Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Score Studio won't be limited to the models trained (past, present or future) on the subnet. You'll be able to run the rest of the computer vision stack in the same app. This is our quantized SAM3, used inside Score Studio, on Djokovic vs Nadal from the 2013 US...

webuildscore's profile picture

Score

9,873 subscribers

21,084 görüntüleme • 20 gün önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

3 Yorum

Jesus Martinez profil fotoğrafı
Jesus Martinez20 gün önce

would've been dope if the video tracked the ball & a counter on hits, etc.

Björn (τ, τ) 🇫🇷 profil fotoğrafı
Björn (τ, τ) 🇫🇷20 gün önce

Bad news for anyone planning to run naked across a tennis court in the future: Score will probably find you. 😂 Jokes aside, I genuinely struggle to see a future where this technology isn't widely adopted. The number of potential use cases for intelligent video analysis is insane — and Bittensor can continuously push the underlying models forward. Score is building something special.

Kian ($/acc) profil fotoğrafı
Kian ($/acc)20 gün önce

the tracking is just beauitful

Benzer Videolar

When we started Score, the standard computer vision tools already existed. About a million people use them every day. Most of those people are still waiting on labels, running training jobs by hand, and watching models fail once they leave the test set. Most of those people are still waiting on labels, running training jobs by hand, and watching models fail once they leave the test set. Most of those people are also still waiting on verified computer vision models, evaluated against real life conditions and ready to be deployed for them to deliver value for their teams, clients or users. Score Studio is the full computer vision path in one place. A team describes the problem. The system can generate the missing scenes, label them, train the candidates, evaluate which ones actually hold, and deploy the winner. Data, labels, training, eval, ship. One loop. If no model exists for that job yet, they can put a bounty on the subnet. Anything from a small vision brick to a full VLM. Miners compete on the task. Only the winning work comes back. Same path for software agents. Any agent can call it. Built to be fully agent-accessible. Built for the people who already do this work: computer vision engineers and the small teams around them in plants, warehouses, farms, robotics, sport, and security. And for the agents those teams will run. That is the part that changes the job. Not another training screen. The stretch that used to take a lab and a calendar, footage, boxes, versions, failed runs, a separate deploy project, sits behind one starting point. And if the network needs a new model, that request is part of the same path. We spent more than a year building it. Then we had a choice. Keep it for us, or commoditize the whole subnet and make it available 24/7, in permissionless and open-source way. And we knew we couldn't keep it for us. It had to live on Bittensor. Open source software already showed how this should work. Infrastructure should not sit inside one company. Same idea as open AI before the phrase changed meaning: inspect it, fork it, keep building. That is what SN44 is for. Open vision intelligence, powered by Bittensor. Miners do the work. Studio is how that gets monetized. Profit does not stay in a company account. It goes back into the subnet through buyback and burn. We built the tool we wanted on day one. It will live on the network now, and for ever. Waitlist is open.
1:11

When we started Score, the standard computer vision tools already existed. About a million people use them every day. Most of those people are still waiting on labels, running training jobs by hand, and watching models fail once they leave the test set. Most of those people are still waiting on labels, running training jobs by hand, and watching models fail once they leave the test set. Most of those people are also still waiting on verified computer vision models, evaluated against real life conditions and ready to be deployed for them to deliver value for their teams, clients or users. Score Studio is the full computer vision path in one place. A team describes the problem. The system can generate the missing scenes, label them, train the candidates, evaluate which ones actually hold, and deploy the winner. Data, labels, training, eval, ship. One loop. If no model exists for that job yet, they can put a bounty on the subnet. Anything from a small vision brick to a full VLM. Miners compete on the task. Only the winning work comes back. Same path for software agents. Any agent can call it. Built to be fully agent-accessible. Built for the people who already do this work: computer vision engineers and the small teams around them in plants, warehouses, farms, robotics, sport, and security. And for the agents those teams will run. That is the part that changes the job. Not another training screen. The stretch that used to take a lab and a calendar, footage, boxes, versions, failed runs, a separate deploy project, sits behind one starting point. And if the network needs a new model, that request is part of the same path. We spent more than a year building it. Then we had a choice. Keep it for us, or commoditize the whole subnet and make it available 24/7, in permissionless and open-source way. And we knew we couldn't keep it for us. It had to live on Bittensor. Open source software already showed how this should work. Infrastructure should not sit inside one company. Same idea as open AI before the phrase changed meaning: inspect it, fork it, keep building. That is what SN44 is for. Open vision intelligence, powered by Bittensor. Miners do the work. Studio is how that gets monetized. Profit does not stay in a company account. It goes back into the subnet through buyback and burn. We built the tool we wanted on day one. It will live on the network now, and for ever. Waitlist is open.

