Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

I'm experimenting with using SAM2 for automatic tracking of NBA players; it's mind-blowing how well this model performs out of the box. we might even add a SAM2-based tracker to the trackers package at some point. trackers:

skalskip92's profile picture

SkalskiP @ CVPR2026

45,938 subscribers

292,965 Aufrufe • vor 1 Jahr •via X (Twitter)

GamingSportWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von SkalskiP
SkalskiPvor 1 Jahr

I found this SAM2 fork that addresses my main issue with the original implementation—it allows running SAM2 on video streams!

Profilbild von SkalskiP
SkalskiPvor 1 Jahr

the results aren’t perfect every time, but a cool idea would be to use SAM2 for automatic labeling of datasets for object detection, instance segmentation, or tracking.

Profilbild von SkalskiP
SkalskiPvor 1 Jahr

if you want to learn more about SAM2 and how to use it for image and video segmentation, here’s a link to my stream from a few months ago.

Profilbild von Brandon Tyler
Brandon Tylervor 1 Jahr

So cool! Looking for stats analytics for basketball. I use @veotechnologies but they don’t offer basketball and the ai teaching is so expensive

Profilbild von SkalskiP
SkalskiPvor 1 Jahr

@veotechnologies stay tuned I’ll be dropping more demos over the next few weeks

Profilbild von phillpafford
phillpaffordvor 1 Jahr

This is awesome, any volleyball efforts?

Profilbild von SkalskiP
SkalskiPvor 1 Jahr

not from me… but I saw some people on X playing with volleyball usecases

Profilbild von HiFi-Ai / Tom Laroc
HiFi-Ai / Tom Larocvor 1 Jahr

@ImgMotion

Profilbild von uɐɥdǝʇS
uɐɥdǝʇSvor 1 Jahr

yeah it’s bananas

Profilbild von Darin
Darinvor 1 Jahr

Can you segment each player at the joints?

Profilbild von SkalskiP
SkalskiPvor 1 Jahr

what to you mean by „joints”?

Ähnliche Videos

✨ CVPR 2025 highlight: A Distractor-Aware Memory for Visual Object Tracking with SAM2 the authors propose a new distractor-aware memory model for SAM2 and an introspection-based update strategy that jointly addresses the segmentation accuracy as well as tracking robustness 🏡 (1/n)🧵👇
0:34

✨ CVPR 2025 highlight: A Distractor-Aware Memory for Visual Object Tracking with SAM2 the authors propose a new distractor-aware memory model for SAM2 and an introspection-based update strategy that jointly addresses the segmentation accuracy as well as tracking robustness 🏡 (1/n)🧵👇

GeekyRakshit (e/mad)

32,669 Aufrufe • vor 1 Jahr

more magic/AI mesh selection, this one w/ SAM2 which takes an initial box/points instead of a text prompt. SAM2 is much faster, in 'stream' mode I can send it frames like it's processing a video (this capture is 1x, SAM2 running locally on 8GB 3070ti).
0:41

more magic/AI mesh selection, this one w/ SAM2 which takes an initial box/points instead of a text prompt. SAM2 is much faster, in 'stream' mode I can send it frames like it's processing a video (this capture is 1x, SAM2 running locally on 8GB 3070ti).

Ryan Schmidt

21,203 Aufrufe • vor 24 Tagen

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware check out this SAM2 vs SAMURAI comparison! - paper: - code: - license: Apache-2.0
0:25

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware check out this SAM2 vs SAMURAI comparison! - paper: - code: - license: Apache-2.0

