Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Agricultural Field Boundary Delineation (Instance Segmentation) with GeoAI Learn an end-to-end GeoAI workflow for agricultural field boundary delineation using instance segmentation and the Fields of the World dataset ( This workflow can be adapted to detect other object types (not just field boundaries) as long as training data is...

giswqs's profile picture

Qiusheng Wu

52,747 subscribers

20,008 görüntüleme • 4 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

🚀 The GeoAI QGIS Plugin is here 🔥 You can run Moondream vision-language models, object detection, image segmentation (SAM 3), and even train your own geospatial segmentation model end-to-end. Website: GitHub: Short demo: Full video tutorial: #QGIS #GeoAI #SAM3 #Geospatial #DeepLearning #ComputerVision #OpenSource #Python
2:11

🚀 The GeoAI QGIS Plugin is here 🔥 You can run Moondream vision-language models, object detection, image segmentation (SAM 3), and even train your own geospatial segmentation model end-to-end. Website: GitHub: Short demo: Full video tutorial: #QGIS #GeoAI #SAM3 #Geospatial #DeepLearning #ComputerVision #OpenSource #Python

Qiusheng Wu

11,738 görüntüleme • 7 ay önce

QGIS GeoAI Plugin v0.5.0 is out! I just released v0.5.0 of the QGIS GeoAI Plugin, bringing interactive image segmentation powered by DeepForest ( to your desktop GIS workflow. With this update, you can load pretrained DeepForest models to segment real-world objects such as trees, birds, livestock, dead trees, and more, directly inside QGIS. Try it out: Documentation: GitHub: #deepforest #geoai #QGIS #geospatial #OpenSource
0:23

QGIS GeoAI Plugin v0.5.0 is out! I just released v0.5.0 of the QGIS GeoAI Plugin, bringing interactive image segmentation powered by DeepForest ( to your desktop GIS workflow. With this update, you can load pretrained DeepForest models to segment real-world objects such as trees, birds, livestock, dead trees, and more, directly inside QGIS. Try it out: Documentation: GitHub: #deepforest #geoai #QGIS #geospatial #OpenSource

Qiusheng Wu

21,385 görüntüleme • 6 ay önce

🚀 GeoAI Tutorial 23: Building Detection from Aerial Imagery and LiDAR Data 🏙️🛰️ In this tutorial, I demonstrate how to train a deep learning segmentation model for building detection by combining aerial/satellite imagery with LiDAR data. You'll learn how to fuse multi-source remote sensing data to improve model accuracy and robustness. 🔗 Tutorial video: 📓 Notebook example: 💻 GitHub repo: 📚 Documentation: 🎥 Full playlist: #GeoAI #geospatial #AI #Python #DeepLearning
0:21

🚀 GeoAI Tutorial 23: Building Detection from Aerial Imagery and LiDAR Data 🏙️🛰️ In this tutorial, I demonstrate how to train a deep learning segmentation model for building detection by combining aerial/satellite imagery with LiDAR data. You'll learn how to fuse multi-source remote sensing data to improve model accuracy and robustness. 🔗 Tutorial video: 📓 Notebook example: 💻 GitHub repo: 📚 Documentation: 🎥 Full playlist: #GeoAI #geospatial #AI #Python #DeepLearning

Qiusheng Wu

12,252 görüntüleme • 1 yıl önce

🚀 GeoAI Tutorial 12: Wetland Mapping with Deep Learning and GeoAI! 🌍 Unlock the power of your geospatial data! Learn to train an wetland detection model and run inference on large datasets—all with just a few lines of code. 🎥 Watch the full tutorial here: 📓 Explore the notebook: 🛠️ Check out the GitHub repository: 📚 Dive into the documentation: 📺 Check out the entire YouTube playlist: #GeoAI #geospatial #AI #Python #DeepLearning
0:20

🚀 GeoAI Tutorial 12: Wetland Mapping with Deep Learning and GeoAI! 🌍 Unlock the power of your geospatial data! Learn to train an wetland detection model and run inference on large datasets—all with just a few lines of code. 🎥 Watch the full tutorial here: 📓 Explore the notebook: 🛠️ Check out the GitHub repository: 📚 Dive into the documentation: 📺 Check out the entire YouTube playlist: #GeoAI #geospatial #AI #Python #DeepLearning

Qiusheng Wu

16,623 görüntüleme • 1 yıl önce

Tracking Anything with Decoupled Video Segmentation paper page: Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation.
0:32

Tracking Anything with Decoupled Video Segmentation paper page: Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation.

