WildDet3D—an open model for monocular 3D object detection in the wild. It works with text, clicks, or 2D boxes, and on zero-shot evals it nearly doubles the best prior scores. 🧵

Ai2

87,199 просмотров • 4 месяцев назад

Introducing Pangram 3.0, a new state-of-the-art for AI detection and transparency. This update introduces what we call AI assistance detection. We recognize that authorship is increasingly mixed, and we want to ensure that AI-assisted writing is correctly categorized as such.
2:10

Introducing Pangram 3.0, a new state-of-the-art for AI detection and transparency. This update introduces what we call AI assistance detection. We recognize that authorship is increasingly mixed, and we want to ensure that AI-assisted writing is correctly categorized as such.

Pangram

29,260 просмотров • 8 месяцев назад

Learn the art of transparent object background removal like a pro
1:00

Learn the art of transparent object background removal like a pro

Photoshop Tricks!

257,945 просмотров • 2 лет назад

Warzone pro Nickool 🇨🇦 speaks on winning the WSOW $50,000 SOLO YOLO "This is 120 of the best players in the world... to be here is just unreal"
0:24

Warzone pro Nickool 🇨🇦 speaks on winning the WSOW $50,000 SOLO YOLO "This is 120 of the best players in the world... to be here is just unreal"

Jake Lucky🔜 GAMESCOM

55,115 просмотров • 1 год назад

In 1998, Terence McKenna predicted that human civilization was speeding toward a perpetual state of strangeness, a future he described as “the Transcendental Object at the End of Time.”
1:16

In 1998, Terence McKenna predicted that human civilization was speeding toward a perpetual state of strangeness, a future he described as “the Transcendental Object at the End of Time.”

Historic Vids

753,232 просмотров • 7 месяцев назад