SkalskiP

124,358 Aufrufe • vor 1 Jahr

🎋MOCOPI vs VIVE TRACKERS🎋 I got a crazy crazy upgrade on full body tracking thanks to the support of my bambuds, so I made a silly dance comparison to compare the tracking between my old FBT and my new one!! ✨ I danced Bibbidiba by Suisei! (ft. bae as my guide lol) I had to use a different model for the Vive comparison because my Toffee model doesn't work well with the trackers! PROS AND CONS 🔽 1. Mocopi is SO MUCH EASIER to set up! It's very very beginner friendly as well and a great asset to get if you're just starting on doing 3D stuff or want to try it out! Vive trackers are lowkey a pain to set up each time! 2. Vive trackers are EXPENSIIIVEEEE!!!!! The tracking is so so so good but only invest in it if you plan to do lots of 3D content! Mocopi is a much affordable option! 3. Related to point 2, but you get what you pay for when it comes to tracking. Vive may be more expensive, but the tracking quality and accuracy makes it worth it. 4. This is only for people that don't have the Valve Headset, but I use a Quest 3 and I have to do EXTRA SETUP to calibrate the trackers with an external program to use in VRChat! (Mocopi also needs an external program (SlimeVR) but it's much easier to set up imo). 5. Since calibration is paired to your headset with the vive trackers, if your headset goes to sleep or something the calibration will be LOST and you will have to recalibrate again which may take 1 to 2 minutes. Mocopi doesn't have this issue and recalibrating is only one button. 6. Mocopi is an IMU so no base stations required but because of this the trackers need to be recalibrated A LOT of times. This may be annoying if you're streaming and you constantly have to press the button to recalibrate. Vive trackers may take longer but you VERY RARELY have to recalibrate if your headset doesn't go to sleep. 7. Vive trackers take a lot of space on your setup. Each tracker needs to be connected to the PC so if you have a lot you may need to buy an USD hub! 8. You need to have a good room space to use vive trackers properly because the base stations need to have a clear view of your trackers or else they can lose tracking! Mocopi is an IMU, so no amount of obstruction will make the trackers lose tracking. 9. The amount of poses and movement that you can do with vive trackers is NIGHT AND DAY compared to the mocopi. A lot of poses or rapid movements will make the mocopis mess up their tracking and you will have to recalibrate. Vive trackers will not need any recalibration. Basically if you're a vtuber that only wants to dabble into 3D content as a fun little thing I think mocopis are very much a good choice! But if you'd like to do 3D stuff that require more intensive tracking like dancing, vive trackers are excellent and very much worth the price!
0:40

🎋MOCOPI vs VIVE TRACKERS🎋 I got a crazy crazy upgrade on full body tracking thanks to the support of my bambuds, so I made a silly dance comparison to compare the tracking between my old FBT and my new one!! ✨ I danced Bibbidiba by Suisei! (ft. bae as my guide lol) I had to use a different model for the Vive comparison because my Toffee model doesn't work well with the trackers! PROS AND CONS 🔽 1. Mocopi is SO MUCH EASIER to set up! It's very very beginner friendly as well and a great asset to get if you're just starting on doing 3D stuff or want to try it out! Vive trackers are lowkey a pain to set up each time! 2. Vive trackers are EXPENSIIIVEEEE!!!!! The tracking is so so so good but only invest in it if you plan to do lots of 3D content! Mocopi is a much affordable option! 3. Related to point 2, but you get what you pay for when it comes to tracking. Vive may be more expensive, but the tracking quality and accuracy makes it worth it. 4. This is only for people that don't have the Valve Headset, but I use a Quest 3 and I have to do EXTRA SETUP to calibrate the trackers with an external program to use in VRChat! (Mocopi also needs an external program (SlimeVR) but it's much easier to set up imo). 5. Since calibration is paired to your headset with the vive trackers, if your headset goes to sleep or something the calibration will be LOST and you will have to recalibrate again which may take 1 to 2 minutes. Mocopi doesn't have this issue and recalibrating is only one button. 6. Mocopi is an IMU so no base stations required but because of this the trackers need to be recalibrated A LOT of times. This may be annoying if you're streaming and you constantly have to press the button to recalibrate. Vive trackers may take longer but you VERY RARELY have to recalibrate if your headset doesn't go to sleep. 7. Vive trackers take a lot of space on your setup. Each tracker needs to be connected to the PC so if you have a lot you may need to buy an USD hub! 8. You need to have a good room space to use vive trackers properly because the base stations need to have a clear view of your trackers or else they can lose tracking! Mocopi is an IMU, so no amount of obstruction will make the trackers lose tracking. 9. The amount of poses and movement that you can do with vive trackers is NIGHT AND DAY compared to the mocopi. A lot of poses or rapid movements will make the mocopis mess up their tracking and you will have to recalibrate. Vive trackers will not need any recalibration. Basically if you're a vtuber that only wants to dabble into 3D content as a fun little thing I think mocopis are very much a good choice! But if you'd like to do 3D stuff that require more intensive tracking like dancing, vive trackers are excellent and very much worth the price!

Toffee 🐾🎋

80,586 Aufrufe • vor 10 Monaten

Fake box office trackers of USA got exposed. Here is the ground reality with proof.
2:19

Fake box office trackers of USA got exposed. Here is the ground reality with proof.