AK

305,683 görüntüleme • 2 yıl önce

🎯 AI Agents for Microsoft Planetary Computer: Explore Satellite Data with Zero Code Unlock satellite data without writing a single line of code! 🌍 In this step-by-step tutorial, you’ll discover how to harness the power of AI agents to search, filter, and visualize geospatial datasets from the Microsoft Planetary Computer — all using natural language. Perfect for researchers, developers, and environmental professionals who want fast, intuitive, code-free access to massive Earth observation datasets like Sentinel-2, Landsat, NAIP, and DEM. Learn how to: ✅ Use zero-code AI agents in Jupyter Notebooks ✅ Search satellite imagery by date, location, or cloud cover ✅ Visualize data instantly using Leafmap ✅ Integrate STAC data catalogs into your GeoAI workflow Full video tutorial available on YouTube: #geospatial #GeoAI #opensource #PlanetaryComputer
1:12

🎯 AI Agents for Microsoft Planetary Computer: Explore Satellite Data with Zero Code Unlock satellite data without writing a single line of code! 🌍 In this step-by-step tutorial, you’ll discover how to harness the power of AI agents to search, filter, and visualize geospatial datasets from the Microsoft Planetary Computer — all using natural language. Perfect for researchers, developers, and environmental professionals who want fast, intuitive, code-free access to massive Earth observation datasets like Sentinel-2, Landsat, NAIP, and DEM. Learn how to: ✅ Use zero-code AI agents in Jupyter Notebooks ✅ Search satellite imagery by date, location, or cloud cover ✅ Visualize data instantly using Leafmap ✅ Integrate STAC data catalogs into your GeoAI workflow Full video tutorial available on YouTube: #geospatial #GeoAI #opensource #PlanetaryComputer

Qiusheng Wu

10,346 görüntüleme • 9 ay önce

An AI assistant for Google Earth Engine is now available in QGIS! You can explore and visualize any dataset from the 80+ PB Earth Engine Data Catalog using natural language, and run scalable geospatial analysis on demand without writing code. Every interaction automatically generates reusable code, making it easy to reproduce results, customize workflows, and transition from no-code to full scripting when needed. Upgrade the plugin to get started and bring AI-powered geospatial analytics directly into your QGIS workflow. GitHub: QGIS plugin: GeoAgent: #EarthEngine #QGIS #OpenSource #GeoAI #Geospatial
1:11

An AI assistant for Google Earth Engine is now available in QGIS! You can explore and visualize any dataset from the 80+ PB Earth Engine Data Catalog using natural language, and run scalable geospatial analysis on demand without writing code. Every interaction automatically generates reusable code, making it easy to reproduce results, customize workflows, and transition from no-code to full scripting when needed. Upgrade the plugin to get started and bring AI-powered geospatial analytics directly into your QGIS workflow. GitHub: QGIS plugin: GeoAgent: #EarthEngine #QGIS #OpenSource #GeoAI #Geospatial

Qiusheng Wu

17,453 görüntüleme • 3 ay önce

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:
4:17

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:

Andrew Ng

151,198 görüntüleme • 2 yıl önce

Over in Japan, there's also a small, niche industry for high-end denim. It can't be overstated how much of this is rooted in the region, not easily transferrable to other areas. For instance, some of this production can get very artisanal, such as hand-dyed denim.
11:07

Over in Japan, there's also a small, niche industry for high-end denim. It can't be overstated how much of this is rooted in the region, not easily transferrable to other areas. For instance, some of this production can get very artisanal, such as hand-dyed denim.

derek guy

29,670 görüntüleme • 1 yıl önce

⚽ Colombia and the United States may not be meeting on the soccer field anytime soon, but firefighters from Colombia recently took the field with CAL FIRE. The training field, that is. Firefighters from Colombia visited CAL FIRE’s Columbia Helitack Base near Sonora, CA to learn more about how CAL FIRE uses helicopters for aerial firefighting, water drops, and rescue operations. Colombia recently purchased multiple helicopters for firefighting and rescue missions and reached out to CAL FIRE to learn from one of the largest aerial firefighting programs in the world. #CALFIRE #InternationalPartnership #WildfireResponse #Aviation
2:10

⚽ Colombia and the United States may not be meeting on the soccer field anytime soon, but firefighters from Colombia recently took the field with CAL FIRE. The training field, that is. Firefighters from Colombia visited CAL FIRE’s Columbia Helitack Base near Sonora, CA to learn more about how CAL FIRE uses helicopters for aerial firefighting, water drops, and rescue operations. Colombia recently purchased multiple helicopters for firefighting and rescue missions and reached out to CAL FIRE to learn from one of the largest aerial firefighting programs in the world. #CALFIRE #InternationalPartnership #WildfireResponse #Aviation

