Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Created an automatic motion blur effect for Tennis using Computer Vision 🎾 Any other visualization ideas for Roland Garros ? 🙂 Tech side: I used Tracknet + YOLOs

Alexandre Devaux

7,774 subscribers

35,165 views • 1 year ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Enhanced my Tennis Viz for Roland Garros! With live player distance tracking, a top-view heatmap, and speed-dependent motion blur. I should run it for a complete game. I wonder how many kilometers they run in a Game?! 🎾

Enhanced my Tennis Viz for Roland Garros! With live player distance tracking, a top-view heatmap, and speed-dependent motion blur. I should run it for a complete game. I wonder how many kilometers they run in a Game?! 🎾

Alexandre Devaux

24,594 views • 1 year ago

With M5, Vision Pro can increase the refresh rate up to 120Hz for reduced motion blur when users look at their physical surroundings, and an even smoother experience when using Mac Virtual Display.

With M5, Vision Pro can increase the refresh rate up to 120Hz for reduced motion blur when users look at their physical surroundings, and an even smoother experience when using Mac Virtual Display.

Aaron

120,984 views • 10 months ago

I just created my own LaTeX-OCR app using Llama 3.2 Vision! Upload the LaTeX code as an image, and it gives you the corresponding LaTeX code using Llama 3.2 multimodal! Here's what I used: - Ollama for serving Llama 3.2 vision locally - Streamlit for the UI Everything is just 50 lines of code! Find the code in the next tweet. -- Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs. Find me → Avi Chawla

I just created my own LaTeX-OCR app using Llama 3.2 Vision! Upload the LaTeX code as an image, and it gives you the corresponding LaTeX code using Llama 3.2 multimodal! Here's what I used: - Ollama for serving Llama 3.2 vision locally - Streamlit for the UI Everything is just 50 lines of code! Find the code in the next tweet. -- Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs. Find me → Avi Chawla

Avi Chawla

15,628 views • 1 year ago

An unexpected side effect that travelling abroad in Greece had for my knowledge of the Classics was a better understanding of Aristophanes. Famously he used the onomatopoeia Βρεκεκέξ ("brekekekex") for the chorus of "The Frogs". In the ruins of ancient Dion, I heard them:

An unexpected side effect that travelling abroad in Greece had for my knowledge of the Classics was a better understanding of Aristophanes. Famously he used the onomatopoeia Βρεκεκέξ ("brekekekex") for the chorus of "The Frogs". In the ruins of ancient Dion, I heard them:

Derek | The Hellenistic Age Podcast

128,610 views • 4 months ago

"Gnome Show", an original series project created by Cas van de Pol (known for his parody videos). Pilot episode >> He's used to working with other indie animators, and I note that Mehdi Alibeygi has joined his team here.

"Gnome Show", an original series project created by Cas van de Pol (known for his parody videos). Pilot episode >> He's used to working with other indie animators, and I note that Mehdi Alibeygi has joined his team here.

Catsuka

79,670 views • 4 months ago

i trained this computer vision model just by asking for "tennis players", using roboflow rapid and SAM3 the model picks out Alcaraz and Sinner, while correctly avoiding the ball boys and fans then I exported the model to python and wrote a script to filter the data, track movement history, and annotate the final video this was a quick experiment but I could expand the project to track player speeds, distance covered, shot count, etc. could use this for a sports analytics app that tracks live matches and calculates custom metrics

i trained this computer vision model just by asking for "tennis players", using roboflow rapid and SAM3 the model picks out Alcaraz and Sinner, while correctly avoiding the ball boys and fans then I exported the model to python and wrote a script to filter the data, track movement history, and annotate the final video this was a quick experiment but I could expand the project to track player speeds, distance covered, shot count, etc. could use this for a sports analytics app that tracks live matches and calculates custom metrics

AA

293,837 views • 9 months ago

Holliday Fun Fact #10 by dashing up ramps immediately after using jump pad you can store your ground slam. any changes in elevation or jumps will cause it to immediately activate I never use this tech as its too niche and situational for an employed person to use

Holliday Fun Fact #10 by dashing up ramps immediately after using jump pad you can store your ground slam. any changes in elevation or jumps will cause it to immediately activate I never use this tech as its too niche and situational for an employed person to use

