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.

Computer vision can see what happened — agentic AI explains why it matters and what to do next. Here’s how teams are upgrading video analytics with vision language models: 🔍 Turn video into searchable intelligence 🧠 Add context and reasoning to system alerts ⚡ Summarize complex scenes and answer... show more

NVIDIA AI

267,163 subscribers

14,273 views • 6 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

ChatGPT + Computer Vision = A dictionary for what you see. By giving ChatGPT eyes, we allow it to answer questions about the world around us.

ChatGPT + Computer Vision = A dictionary for what you see. By giving ChatGPT eyes, we allow it to answer questions about the world around us.

Aaron Ng

276,267 views • 3 years ago

📁 Fei-Fei Li, computer vision pioneer and Stanford professor, says the next frontier of AI is spatial intelligence. The ability to perceive, reason and act in the physical world. Not just see and talk. But do. Just as vision triggered the Cambrian explosion of life, spatial intelligence could trigger the next explosion of AI.

📁 Fei-Fei Li, computer vision pioneer and Stanford professor, says the next frontier of AI is spatial intelligence. The ability to perceive, reason and act in the physical world. Not just see and talk. But do. Just as vision triggered the Cambrian explosion of life, spatial intelligence could trigger the next explosion of AI.

Jon Hernandez

24,361 views • 4 months ago

When you give an AI agent money, how do you trust what it’s really doing? Sreeram Kannan explains why verifiable agents, AI systems you can cryptographically audit, are the key to trustless, safe agentic trading. 🎙️ w/ Ash Bennington on Real Vision

When you give an AI agent money, how do you trust what it’s really doing? Sreeram Kannan explains why verifiable agents, AI systems you can cryptographically audit, are the key to trustless, safe agentic trading. 🎙️ w/ Ash Bennington on Real Vision

EigenCloud

35,069 views • 9 months ago

Copilot Vision sees what you see and is here to expand your world while making it sweeter. 🤭 See what the power of Vision can help you with. Try it now. 🌸

Copilot Vision sees what you see and is here to expand your world while making it sweeter. 🤭 See what the power of Vision can help you with. Try it now. 🌸

Microsoft Copilot

13,311 views • 1 year ago

EXCLUSIVE: Microsoft just launched Copilot Vision in Edge—the first AI that can navigate the internet with you in real time. I sat down with Mustafa Suleyman (CEO of Microsoft AI) to discuss how it works, infinite memory, AI companions, agents, and more. Timestamps: 0:00 Intro 0:58 Microsoft Copilot Vision rundown 02:35 Initial reactions and use cases 04:57 How Copilot Vision works 06:02 Teaching AI to remember 08:13 How Microsoft AI is differentiating from OpenAI 09:27 The push for the true AI companion 11:28 Living with a co-intelligence in 10+ years 14:04 How Microsoft handles your data 16:11 When and how can you try Copilot Vision? 18:15 Agentic AI that controls your computer 20:25 What's next: support, gaming, and more 22:34 Preparing the next generation with Copilot 25:11 Mustafa’s advice for students and businesses

EXCLUSIVE: Microsoft just launched Copilot Vision in Edge—the first AI that can navigate the internet with you in real time. I sat down with Mustafa Suleyman (CEO of Microsoft AI) to discuss how it works, infinite memory, AI companions, agents, and more. Timestamps: 0:00 Intro 0:58 Microsoft Copilot Vision rundown 02:35 Initial reactions and use cases 04:57 How Copilot Vision works 06:02 Teaching AI to remember 08:13 How Microsoft AI is differentiating from OpenAI 09:27 The push for the true AI companion 11:28 Living with a co-intelligence in 10+ years 14:04 How Microsoft handles your data 16:11 When and how can you try Copilot Vision? 18:15 Agentic AI that controls your computer 20:25 What's next: support, gaming, and more 22:34 Preparing the next generation with Copilot 25:11 Mustafa’s advice for students and businesses

Rowan Cheung

268,106 views • 1 year ago

Dr. Fei-Fei Li (Fei-Fei Li), the Godmother of AI, on the origin of computer vision and why spatial intelligence is the next frontier. At AI Startup School in San Francisco. 01:00 - Origins of ImageNet 02:15 - The Dream to Make Machines See 03:28 - A paradigm shift in AI 05:50 - AlexNet and Deep Learning 08:00 - Evolving Computer Vision 12:20 - Building World Labs 13:00 - The next frontier in AI 14:20 - Why Spatial Intelligence Is Harder Than Language 18:40 - Technical Barriers for Vision-Based AI 20:00 - AI is more than LLMs 25:50 - Fei Fei’s Journey 29:30 - Mentoring some of the legends of AI 33:00 - Audience Q&A