CAL FIRE

10,273 görüntüleme • 23 gün önce

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.
0:33

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

AK

122,560 görüntüleme • 3 yıl önce

The white men's mindset, where they believe they can overcome any obstacle just because their skin is white, as they may not perceive the racist systemic advantages that have made their path easier, comes to an end when on the playing field with black athletes.
2:51

The white men's mindset, where they believe they can overcome any obstacle just because their skin is white, as they may not perceive the racist systemic advantages that have made their path easier, comes to an end when on the playing field with black athletes.

kevin blue

44,823 görüntüleme • 5 ay önce

.Google DeepMind is powering a new agricultural landscape understanding layer in Google Earth for portions of the Asia-Pacific region to bring powerful data to our iconic imagery. Leveraging machine learning and satellite imagery, this data layer is able to visualize the ""atomic units"" of agriculture: individual field boundaries. This model doesn't just delineate fields; it determines acreage and identifies critical landscape elements like water bodies and vegetation. Use these granular insights to: ✅ Calculate specific acreage. ✅ Identify water resources for drought contingency planning. ✅ Deliver insights at the farm level, not just the regional level. Go from regional aggregates to atomic units. Get the insights that inspire action. #GoogleEarth #GoogleDeepMind #AI
0:21

.Google DeepMind is powering a new agricultural landscape understanding layer in Google Earth for portions of the Asia-Pacific region to bring powerful data to our iconic imagery. Leveraging machine learning and satellite imagery, this data layer is able to visualize the ""atomic units"" of agriculture: individual field boundaries. This model doesn't just delineate fields; it determines acreage and identifies critical landscape elements like water bodies and vegetation. Use these granular insights to: ✅ Calculate specific acreage. ✅ Identify water resources for drought contingency planning. ✅ Deliver insights at the farm level, not just the regional level. Go from regional aggregates to atomic units. Get the insights that inspire action. #GoogleEarth #GoogleDeepMind #AI

Google Earth

231,504 görüntüleme • 6 ay önce

“[Nebraska tight end coach Marcus Satterfield] said, ‘Mike, I think this guy is going to be playing in the NFL and his best football as a tight end won’t be with us at Nebraska.” - Mike Schaefer Heinrich Haarberg is proving on and off the field that he remains an impact player for the Huskers. Presented by Centris Federal Credit Union.
2:00

“[Nebraska tight end coach Marcus Satterfield] said, ‘Mike, I think this guy is going to be playing in the NFL and his best football as a tight end won’t be with us at Nebraska.” - Mike Schaefer Heinrich Haarberg is proving on and off the field that he remains an impact player for the Huskers. Presented by Centris Federal Credit Union.

Hurrdat Sports

47,583 görüntüleme • 9 ay önce

Exciting update on PantheonOS: Introducing Pantheon-Notebook & Pantheon-CLI — the first fully open-source, Python-based agentic tools that go beyond Claude Code in the field of data analysis. Pantheon-CLI runs entirely on your computer or server, supports 60+ tools and 50+ databases, and can call any Python, R, or Julia package alongside natural language. Chat with your data directly. It look like python-claude-code, but more appreciate for data analysis. Pantheon-Notebook brings the same agentic framework into Jupyter! Not just for writing code, it can also run and revise code automatically to generate the correct result, and even operate on files and study from website — beyond what any other tool can do! With Pantheon, you mix natural language + programming in one workflow, focusing on discovery instead of syntax barriers. We've applied Pantheon in some real-world cases: finance (customer explore), biology (Seurat, cell segmentation, annotation), sociology (survey analysis), and drug discovery (molecular docking). Pantheon is not just a CLI or a plugin — it's an agentic operating system for science, spanning both terminal and notebook. Why not try it now? We are actively preparing publications from this series of projects. Major contributors will be recognized in our GitHub repository and listed as key authors in these manuscripts. Feel free to reach out for collaborations, research assistant positions, visiting opportunities, rotation project or future PhD projects.
1:16