Score

11,292 görüntüleme • 28 gün önce

Roboflow charges you for models you have to verify yourself. Introducing Score Studio: the decentralised alternative where every model arrives already proven and ready to work in real world conditions. Every model on the platform is battle-tested through SN44's validation mechanism before you ever touch it. Miners compete, validators score, only the winners survive. You get the output of a permanent open competition, at a fraction of the price. Datasets, annotation, training, deployment. All of it cheaper. All of it validated, accurate and efficient. Need a model that doesn't exist yet? Launch your own model inquiry from the Studio and put the network to work on it. Pay in USD or SN44, straight at subnet level. We're putting the final touches on it now.
2:14

Roboflow charges you for models you have to verify yourself. Introducing Score Studio: the decentralised alternative where every model arrives already proven and ready to work in real world conditions. Every model on the platform is battle-tested through SN44's validation mechanism before you ever touch it. Miners compete, validators score, only the winners survive. You get the output of a permanent open competition, at a fraction of the price. Datasets, annotation, training, deployment. All of it cheaper. All of it validated, accurate and efficient. Need a model that doesn't exist yet? Launch your own model inquiry from the Studio and put the network to work on it. Pay in USD or SN44, straight at subnet level. We're putting the final touches on it now.

Score

35,258 görüntüleme • 1 ay önce

John Wick scenes are one of the hardest to track. we ran our subnet vision models on one of them. Shot at night, barely any light. The camera whipping around, cars sliding sideways, people cutting through the gaps, all of it smeared with motion blur. this is the footage most models fall apart on. Ours held it. every car and every person detected, outlined, and tracked, each one carried under its own ID from the moment it enters frame to the moment it leaves. thousands of unique tracks across the clip, through the dark and the chaos, without losing the thread. And the model doing it is smaller than you would ever guess. no giant model, no cloud.
0:55

John Wick scenes are one of the hardest to track. we ran our subnet vision models on one of them. Shot at night, barely any light. The camera whipping around, cars sliding sideways, people cutting through the gaps, all of it smeared with motion blur. this is the footage most models fall apart on. Ours held it. every car and every person detected, outlined, and tracked, each one carried under its own ID from the moment it enters frame to the moment it leaves. thousands of unique tracks across the clip, through the dark and the chaos, without losing the thread. And the model doing it is smaller than you would ever guess. no giant model, no cloud.

Score

22,195 görüntüleme • 23 gün önce

Rob Wright, who Adam Finkelstein expects to be one of the best point guards on the market this year, is likely to command a premium given the limited star power at the position in the portal. "Rob Wright could become one of the highest-paid players in the sport..." Travis Branham Louisville and Kentucky are two programs Branham is currently monitoring.
2:34

Rob Wright, who Adam Finkelstein expects to be one of the best point guards on the market this year, is likely to command a premium given the limited star power at the position in the portal. "Rob Wright could become one of the highest-paid players in the sport..." Travis Branham Louisville and Kentucky are two programs Branham is currently monitoring.