Dr. Fei-Fei Li (Fei-Fei Li), the Godmother of AI, on the origin of computer vision and why spatial intelligence is the next frontier. At AI Startup School in San Francisco. 01:00 - Origins of ImageNet 02:15 - The Dream to Make Machines See 03:28 - A paradigm shift in AI 05:50 - AlexNet and Deep Learning 08:00 - Evolving Computer Vision 12:20 - Building World Labs 13:00 - The next frontier in AI 14:20 - Why Spatial Intelligence Is Harder Than Language 18:40 - Technical Barriers for Vision-Based AI 20:00 - AI is more than LLMs 25:50 - Fei Fei’s Journey 29:30 - Mentoring some of the legends of AI 33:00 - Audience Q&A

Y Combinator

194,393 views • 1 year ago

one of the biggest hurdles in computer vision is that the front end actually matters. you can’t just build models and call it a product. that’s why we’re building Manako. we see it as a “control plane” for visual intelligence. where data, policies, and operators meet. where vision stops being research and starts having real impact in the physical world. this is built for people running real systems. operators who can do 1,000x more when vision is packaged as a real ai product from a dev perspective, we’re already 2 months ahead of plan. now the focus is polish, usability, and connecting it directly into the subnet. build with vision.

one of the biggest hurdles in computer vision is that the front end actually matters. you can’t just build models and call it a product. that’s why we’re building Manako. we see it as a “control plane” for visual intelligence. where data, policies, and operators meet. where vision stops being research and starts having real impact in the physical world. this is built for people running real systems. operators who can do 1,000x more when vision is packaged as a real ai product from a dev perspective, we’re already 2 months ahead of plan. now the focus is polish, usability, and connecting it directly into the subnet. build with vision.

Max

10,537 views • 6 months ago

This is so cool 🔥 Score - Subnet 44 just partnered with Reading FC to bring Computer Vision AI into the club.. helping with tactical analysis and player recruitment Subnet 44 on #Bittensor making real world moves.. love it 👏 $TAO

This is so cool 🔥 Score - Subnet 44 just partnered with Reading FC to bring Computer Vision AI into the club.. helping with tactical analysis and player recruitment Subnet 44 on #Bittensor making real world moves.. love it 👏 $TAO

𝗗𝗥𝗘𝗔𝗗 𝗕𝗢𝗡𝗚𝗢

16,018 views • 8 months ago

🤯 Building computer-vision applications is never going to be the same again. As Andrej Karpathy says, "English is going to be the new programming-language", and we just made that happen for programming visual AI. 👨‍💻 This past month, the VLM Run team cooked up something magical that I'm especially proud of - a natural-language interface to build and run computer vision workflows (object-detection, OCR, parsing, and so much more) – all via our new VLM Run MCP server. 🔌 It works with any MCP-compatible AI agent (Claude, OpenAI, Cursor, etc.) and abstracts complex visual workflows into simple English commands. No need to write Python or fiddle with bespoke computer-vision code – just say what you want your agent to do, and it does it. Here’s a glimpse into what you can build today ( ☑️ Image AI agents – run detection, tagging, blurring, cropping, and more traditional CV tasks with English ☑️ Document AI agents – extract totals from invoices, search visual content, or act on what’s found ☑️ Video AI agents – understand scene content, trim clips, add subtitles, and create ready-to-share edits ☑️ And best-of-all, it's fully programmable with English. 🧑‍🍳 MCP Showcase: 📚 MCP Cookbooks: 📚 MCP Docs: #computervision #ai #agents #llm #vlm #mcp #vibecoding #genai

🤯 Building computer-vision applications is never going to be the same again. As Andrej Karpathy says, "English is going to be the new programming-language", and we just made that happen for programming visual AI. 👨‍💻 This past month, the VLM Run team cooked up something magical that I'm especially proud of - a natural-language interface to build and run computer vision workflows (object-detection, OCR, parsing, and so much more) – all via our new VLM Run MCP server. 🔌 It works with any MCP-compatible AI agent (Claude, OpenAI, Cursor, etc.) and abstracts complex visual workflows into simple English commands. No need to write Python or fiddle with bespoke computer-vision code – just say what you want your agent to do, and it does it. Here’s a glimpse into what you can build today ( ☑️ Image AI agents – run detection, tagging, blurring, cropping, and more traditional CV tasks with English ☑️ Document AI agents – extract totals from invoices, search visual content, or act on what’s found ☑️ Video AI agents – understand scene content, trim clips, add subtitles, and create ready-to-share edits ☑️ And best-of-all, it's fully programmable with English. 🧑‍🍳 MCP Showcase: 📚 MCP Cookbooks: 📚 MCP Docs: #computervision #ai #agents #llm #vlm #mcp #vibecoding #genai

Sudeep Pillai

17,789 views • 1 year ago

OpenAI just released access to Computer Use Agent via an API. It combines GPT-4o vision with advanced reasoning for an AI Agent to simulate controlling computer interfaces and performing tasks just like humans. You can try it for free using this Agent Playground.

OpenAI just released access to Computer Use Agent via an API. It combines GPT-4o vision with advanced reasoning for an AI Agent to simulate controlling computer interfaces and performing tasks just like humans. You can try it for free using this Agent Playground.

