正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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 🚀

268,372 subscribers

31,386 次观看 • 6 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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:

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:

Akshay 🚀

373,358 次观看 • 3 个月前

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:

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 次观看 • 1 个月前

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 👀

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 👀

merve

155,222 次观看 • 1 年前

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

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

moondream

52,595 次观看 • 8 个月前

Sam 3 by Facebook now on MLX 🚀 Here is a realtime object tracking running on M3 Max 96GB.

Sam 3 by Facebook now on MLX 🚀 Here is a realtime object tracking running on M3 Max 96GB.

Prince Canuma

180,245 次观看 • 2 个月前

🚨 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 ➡️

🚨 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 次观看 • 1 年前

Starship is the largest flying object ever made! It's a crazy time to be alive.

Starship is the largest flying object ever made! It's a crazy time to be alive.

Tesla Owners Silicon Valley

99,510 次观看 • 1 年前

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

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

moondream

60,524 次观看 • 8 个月前

Football players detection + tracking using Ultralytics YOLO26 ⚽️ It took me 30 minutes to train the YOLO26 model on a custom dataset using Ultralytics Platform. Later, I used the object tracker (Bytetrack) for tracking the players; tracking could be improved further, and I am working on it this week. More info 👇 #soccer #football #MachineLearning

Football players detection + tracking using Ultralytics YOLO26 ⚽️ It took me 30 minutes to train the YOLO26 model on a custom dataset using Ultralytics Platform. Later, I used the object tracker (Bytetrack) for tracking the players; tracking could be improved further, and I am working on it this week. More info 👇 #soccer #football #MachineLearning

Muhammad Rizwan Munawar

42,237 次观看 • 1 个月前

An object in motion stays in motion

An object in motion stays in motion

tallyberry

255,461 次观看 • 8 个月前

What is Magnus effect? When a small amount of spin is added to a dropped object, the object moves forward ...

What is Magnus effect? When a small amount of spin is added to a dropped object, the object moves forward ...

The Figen

823,631 次观看 • 1 年前

New Moondream 2B release! 🌛 visual reasoning (!!) 🌜better object detection 🌛 improved UI understanding 🌜40% faster text generation

New Moondream 2B release! 🌛 visual reasoning (!!) 🌜better object detection 🌛 improved UI understanding 🌜40% faster text generation

vik

83,838 次观看 • 11 个月前

Blender has officially became industry standard as from 4.1 further it will be possible to select object hierarchy by doubleclicking the object icon in the outliner💪 #b3d

Blender has officially became industry standard as from 4.1 further it will be possible to select object hierarchy by doubleclicking the object icon in the outliner💪 #b3d

Pavel Oliva 🔶

80,631 次观看 • 2 年前

Gender and sexuality studies . . . First you will become My object. After that, anything is possible.

Gender and sexuality studies . . . First you will become My object. After that, anything is possible.

Ōkimi Rei Yamazawa SF Bay Area

24,369 次观看 • 1 年前

The plantar grasp reflex is found in infants of humans and most primates. When an object is placed close to a foot, the toes will close reflexively, as the object is grasped via palmar grasp.

The plantar grasp reflex is found in infants of humans and most primates. When an object is placed close to a foot, the toes will close reflexively, as the object is grasped via palmar grasp.

Massimo

116,524 次观看 • 1 年前

What is the bright object that comes into view ~10 seconds into the video?

What is the bright object that comes into view ~10 seconds into the video?

Prof. Brian Keating

23,893 次观看 • 6 个月前

If you're working with Blender and Marvelous Designer and noticing some weird normal shading, its most likely due to Custom Split Normals. In your Object Data Properties, navigate to Geometry Data and clear the custom split normals data that was imported to resolve it.

If you're working with Blender and Marvelous Designer and noticing some weird normal shading, its most likely due to Custom Split Normals. In your Object Data Properties, navigate to Geometry Data and clear the custom split normals data that was imported to resolve it.

Pilgrim

13,814 次观看 • 11 个月前

The GeoAI Python package now supports object detection using pre-trained models from the GeoDeep libarary ( The supported object types include cars, trees, birds, planes, aerovision, utilities, buildings, and roads. Try it out: GitHub: Notebook example: #geospatial #geoai #opensource #python

The GeoAI Python package now supports object detection using pre-trained models from the GeoDeep libarary ( The supported object types include cars, trees, birds, planes, aerovision, utilities, buildings, and roads. Try it out: GitHub: Notebook example: #geospatial #geoai #opensource #python

Qiusheng Wu

86,855 次观看 • 2 个月前

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: 🧵👇

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: 🧵👇

NVIDIA AI Developer

26,238 次观看 • 3 年前

In the latest #camkeys update you can set custom FOV **PER-OBJECT**

In the latest #camkeys update you can set custom FOV PER-OBJECT

Beyond Dev - Tyler Walker

80,495 次观看 • 6 个月前