Blue Sattai Maran

83,686 Aufrufe • vor 2 Jahren

"Aydan why don't you make videos anymore?" Why? Because over the last two years every single time I get in vr to try and film. This shit happens. It makes it so fucking hard to get motivated to do it when I can't get one locked off angle shot. Before you say something like "Have you covered all the reflective surfaces?" "Have you re-paired the trackers?" "Try replacing the lighthouses?" "Try replacing the cables?" "The Dongles might be bad?" "The Trackers might be bad?" "The Controllers might be bad?" "Try a USB hub?" "Try USB Ports?" "Try this 7-1 in one dongle hub?" "Try Tundra Trackers?" "Try This 3-1 dongle hub?" "Try pairing one controller each to a dongle, and pair the trackers to a single dongle too?" "Have you tried reinstalling the software? "Have you tried Steam VR Beta?" "Try Slime trackers?" "Try Quest Pro?" "Try less 2.4ghz band devices?" "Maybe your Wifi bulbs are interfering?" "Try Bigscreen Beyond 2e?" "Try 2 Lighthouses?" "Try 3 Lighthouses?" "Try 4 Lighthouses?" "Maybe your computers bad? Get a new one?" YES. I have fucking tried all that shit. Literally have spent thousands of dollars trouble shooting this issues. I currently own 3 tracking headsets 9 lighthouses 6 vive trackers 3 tundra trackers 8 slime trackers 5 pairs of index controllers. And I've tried on 3 different computers. I have talked to like 20 different people. No one has an answer. I'm at the end of my rope at this point. Every time I get into VR I'm filled with dread because I know I'm going to get mad or frustrated. I'm just...sad. I want to make content, but I don't fucking know what to do at this point.
1:08

"Aydan why don't you make videos anymore?" Why? Because over the last two years every single time I get in vr to try and film. This shit happens. It makes it so fucking hard to get motivated to do it when I can't get one locked off angle shot. Before you say something like "Have you covered all the reflective surfaces?" "Have you re-paired the trackers?" "Try replacing the lighthouses?" "Try replacing the cables?" "The Dongles might be bad?" "The Trackers might be bad?" "The Controllers might be bad?" "Try a USB hub?" "Try USB Ports?" "Try this 7-1 in one dongle hub?" "Try Tundra Trackers?" "Try This 3-1 dongle hub?" "Try pairing one controller each to a dongle, and pair the trackers to a single dongle too?" "Have you tried reinstalling the software? "Have you tried Steam VR Beta?" "Try Slime trackers?" "Try Quest Pro?" "Try less 2.4ghz band devices?" "Maybe your Wifi bulbs are interfering?" "Try Bigscreen Beyond 2e?" "Try 2 Lighthouses?" "Try 3 Lighthouses?" "Try 4 Lighthouses?" "Maybe your computers bad? Get a new one?" YES. I have fucking tried all that shit. Literally have spent thousands of dollars trouble shooting this issues. I currently own 3 tracking headsets 9 lighthouses 6 vive trackers 3 tundra trackers 8 slime trackers 5 pairs of index controllers. And I've tried on 3 different computers. I have talked to like 20 different people. No one has an answer. I'm at the end of my rope at this point. Every time I get into VR I'm filled with dread because I know I'm going to get mad or frustrated. I'm just...sad. I want to make content, but I don't fucking know what to do at this point.

Aydan

12,663 Aufrufe • vor 3 Monaten

"There's a total of 51,801,803 [Ordinals]... image trackers... that's... more than a third of the entire UTXO set. So almost 40% of your entire Bitcoin live state... almost half of that is being used as a data tracker for some NFT." ~ The Shitcoin Insider
0:40

"There's a total of 51,801,803 [Ordinals]... image trackers... that's... more than a third of the entire UTXO set. So almost 40% of your entire Bitcoin live state... almost half of that is being used as a data tracker for some NFT." ~ The Shitcoin Insider

Guy Swann

16,218 Aufrufe • vor 5 Monaten

Using our smart insoles as foot trackers in VRChat With our OSC server we can stream motion and pressure data into #VRChat *Our insoles are 3DoF (just orientation, no position) We fixed the feet to the ground for demonstration, but they’re best used alongside other trackers Special thanks to Duinrahaic for helping out with debugging
1:06

Using our smart insoles as foot trackers in VRChat With our OSC server we can stream motion and pressure data into #VRChat *Our insoles are 3DoF (just orientation, no position) We fixed the feet to the ground for demonstration, but they’re best used alongside other trackers Special thanks to Duinrahaic for helping out with debugging

Brilliant Wear

111,764 Aufrufe • vor 1 Jahr

Rep. Nancy Mace: "The American people in South Carolina, we're okay now with the conflict and how well it's gone for President Trump, but at some point the American people are going to want to know the full extent of the purpose of this conflict and how soon we can get out."
2:23

Rep. Nancy Mace: "The American people in South Carolina, we're okay now with the conflict and how well it's gone for President Trump, but at some point the American people are going to want to know the full extent of the purpose of this conflict and how soon we can get out."