247Sports

97,720 görüntüleme • 5 ay önce

Gilbert Arenas on the NBA vs 1v1 players debate: "The benefit in a one-on-one style goes to the one-on-one player. Your NBA credentials has no weight in a one-on-one game... So Nas, or any of those guys, they will have the upper hand on an NBA player."
0:24

Gilbert Arenas on the NBA vs 1v1 players debate: "The benefit in a one-on-one style goes to the one-on-one player. Your NBA credentials has no weight in a one-on-one game... So Nas, or any of those guys, they will have the upper hand on an NBA player."

Ballislife.com

590,988 görüntüleme • 4 ay önce

Our stock Quad-Motor R1S is the first production EV to complete the Rubicon Trail, one of the most challenging off-road trails in North America. Thanks to Rubicon Trail Foundation for working to keep the trail open and sustainable. Details on the historic run:
0:33

Our stock Quad-Motor R1S is the first production EV to complete the Rubicon Trail, one of the most challenging off-road trails in North America. Thanks to Rubicon Trail Foundation for working to keep the trail open and sustainable. Details on the historic run:

Rivian

160,863 görüntüleme • 3 yıl önce

.SnowflakeDB is thrilled to announce #SnowflakeArctic: A state-of-the-art large language model uniquely designed to be the most open, enterprise-grade LLM on the market. This is a big step forward for open source LLMs. And it’s a big moment for Snowflake in our #AI journey as we continue to build best-in-class enterprise-grade products for our customers. The era of enterprise AI is here. 🚀
1:04

.SnowflakeDB is thrilled to announce #SnowflakeArctic: A state-of-the-art large language model uniquely designed to be the most open, enterprise-grade LLM on the market. This is a big step forward for open source LLMs. And it’s a big moment for Snowflake in our #AI journey as we continue to build best-in-class enterprise-grade products for our customers. The era of enterprise AI is here. 🚀

sridhar

243,849 görüntüleme • 2 yıl önce

Since history is also the study of change, thinking about the future gives us a perspective on the present, in much the same way as studying the past. Watch the whole interview on PoliticsJOE:
0:25

Since history is also the study of change, thinking about the future gives us a perspective on the present, in much the same way as studying the past. Watch the whole interview on PoliticsJOE:

Yuval Noah Harari

29,235 görüntüleme • 11 ay önce

The bank is open 💰 This #SoFiPlayIn Tournament, players banked 16 shots. And those baskets netted SoFi Plus members $10 each in rewards points, for a total of $160! There’s still time to score—be one of the first 5,000 eligible fans to sign up from 4/10/25–4/30/25. Go to to get in on the action.
1:35

The bank is open 💰 This #SoFiPlayIn Tournament, players banked 16 shots. And those baskets netted SoFi Plus members $10 each in rewards points, for a total of $160! There’s still time to score—be one of the first 5,000 eligible fans to sign up from 4/10/25–4/30/25. Go to to get in on the action.

NBA

118,193 görüntüleme • 1 yıl önce

No one else can do this. While every other CV platform is still selling another fine-tuning dashboard We’re about to let anyone order actual frontier lab work in a few clicks. The kind only Bittensor miners can deliver. Model Foundry is coming to Score Studio. Zero compute? Zero data? Zero ML team? Doesn’t matter. You describe the hard vision problem, our miners build the production model, you pay inside the Studio. That spend goes straight into SN44 buyback + burn. Money never leaves the subnet. No gatekeepers. No bottlenecks. Just open frontier vision for everyone. Check out the Model Foundry flow 👇
1:08

No one else can do this. While every other CV platform is still selling another fine-tuning dashboard We’re about to let anyone order actual frontier lab work in a few clicks. The kind only Bittensor miners can deliver. Model Foundry is coming to Score Studio. Zero compute? Zero data? Zero ML team? Doesn’t matter. You describe the hard vision problem, our miners build the production model, you pay inside the Studio. That spend goes straight into SN44 buyback + burn. Money never leaves the subnet. No gatekeepers. No bottlenecks. Just open frontier vision for everyone. Check out the Model Foundry flow 👇