Holliday "HereComesBarrel" Deadlock

40,899 views • 11 months ago

🥽 Want to use your new Apple Vision Pro to control your robot? Want to record how you navigate / manipulate the world to train a policy? I developed an app for VisionOS that can stream your head / wrist / finger movements over WiFi, which you can subscribe on any machines using a simple python library. 🧵[1/6]

🥽 Want to use your new Apple Vision Pro to control your robot? Want to record how you navigate / manipulate the world to train a policy? I developed an app for VisionOS that can stream your head / wrist / finger movements over WiFi, which you can subscribe on any machines using a simple python library. 🧵[1/6]

Younghyo Park

214,278 views • 2 years ago

Michael "I am a conservative INTELLECTUAL thought leader" Knowles, but the only argument I have is... none? Instead, I let my team scroll through hundreds of comments to find the one posted by an account not located in the USA so I can create the illusion of an op that doesn’t exist. I am still not intelligent enough to consider that what this person says could be true regardless of where they live, that free speech doesn’t stop at America’s borders, that X wasn’t created only for Americans, and that what America does has an effect on the entire world - or simply that the account could be American and temporarily outside the United States, whether on vacation or for any number of other reasons. (Knowles has now done this a dozen times, and the fact that he thinks this is some kind of smart gotcha makes me feel embarrassed for him.)

Michael "I am a conservative INTELLECTUAL thought leader" Knowles, but the only argument I have is... none? Instead, I let my team scroll through hundreds of comments to find the one posted by an account not located in the USA so I can create the illusion of an op that doesn’t exist. I am still not intelligent enough to consider that what this person says could be true regardless of where they live, that free speech doesn’t stop at America’s borders, that X wasn’t created only for Americans, and that what America does has an effect on the entire world - or simply that the account could be American and temporarily outside the United States, whether on vacation or for any number of other reasons. (Knowles has now done this a dozen times, and the fact that he thinks this is some kind of smart gotcha makes me feel embarrassed for him.)

diana bloom

37,854 views • 21 days ago

sorry Jake let me explain a bit more about my work in my advertising agency: because we work with big clients, we run a lot of tests, especially with AI why do I use a famous actor for my internal tests? because a well-known face is instantly recognisable and easy to share to clients, you immediately understand the expressions, the acting style, and whether the generation is efficient or not it helps us judge the quality of the tool of course, I know the ethical side is complicated these tests are strictly internal, purely experimental, and never used for commercial purposes. using someone’s likeness without consent is completely forbidden, and I fully respect that i’m just sharing this video as an example of a technical test I generated by mistake, not for any public or commercial use what do you think of it? the tech is powerful, but it needs to be handled responsibly

sorry Jake let me explain a bit more about my work in my advertising agency: because we work with big clients, we run a lot of tests, especially with AI why do I use a famous actor for my internal tests? because a well-known face is instantly recognisable and easy to share to clients, you immediately understand the expressions, the acting style, and whether the generation is efficient or not it helps us judge the quality of the tool of course, I know the ethical side is complicated these tests are strictly internal, purely experimental, and never used for commercial purposes. using someone’s likeness without consent is completely forbidden, and I fully respect that i’m just sharing this video as an example of a technical test I generated by mistake, not for any public or commercial use what do you think of it? the tech is powerful, but it needs to be handled responsibly

INK

71,124 views • 9 months ago

Check out this Stereo4D paper from Google DeepMind. It's a pretty clever approach to a persistent problem in computer vision -- getting good training data for how things move in 3D. The key insight is using VR180 videos -- those stereo fisheye videos we launched back in 2017 for YouTubeVR. It was always clear that structured stereo datasets would be valuable for computer vision -- and we launched some powerful VR tools with it back in 2017 (link below). But what's the game changer now in 2024 is the scale -- they're providing 110K high quality clips :-) That's the kind of massive, real-world AI dataset that was just a dream back then! They're using it to train this model called DynaDUSt3R that can predict both 3D structure and motion from video frames. Which means it tracks how objects move between frames while simultaneously reconstructing their 3D shape. And given we're dealing with real stereoscopic content, results are notably better than synthetic data, giving you a faithful rendition of the real-world with a diverse set of subject matter. It's one of those through lines when tackling a timeless mission like mapping the world or spatial computing -- VR content created for immersion becoming the foundation for teaching machines to understand how the world moves. Sometimes innovation chains together in unexpected ways! Links to projects below⛓️