Aaron Rupar

125,905 Aufrufe • vor 3 Monaten

This app category is INSANE 🤯 Habit trackers printing $30k–$200k/m It’s one of the most competitive spaces and it still doesn’t matter Everyone when getting into apps starts with either a habit tracker or a calorie tracker Yet, 99% of people fail hard because they don't distribute I built my entire app with And even attached 4 VIRAL examples of exactly how to market this niche:
0:47

This app category is INSANE 🤯 Habit trackers printing $30k–$200k/m It’s one of the most competitive spaces and it still doesn’t matter Everyone when getting into apps starts with either a habit tracker or a calorie tracker Yet, 99% of people fail hard because they don't distribute I built my entire app with And even attached 4 VIRAL examples of exactly how to market this niche:

Jah Mills

17,351 Aufrufe • vor 4 Monaten

Trackers at the ready! Midnight Jukebox gets the better of a good battle with fellow Point-to-Point scorer Smokehouse and are chased home by the closing Sea Tempest to make a winning debut under rules for the Fergal O'Brien Racing team... Southwell Racecourse | Jonathan Burke
0:39

Trackers at the ready! Midnight Jukebox gets the better of a good battle with fellow Point-to-Point scorer Smokehouse and are chased home by the closing Sea Tempest to make a winning debut under rules for the Fergal O'Brien Racing team... Southwell Racecourse | Jonathan Burke

At The Races

10,441 Aufrufe • vor 4 Monaten

Want to feel the touch of other's in #VRChat ? Don't want to pay a fortune for a haptic vest? Do you already have Vive trackers? Now you can feel everything using your trackers, a cheap vibration motor, and a 3D printed #HapticPancake Guide:
0:33

Want to feel the touch of other's in #VRChat ? Don't want to pay a fortune for a haptic vest? Do you already have Vive trackers? Now you can feel everything using your trackers, a cheap vibration motor, and a 3D printed #HapticPancake Guide:

Zelus Pawcake

89,431 Aufrufe • vor 2 Jahren

Unbelievably smooth and precise tracking at 4,000 mm with global shutter at 120 FPS in 4K coming to a #Starship launch near you! This is one of five human operated trackers we will have for this next launch! Incredible work on these controllers Collin Thrash!!!
0:31

Unbelievably smooth and precise tracking at 4,000 mm with global shutter at 120 FPS in 4K coming to a #Starship launch near you! This is one of five human operated trackers we will have for this next launch! Incredible work on these controllers Collin Thrash!!!

Everyday Astronaut

186,462 Aufrufe • vor 2 Jahren

Well, i don't even know how to describe this one. But i'm very happy with how it turned out Consider this as some sort of camera/action animation exercise or something (featuring Urban Tracker as usual, huns) In other news, IT'S MY BIRTHDAY AAAAAAAAAAAAAAAA #CoDMobile #CODm
0:21

Well, i don't even know how to describe this one. But i'm very happy with how it turned out Consider this as some sort of camera/action animation exercise or something (featuring Urban Tracker as usual, huns) In other news, IT'S MY BIRTHDAY AAAAAAAAAAAAAAAA #CoDMobile #CODm

LiSh Dranthon || COMMS CLOSED

30,843 Aufrufe • vor 2 Jahren

ATR Trackers at the ready! 👀 Domenico Contarini and Exmoor draw well clear of the field and it's the latter who comes out on top of a good tussle, putting his experience to good use and edging ahead close to home... Newcastle Racecourse | Andrew Balding
0:35

ATR Trackers at the ready! 👀 Domenico Contarini and Exmoor draw well clear of the field and it's the latter who comes out on top of a good tussle, putting his experience to good use and edging ahead close to home... Newcastle Racecourse | Andrew Balding

At The Races

21,962 Aufrufe • vor 3 Monaten

🚀 The Segment Anything Model (SAM) has been upgraded to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: **Highlights:** 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearch
0:22