Score

24,327 görüntüleme • 1 ay önce

ITV has commissioned #TheGoldenElevators, a high-stakes new quiz show hosted by Richard Osman, produced by Studio Lambert and Talpa Studios. Set in the lobby of a towering skyscraper, every question presents two possible answers, each represented by an elevator. Before the doors close, players can confer, debate, persuade and mislead. Then they choose. Step into the correct lift and move closer to the top. Step into the wrong one and everyone inside is plunged straight to the lobby and out of the game. Hear more from Richard on this brand new show on today’s The Rest Is Entertainment podcast! 📻
1:08

ITV has commissioned #TheGoldenElevators, a high-stakes new quiz show hosted by Richard Osman, produced by Studio Lambert and Talpa Studios. Set in the lobby of a towering skyscraper, every question presents two possible answers, each represented by an elevator. Before the doors close, players can confer, debate, persuade and mislead. Then they choose. Step into the correct lift and move closer to the top. Step into the wrong one and everyone inside is plunged straight to the lobby and out of the game. Hear more from Richard on this brand new show on today’s The Rest Is Entertainment podcast! 📻

Studio Lambert

12,163 görüntüleme • 4 ay önce

Dartmouth 6’9 Point Forward Brandon Mitchell-Day is one of the most intriguing prospects in the 2026 NBA Draft Mitchell-Day was one of the best players in the Ivy League this season as a Junior who averaged 14/8/3 on 51/34/80 splits. While being one of the best defenders, passers and scorers in the conference at 6’9 Mitchell-Day has a unique mix of playmaking, defensive versatility, finishing, shot creation, and shooting upside that not a lot of players his height have. He’s also a strong athlete. He’s a strong off ball player as well, shooting 65% as a cutter and roll man, having a lot of versatility on the court. Mitchell-Day is set to be one of the best players in the Ivy League as one of the few all conference players returning, and has a chance to rise on draft boards with a strong season.
2:54

Dartmouth 6’9 Point Forward Brandon Mitchell-Day is one of the most intriguing prospects in the 2026 NBA Draft Mitchell-Day was one of the best players in the Ivy League this season as a Junior who averaged 14/8/3 on 51/34/80 splits. While being one of the best defenders, passers and scorers in the conference at 6’9 Mitchell-Day has a unique mix of playmaking, defensive versatility, finishing, shot creation, and shooting upside that not a lot of players his height have. He’s also a strong athlete. He’s a strong off ball player as well, shooting 65% as a cutter and roll man, having a lot of versatility on the court. Mitchell-Day is set to be one of the best players in the Ivy League as one of the few all conference players returning, and has a chance to rise on draft boards with a strong season.

KJ

19,662 görüntüleme • 1 yıl önce

The 17th at Ganton Golf Club is one of the longest par 3's in the country, measuring a mighty 246 yards from the back tees. A fantastic tee shot is required to get on the green in regulation on this hole and par is a great score.
0:20

The 17th at Ganton Golf Club is one of the longest par 3's in the country, measuring a mighty 246 yards from the back tees. A fantastic tee shot is required to get on the green in regulation on this hole and par is a great score.

Ganton Golf Club

33,474 görüntüleme • 7 ay önce

An hour of lab evals catches a model that doesn't work. It won't catch one that fails once every two hundred trials, or degrades over a week, or runs fine on this robot and badly on the one beside it. So the eval moved to where the work is. Every episode, every site, graded on the customer's definition of good. Over a terabyte a day, autolabelled into SOP steps, outcomes, and failure modes. Today, a new Dyna deployment goes from setup to production ROI in as little as three days. This is just scratching the surface. Also - we're hiring across deployment research:
0:34

An hour of lab evals catches a model that doesn't work. It won't catch one that fails once every two hundred trials, or degrades over a week, or runs fine on this robot and badly on the one beside it. So the eval moved to where the work is. Every episode, every site, graded on the customer's definition of good. Over a terabyte a day, autolabelled into SOP steps, outcomes, and failure modes. Today, a new Dyna deployment goes from setup to production ROI in as little as three days. This is just scratching the surface. Also - we're hiring across deployment research:

Dyna Robotics

11,455 görüntüleme • 27 gün önce

Polo, a behind-the-scenes look at the fast-paced and glamorous world of the sport, is coming to Netflix on December 10. Follow elite global players on and off the field as they compete in the high-stakes U.S. Open Polo Championship. From executive producers Prince Harry and Meghan, The Duke and Duchess of Sussex.
2:18

Polo, a behind-the-scenes look at the fast-paced and glamorous world of the sport, is coming to Netflix on December 10. Follow elite global players on and off the field as they compete in the high-stakes U.S. Open Polo Championship. From executive producers Prince Harry and Meghan, The Duke and Duchess of Sussex.

Netflix

712,611 görüntüleme • 1 yıl önce

Most AI tools give everyone access to the same generic models. The result? Everything looks the same. We have a different vision for AI creation. Introducing TITLES, a new creative studio built around AI models trained and owned by artists. In Studio, you can create with distinct visual perspectives developed by artists, across image and video — all in one place. This is the future we're building toward: not one model for everyone, but a growing network of unique styles you can build with — where artists get credited and paid as the work spreads. Enter Your Creative Studio:
0:23

Most AI tools give everyone access to the same generic models. The result? Everything looks the same. We have a different vision for AI creation. Introducing TITLES, a new creative studio built around AI models trained and owned by artists. In Studio, you can create with distinct visual perspectives developed by artists, across image and video — all in one place. This is the future we're building toward: not one model for everyone, but a growing network of unique styles you can build with — where artists get credited and paid as the work spreads. Enter Your Creative Studio:

TITLES

2,748,246 görüntüleme • 5 ay önce

AI TENNIS ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, PYTORCH, AND KEYPOINT EXTRACTION. Take any tennis match broadcast, any camera angle, any resolution. Feed it into the pipeline. YOLO detects both players and the tennis ball frame by frame. No manual labeling, no pre-annotated dataset. A fine-tuned YOLOv5 model trained on a Roboflow tennis ball dataset handles the ball - the hardest object to track in any sport. Tiny, fast, constantly occluded. The model finds it anyway. Trackers maintain identity across frames so Player 1 stays Player 1 from the first serve to match point. But detection is just the start. A ResNet50 CNN trained in PyTorch predicts court keypoints from every frame - the corners, service lines, baselines, net posts. Fourteen points that define the entire playing surface geometry. From those keypoints the system builds a homography matrix and warps the broadcast perspective into a top-down mini court with real coordinates. Now every player has a position in real space, not pixel space. Every frame becomes a measurement. Every rally becomes a dataset. Player movement speed - calculated from position deltas between frames, converted to meters per second through the homography. Ball shot speed - measured from the ball trajectory across consecutive detections. Number of shots per rally - counted automatically through ball direction changes. All of this rendered live on the video as an overlay. A mini court in the corner showing both players as dots moving in real time. Stats updating after every point. OpenCV handles the rendering. Pandas handles the math. PyTorch handles the intelligence. YOLO handles the eyes. No Hawkeye subscription, no court-embedded sensors, no tracking chips in the ball. A Python script, a trained model, and a GPU. The full code is on GitHub. The tutorial walks through every module - from ball detector training to court keypoint extraction to the final statistical overlay. Professional teams used to need broadcast deals and proprietary hardware for this kind of analysis. Now you build it in an afternoon with open-source tools. Trading here: Computer vision didn't just enter tennis. It made the expensive stuff free.
4:41:24