Check out this Stereo4D paper from Google DeepMind. It's a pretty clever approach to a persistent problem in computer vision -- getting good training data for how things move in 3D. The key insight is using VR180 videos -- those stereo fisheye videos we launched back in 2017 for YouTubeVR. It was always clear that structured stereo datasets would be valuable for computer vision -- and we launched some powerful VR tools with it back in 2017 (link below). But what's the game changer now in 2024 is the scale -- they're providing 110K high quality clips :-) That's the kind of massive, real-world AI dataset that was just a dream back then! They're using it to train this model called DynaDUSt3R that can predict both 3D structure and motion from video frames. Which means it tracks how objects move between frames while simultaneously reconstructing their 3D shape. And given we're dealing with real stereoscopic content, results are notably better than synthetic data, giving you a faithful rendition of the real-world with a diverse set of subject matter. It's one of those through lines when tackling a timeless mission like mapping the world or spatial computing -- VR content created for immersion becoming the foundation for teaching machines to understand how the world moves. Sometimes innovation chains together in unexpected ways! Links to projects below⛓️

Bilawal Sidhu

68,515 views • 1 year ago

I didn’t sleep last night - I’m building Netflix for my cats. 🐈📺 It’s an on-device AI agent that plays videos based on their mood. Runs on my Raspberry Pi - uses camera + sound + motion to figure out if they’re bored, anxious, or curious. right now it's on my monitor. soon they’ll have their own display that turns on automatically when I’m not home. It’s funny, but it works. would love any ideas or suggestions you think could make it better. 😸

I didn’t sleep last night - I’m building Netflix for my cats. 🐈📺 It’s an on-device AI agent that plays videos based on their mood. Runs on my Raspberry Pi - uses camera + sound + motion to figure out if they’re bored, anxious, or curious. right now it's on my monitor. soon they’ll have their own display that turns on automatically when I’m not home. It’s funny, but it works. would love any ideas or suggestions you think could make it better. 😸

Pankaj

38,090 views • 10 months ago

I’ve spent nearly two decades in front of the camera, with about 15 years working for other people and various companies. I used to model high fashion regularly, even walking runways for top designers. Over time, my look shifted from the “typical” model aesthetic to something I love even more. Turns out, I like to eat and lift, so my body naturally changed 😛 Now, at 35, I’m shooting concepts and ideas that reflect my own creativity and vision. Wearing looks that make me feel powerful. Embracing age and muscle. Blending my past with my present. Getting weird. Keeping it fun. What do you think of this look? #photoshoot #bts #fashion

I’ve spent nearly two decades in front of the camera, with about 15 years working for other people and various companies. I used to model high fashion regularly, even walking runways for top designers. Over time, my look shifted from the “typical” model aesthetic to something I love even more. Turns out, I like to eat and lift, so my body naturally changed 😛 Now, at 35, I’m shooting concepts and ideas that reflect my own creativity and vision. Wearing looks that make me feel powerful. Embracing age and muscle. Blending my past with my present. Getting weird. Keeping it fun. What do you think of this look? #photoshoot #bts #fashion

Janna Breslin

36,642 views • 1 year ago

Made a quick haptic feedback prototype for hand-tracking interactions with a voxel. Felt fun and engaging. It's another level of immersiveness (unfortunately, the video is not able to convey this). Visual design alone can make an interactive experience great, but if you want to make it exceptional, DIFFERENT, this is where haptic design plays the key role. The device on my wrist is from the Hapticlabs.io Prototyping Kit (the thing on my index fingertip is called Linear Resonant Actuator). It's a beautiful, simple-to-use tool. Found a good case for it in my experiments :) To get hand-tracking data, I used the Leap Motion controller (Computer Vision Camera), which is excellent for quick prototypes like this. I saw people experimenting with gloves to build a solid haptic feedback system for XR. It's great for advanced immersive experiences (video games/simulators/interactive entertainment). But for many day-to-day use cases (productivity/OS/media entertainment), having just a "simple" thimble that provides the haptic feedback for the "touching" fingertip will already significantly improve the UX. Hope we will have something like this from our major XR vendors in the near future.