Exciting update on PantheonOS: Introducing Pantheon-Notebook & Pantheon-CLI — the first fully open-source, Python-based agentic tools that go beyond Claude Code in the field of data analysis. Pantheon-CLI runs entirely on your computer or server, supports 60+ tools and 50+ databases, and can call any Python, R, or Julia package alongside natural language. Chat with your data directly. It look like python-claude-code, but more appreciate for data analysis. Pantheon-Notebook brings the same agentic framework into Jupyter! Not just for writing code, it can also run and revise code automatically to generate the correct result, and even operate on files and study from website — beyond what any other tool can do! With Pantheon, you mix natural language + programming in one workflow, focusing on discovery instead of syntax barriers. We've applied Pantheon in some real-world cases: finance (customer explore), biology (Seurat, cell segmentation, annotation), sociology (survey analysis), and drug discovery (molecular docking). Pantheon is not just a CLI or a plugin — it's an agentic operating system for science, spanning both terminal and notebook. Why not try it now? We are actively preparing publications from this series of projects. Major contributors will be recognized in our GitHub repository and listed as key authors in these manuscripts. Feel free to reach out for collaborations, research assistant positions, visiting opportunities, rotation project or future PhD projects.

evo-devo

45,640 görüntüleme • 11 ay önce

For a decade this guy played dumb and acted like he just didn't understand XRP. Now he aggressively attacks XRP. Same with Caitlin Long. What's changed? Why now? Just as we approach the level regulatory playing field. Just as the Bitcoin regulatory monopoly is about to end. XRP was contained by regulatory capture so they didn't need to attack it until now. The fear is real.
0:52

For a decade this guy played dumb and acted like he just didn't understand XRP. Now he aggressively attacks XRP. Same with Caitlin Long. What's changed? Why now? Just as we approach the level regulatory playing field. Just as the Bitcoin regulatory monopoly is about to end. XRP was contained by regulatory capture so they didn't need to attack it until now. The fear is real.

Digital Asset Investor

45,470 görüntüleme • 11 ay önce

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.
4:28

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

AK

140,624 görüntüleme • 3 yıl önce

A hundred children, some barely old enough to walk straight, being drilled in combat tactics while dressed as jihadist fighters in an open training field. All to fight and murder Israelis and die as martyrs. This is not a movie. This is the factory producing the next generation of suicide bombers and terrorists. The world watches. Radical Islamists prepare. When will we stop pretending this is ‘just culture’?
0:44

A hundred children, some barely old enough to walk straight, being drilled in combat tactics while dressed as jihadist fighters in an open training field. All to fight and murder Israelis and die as martyrs. This is not a movie. This is the factory producing the next generation of suicide bombers and terrorists. The world watches. Radical Islamists prepare. When will we stop pretending this is ‘just culture’?

Mor Edge Insight

26,391 görüntüleme • 2 ay önce

Hot Route Glitch is PATCHED in CFB26 🚨 You can no longer flip your formation and obtain TE/HB routes with your WRs as they pass them. This also applies to reversed routes that did not flip as they cross to the other side of the field.
0:35

Hot Route Glitch is PATCHED in CFB26 🚨 You can no longer flip your formation and obtain TE/HB routes with your WRs as they pass them. This also applies to reversed routes that did not flip as they cross to the other side of the field.

Ace

37,793 görüntüleme • 1 yıl önce

New short course on LLMOps! LLMOps (large language model operations) is a rapidly developing field that takes ideas from MLOps (machine learning operations) and specializes them to building and deploying LLM-based applications. In this course, taught by Google Cloud's Erwin Huizenga, you'll learn to use automation to make building, tuning and deploying an LLM-based application less manual and more efficient. You'll learn how to: - Apply supervised fine-tuning to tune an LLM to a specific task - Automate and orchestrate LLM-tuning and deployment by customizing a pre-built tuning pipeline - Apply best practices for preparing training data for supervised fine-tuning of an LLM - Create an LLMOps workflow you can adapt to other LLM-tuning jobs This course doesn't assume any prior MLOps or LLMOps experience. Sign up here to learn about this emerging field!
2:11

New short course on LLMOps! LLMOps (large language model operations) is a rapidly developing field that takes ideas from MLOps (machine learning operations) and specializes them to building and deploying LLM-based applications. In this course, taught by Google Cloud's Erwin Huizenga, you'll learn to use automation to make building, tuning and deploying an LLM-based application less manual and more efficient. You'll learn how to: - Apply supervised fine-tuning to tune an LLM to a specific task - Automate and orchestrate LLM-tuning and deployment by customizing a pre-built tuning pipeline - Apply best practices for preparing training data for supervised fine-tuning of an LLM - Create an LLMOps workflow you can adapt to other LLM-tuning jobs This course doesn't assume any prior MLOps or LLMOps experience. Sign up here to learn about this emerging field!

Andrew Ng

221,803 görüntüleme • 2 yıl önce