AI TENNIS ANALYSIS. A FULL COMPUTER VISION SYSTEM. BUILT ON YOLO, PYTORCH, AND KEYPOINT EXTRACTION. Take any tennis match broadcast, any camera angle, any resolution. Feed it into the pipeline. YOLO detects both players and the tennis ball frame by frame. No manual labeling, no pre-annotated dataset. A fine-tuned YOLOv5 model trained on a Roboflow tennis ball dataset handles the ball - the hardest object to track in any sport. Tiny, fast, constantly occluded. The model finds it anyway. Trackers maintain identity across frames so Player 1 stays Player 1 from the first serve to match point. But detection is just the start. A ResNet50 CNN trained in PyTorch predicts court keypoints from every frame - the corners, service lines, baselines, net posts. Fourteen points that define the entire playing surface geometry. From those keypoints the system builds a homography matrix and warps the broadcast perspective into a top-down mini court with real coordinates. Now every player has a position in real space, not pixel space. Every frame becomes a measurement. Every rally becomes a dataset. Player movement speed - calculated from position deltas between frames, converted to meters per second through the homography. Ball shot speed - measured from the ball trajectory across consecutive detections. Number of shots per rally - counted automatically through ball direction changes. All of this rendered live on the video as an overlay. A mini court in the corner showing both players as dots moving in real time. Stats updating after every point. OpenCV handles the rendering. Pandas handles the math. PyTorch handles the intelligence. YOLO handles the eyes. No Hawkeye subscription, no court-embedded sensors, no tracking chips in the ball. A Python script, a trained model, and a GPU. The full code is on GitHub. The tutorial walks through every module - from ball detector training to court keypoint extraction to the final statistical overlay. Professional teams used to need broadcast deals and proprietary hardware for this kind of analysis. Now you build it in an afternoon with open-source tools. Trading here: Computer vision didn't just enter tennis. It made the expensive stuff free.

zostaff

121,478 görüntüleme • 5 ay önce

Up, Back and Through Possession 5v2 in the area in which the ball is. 🔵 Target is to get the ball from one end player to another. The ball must go through the central player on the line. The ball will either go into the central player, who will set to the run of one of the two wide players, or he will set back to the other midfielder who will again look for the run of a wide midfielder (Up, Back and Through). Both wingers will be on the outside lines of the half with the ball, when the ball is transferred the central player will move into the new area, one defender will follow into the other half and the two wingers will follow to create the 5v2. Made on TacticalPad® Tactical ✭ Competitive Tender.  JUST COACH Lloyd Owers The Sporting Resource The Coaching Family @RJPcoach @ExchangeCoaches TheBeardedCoach @205_Sports Coach Siya Maloka SessionShare Charlie Huyton Felix Lehmann @FootballTrnng Tom Skeath Breakthrough Soccer @become_excel
0:24

Up, Back and Through Possession 5v2 in the area in which the ball is. 🔵 Target is to get the ball from one end player to another. The ball must go through the central player on the line. The ball will either go into the central player, who will set to the run of one of the two wide players, or he will set back to the other midfielder who will again look for the run of a wide midfielder (Up, Back and Through). Both wingers will be on the outside lines of the half with the ball, when the ball is transferred the central player will move into the new area, one defender will follow into the other half and the two wingers will follow to create the 5v2. Made on TacticalPad® Tactical ✭ Competitive Tender.  JUST COACH Lloyd Owers The Sporting Resource The Coaching Family @RJPcoach @ExchangeCoaches TheBeardedCoach @205_Sports Coach Siya Maloka SessionShare Charlie Huyton Felix Lehmann @FootballTrnng Tom Skeath Breakthrough Soccer @become_excel

Conor Edwards

144,015 görüntüleme • 2 yıl önce

It's not every day that a DePIN project partners with a $20B+ revenue giant. Valeo is one of the biggest players in the automotive industry 🚗 Together, we're building one of the largest open-source multi-camera World Foundation Models for the future of Physical AI 💪
0:57

It's not every day that a DePIN project partners with a $20B+ revenue giant. Valeo is one of the biggest players in the automotive industry 🚗 Together, we're building one of the largest open-source multi-camera World Foundation Models for the future of Physical AI 💪

NATIX Network

16,219 görüntüleme • 7 ay önce