Made a quick haptic feedback prototype for hand-tracking interactions with a voxel. Felt fun and engaging. It's another level of immersiveness (unfortunately, the video is not able to convey this). Visual design alone can make an interactive experience great, but if you want to make it exceptional, DIFFERENT, this is where haptic design plays the key role. The device on my wrist is from the Hapticlabs.io Prototyping Kit (the thing on my index fingertip is called Linear Resonant Actuator). It's a beautiful, simple-to-use tool. Found a good case for it in my experiments :) To get hand-tracking data, I used the Leap Motion controller (Computer Vision Camera), which is excellent for quick prototypes like this. I saw people experimenting with gloves to build a solid haptic feedback system for XR. It's great for advanced immersive experiences (video games/simulators/interactive entertainment). But for many day-to-day use cases (productivity/OS/media entertainment), having just a "simple" thimble that provides the haptic feedback for the "touching" fingertip will already significantly improve the UX. Hope we will have something like this from our major XR vendors in the near future.

Oleg Frolov

35,579 views • 9 months ago

Our game won Chroma Awards! Two people (one without any game dev experience) used 404's tech to generate over 12,000 3D assets and create an immersive game in one month! Awards like this help us showcase how AI will have such an incredible impact on the creative industries by democratizing who can create and what is possible. We'll publish more shots of the game, how to play and where it's going - but for now, check out the official entry to learn more about the concept and creation process: And view some of the 6500+ other entries of the competition!

Our game won Chroma Awards! Two people (one without any game dev experience) used 404's tech to generate over 12,000 3D assets and create an immersive game in one month! Awards like this help us showcase how AI will have such an incredible impact on the creative industries by democratizing who can create and what is possible. We'll publish more shots of the game, how to play and where it's going - but for now, check out the official entry to learn more about the concept and creation process: And view some of the 6500+ other entries of the competition!

404

48,507 views • 8 months ago

I try my best to not talk about Irish politics, but getting sent things like this by my Garda friends just angers me too much. This happened today. The police (Gardai) in Ireland have been attacked and bullied by scumbags for years now. They know they can get away with it. Stripped of any power to do anything about it. The Gardai are trained to retreat and not engage when violence breaks out. This is what happens when you remove your police forces ability to police. The Gardai voted with an enormous majority vote of no confidence against the head of the Gardai. Our minister for justice ignored them. Overworked, underpayed, and stripped of any protection in policing. I know policing in America is a sore topic for good reason. Ye are on the other side of the spectrum. Too much power. This is what happens when you swing to the other side. Chaos. I’m ashamed of how Ireland is being governed. A failed socialist state. It’s why I left, and it’s why I won’t be going back any time soon. Helen McEntee, you need to resign.

I try my best to not talk about Irish politics, but getting sent things like this by my Garda friends just angers me too much. This happened today. The police (Gardai) in Ireland have been attacked and bullied by scumbags for years now. They know they can get away with it. Stripped of any power to do anything about it. The Gardai are trained to retreat and not engage when violence breaks out. This is what happens when you remove your police forces ability to police. The Gardai voted with an enormous majority vote of no confidence against the head of the Gardai. Our minister for justice ignored them. Overworked, underpayed, and stripped of any protection in policing. I know policing in America is a sore topic for good reason. Ye are on the other side of the spectrum. Too much power. This is what happens when you swing to the other side. Chaos. I’m ashamed of how Ireland is being governed. A failed socialist state. It’s why I left, and it’s why I won’t be going back any time soon. Helen McEntee, you need to resign.

Brian Mac Mághnais

120,624 views • 2 years ago

I don't really like dogs. I am physically challenged and can't walk properly and they bark at me for different walking. But these days I am becoming more and more fond of them because of them. It all started when their mother was pregnant and my mom used to give her milk every morning and evening. After they were born first they used to come with their mother and now their mother sees them having milk and let them have it. That's the other story but why I am liking them? Because they know my office timings. When I go to office and start my scooty they run from wherever they are and start dancing around my scooty. Then my mother gives them milk and they get to a side and I can go. In the evening they listen to my honking and run from wherever they are and again gather around my scooty trying to play with me. Sometimes I am afraid so that they don't get run over. But as usual milk comes and they get to a side and I can enter my home. Other than my family members they are also waiting for me. And I am loving it 🙂❤️