🚀 The Segment Anything Model (SAM) has been upgraded to SAM2, featuring an efficient image encoder for segmenting images and videos. But does SAM2 outperform SAM1 in medical image and video segmentation? We're thrilled to present our paper "Segment Anything in Medical Images and Videos: Benchmark and Deployment"! We comprehensively benchmark SAM2 across 11 medical image modalities and videos. 📄 Paper: 💻 Code: **Highlights:** 1. SAM2 doesn’t always outperform SAM1 in 2D medical images, but excels in video segmentation, making it more accurate and efficient for 3D images, such as CT and MR scans. 2. MedSAM still outperforms SAM2 on most 2D modalities, but SAM2 surpasses MedSAM for 3D image segmentation in a slice-by-slice approach. 3. Segmentation performance varies with model size; sometimes the smallest model outperforms larger ones. 4. Fine-tuning SAM2 significantly boosts its performance for medical image segmentation. While SAM2 may struggle with challenging objects that have unclear boundaries or low contrast, it excels in generating good initial segmentation masks for common medical images and videos. However, the official interface doesn’t support medical data formats and has limitations on video length. To address this, we've developed a 3D Slicer Plugin and Gradio API for efficient 3D medical image and video segmentation. We invite you to try them out and provide feedback! 🔧 Deployment: - 3D Slicer Plugin: - Gradio API: (Note: Due to GPU limitations, the online API is available for only 12 hours and may be slow. We highly recommend deploying the Gradio API with your own computing resources: A big shoutout to Jun Ma (JunMa) who recently joined our UHN AI hub (UHN AI Hub) as Machine Learning Lead, and kudos to all co-authors: Sumin Kim, Feifei Li, Mohammed Baharoon (Mohammed Baharoon), Reza Asakereh, and Hongwei Lyu! This is true teamwork! Looking forward to collaborating with the community to advance 3D medical image and video segmentation foundation models! University Health Network U of T Department of Computer Science Department of Laboratory Medicine & Pathobiology Temerty Centre for AI in Medicine (T-CAIREM) Vector Institute #MedTech #AIinHealthcare #DeepLearning #MedicalImaging #SAM2 #MedSAM #AIResearch

Bo Wang

178,455 Aufrufe • vor 1 Jahr

Super excited to introduce SAM2 Studio! 🚀🤖 I've been getting a lot of questions lately on supporting AI inference tailored for patient data and sensitive workflows. We optimized SAM2 to run completely on-device in real time for all of your medical segmentation workflows - including surgical video segmentation, radiographs, pathology slides and more!
0:40

Super excited to introduce SAM2 Studio! 🚀🤖 I've been getting a lot of questions lately on supporting AI inference tailored for patient data and sensitive workflows. We optimized SAM2 to run completely on-device in real time for all of your medical segmentation workflows - including surgical video segmentation, radiographs, pathology slides and more!

Cyril Zakka, MD

19,814 Aufrufe • vor 1 Jahr

This is for those trackers who are so ILLITERATE that they can’t even understand a simple explanation. Watch the whole video till the end. Tamil Twitter trackers should have some shame or basic comprehension skills because they have neither. Aura Myruaa nu!!! #Thuglife
0:57

This is for those trackers who are so ILLITERATE that they can’t even understand a simple explanation. Watch the whole video till the end. Tamil Twitter trackers should have some shame or basic comprehension skills because they have neither. Aura Myruaa nu!!! #Thuglife

𝚃𝙷

141,613 Aufrufe • vor 1 Jahr

This box came all the way from Massachusetts in a minutes notice... it's the UMass Minutemen! Some great players came out of UMass, and one of my favorite actors went here too! Thank you to Coach Harasymiak and UMass Football for sending this awesome package! Go Minutemen!
4:21

This box came all the way from Massachusetts in a minutes notice... it's the UMass Minutemen! Some great players came out of UMass, and one of my favorite actors went here too! Thank you to Coach Harasymiak and UMass Football for sending this awesome package! Go Minutemen!

Jon Gruden

385,553 Aufrufe • vor 10 Monaten

📽️I realise it's a bit odd to mark the launch of a podcast with a 13m deep dive screen. But, well, maybe I'm just a bit odd. Anyway here's the story of how LEDs saved the world. And why, paradoxically, they might NOT save the world. Mind-blowing data on light, energy & more!👇
13:32

📽️I realise it's a bit odd to mark the launch of a podcast with a 13m deep dive screen. But, well, maybe I'm just a bit odd. Anyway here's the story of how LEDs saved the world. And why, paradoxically, they might NOT save the world. Mind-blowing data on light, energy & more!👇

Ed Conway

36,959 Aufrufe • vor 5 Tagen