I don't really like dogs. I am physically challenged and can't walk properly and they bark at me for different walking. But these days I am becoming more and more fond of them because of them. It all started when their mother was pregnant and my mom used to give her milk every morning and evening. After they were born first they used to come with their mother and now their mother sees them having milk and let them have it. That's the other story but why I am liking them? Because they know my office timings. When I go to office and start my scooty they run from wherever they are and start dancing around my scooty. Then my mother gives them milk and they get to a side and I can go. In the evening they listen to my honking and run from wherever they are and again gather around my scooty trying to play with me. Sometimes I am afraid so that they don't get run over. But as usual milk comes and they get to a side and I can enter my home. Other than my family members they are also waiting for me. And I am loving it 🙂❤️

Sandeep Thakur

14,513 views • 7 months ago

✨ I revived my first AI startup from 6 years ago with Claude Code [ 💡 ] Back then it used GPT-3 (this was 2 years before ChatGPT existed!) to generate new startup ideas which then people can vote on And the best startup ideas rise to the top! Back then I made it because people complained they didn't have any ideas to build a startup This week I moved it to its own VPS and installed Claude Code and told it to fix everything, the DB had become big and there was stupid write operations on every page load that it made it very slow Claude Code is excellent at fixing all those small bugs from old projects and quickly fixing them As Garry Tan says "boil the oceans" as in before I'd not have the time to fix these kinds of projects, it wouldn't be worth it, I mean IdeasAI doesn't even make money, but now it takes me an hour to do this and it works again! I also upgraded GPT-3 to xAI's Grok 4.2 for new startup ideas

✨ I revived my first AI startup from 6 years ago with Claude Code [ 💡 ] Back then it used GPT-3 (this was 2 years before ChatGPT existed!) to generate new startup ideas which then people can vote on And the best startup ideas rise to the top! Back then I made it because people complained they didn't have any ideas to build a startup This week I moved it to its own VPS and installed Claude Code and told it to fix everything, the DB had become big and there was stupid write operations on every page load that it made it very slow Claude Code is excellent at fixing all those small bugs from old projects and quickly fixing them As Garry Tan says "boil the oceans" as in before I'd not have the time to fix these kinds of projects, it wouldn't be worth it, I mean IdeasAI doesn't even make money, but now it takes me an hour to do this and it works again! I also upgraded GPT-3 to xAI's Grok 4.2 for new startup ideas

@levelsio

180,039 views • 5 months ago

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!

Akshay 🚀

126,213 views • 10 months ago

DeCAF won the #ICML Test of Time Award 2024! Big congrats to trevordarrell (my PhD advisor at MIT), and Jeff Donahue. 🎉 You may not heard of DeCAF, but it is everywhere! DeCAF stands for Deep Convolutional Activation Features. Published ten years ago, the DeCAF paper is a groundbreaking work that shows the activation features of the last few layers of a deep network contain useful features that can be "repurposed" for or "transferred to" many other tasks, not just the original task the network was trained for. I created this exercise to show where we can see DeCAF's influence in some of the most well-known architectures: AlexNet, ViT, U-Net, CLIP, and Latent Diffusion, to prove that DeCAF's "Test of Time Award" is well-deserved! Let's give a round of applause to DeCAF, the unsung hero of computer vision.

DeCAF won the #ICML Test of Time Award 2024! Big congrats to trevordarrell (my PhD advisor at MIT), and Jeff Donahue. 🎉 You may not heard of DeCAF, but it is everywhere! DeCAF stands for Deep Convolutional Activation Features. Published ten years ago, the DeCAF paper is a groundbreaking work that shows the activation features of the last few layers of a deep network contain useful features that can be "repurposed" for or "transferred to" many other tasks, not just the original task the network was trained for. I created this exercise to show where we can see DeCAF's influence in some of the most well-known architectures: AlexNet, ViT, U-Net, CLIP, and Latent Diffusion, to prove that DeCAF's "Test of Time Award" is well-deserved! Let's give a round of applause to DeCAF, the unsung hero of computer vision.

Tom Yeh

21,420 views • 2 years ago