Shubham Saboo

64,206 views • 1 year ago

QACE Dynamics | VIBR Tech Preview 1 Introducing VIBR, the vision intelligence block that brings real perception to robots. In this first preview, we take a simple vacuum bot, connect it through the QACE dApp, and instantly give it object detection and smarter behavior without touching code. QACE makes it easy by automating the usual workflow: what once took hours of coding in Python and assembling AI models is now reduced to a few clicks. Complex AI vision blocks are created, configured, and ready-to-deploy scripts are generated automatically. Robots can now see, decide, and act in real time. Up next: we will show how these rules and actions evolve into full autonomy modules, with the Qognix Tech Preview dropping this week.

QACE Dynamics | VIBR Tech Preview 1 Introducing VIBR, the vision intelligence block that brings real perception to robots. In this first preview, we take a simple vacuum bot, connect it through the QACE dApp, and instantly give it object detection and smarter behavior without touching code. QACE makes it easy by automating the usual workflow: what once took hours of coding in Python and assembling AI models is now reduced to a few clicks. Complex AI vision blocks are created, configured, and ready-to-deploy scripts are generated automatically. Robots can now see, decide, and act in real time. Up next: we will show how these rules and actions evolve into full autonomy modules, with the Qognix Tech Preview dropping this week.

Qace Dynamics

29,448 views • 10 months ago

This 1-hour tutorial on building a Football AI system shows how to analyze matches and move toward real-time sports analytics using computer vision. Bookmark this & give it 1 hour today. This is a solid foundation if you want to build your own sports bot. Then read the post below.

This 1-hour tutorial on building a Football AI system shows how to analyze matches and move toward real-time sports analytics using computer vision. Bookmark this & give it 1 hour today. This is a solid foundation if you want to build your own sports bot. Then read the post below.

Goaty

108,512 views • 3 months ago

The age of video analytics #AIagents is here. 🎥 From factory to smart cities, enterprises like Pegatron, Linker Vision, VΛST Data, and Siemens are using #generativeAI to see, search, and summarize massive volumes of video—at scale. Explore how the NVIDIA AI Blueprint for video search and summarization (VSS) from #NVIDIAMetropolis is powering this shift. ➡️ #COMPUTEX2025

The age of video analytics #AIagents is here. 🎥 From factory to smart cities, enterprises like Pegatron, Linker Vision, VΛST Data, and Siemens are using #generativeAI to see, search, and summarize massive volumes of video—at scale. Explore how the NVIDIA AI Blueprint for video search and summarization (VSS) from #NVIDIAMetropolis is powering this shift. ➡️ #COMPUTEX2025

NVIDIA AI

20,775 views • 1 year ago

The age of AI agents is here. Models can read, see, talk, and now, even use a computer— all by themselves. One of the first out of the gates is Anthropic’s Claude Computer Use. YC's Garry Tan dives into how it works, what it can do, and how it may change AI forever.

The age of AI agents is here. Models can read, see, talk, and now, even use a computer— all by themselves. One of the first out of the gates is Anthropic’s Claude Computer Use. YC's Garry Tan dives into how it works, what it can do, and how it may change AI forever.

Y Combinator

265,909 views • 1 year ago

As AI accelerates content creation, traditional security controls struggle to keep up. We recently released Shield Pro to GA to address this shift, using agentic AI to automatically classify unstructured content with context, detect ransomware behavior early, and streamline how security teams investigate and respond to threats. Instead of relying solely on static rules, Shield Pro embeds intelligence directly into content security workflows, helping teams protect collaboration at scale without adding friction. Read more to understand how agentic AI is reshaping content security:

As AI accelerates content creation, traditional security controls struggle to keep up. We recently released Shield Pro to GA to address this shift, using agentic AI to automatically classify unstructured content with context, detect ransomware behavior early, and streamline how security teams investigate and respond to threats. Instead of relying solely on static rules, Shield Pro embeds intelligence directly into content security workflows, helping teams protect collaboration at scale without adding friction. Read more to understand how agentic AI is reshaping content security:

Box

816,255 views • 6 months ago

🔓Unlock the power of multimodal AI with PaliGemma and Keras! Keras software engineer Varun Singh gave an inside look at how PaliGemma works to solve language and computer vision tasks and how to leverage Keras for streamlined development. Watch →

🔓Unlock the power of multimodal AI with PaliGemma and Keras! Keras software engineer Varun Singh gave an inside look at how PaliGemma works to solve language and computer vision tasks and how to leverage Keras for streamlined development. Watch →

Google for Developers

33,761 views • 1 year ago

for Basketball AI, I want to read jersey numbers and map them to player names I'm using RF-DETR + SmolVLM2 combo to do it - detect jersey numbers in real-time with RF-DETR - crop number regions - OCR the numbers with SmolVLM2 computer vision + sports:

for Basketball AI, I want to read jersey numbers and map them to player names I'm using RF-DETR + SmolVLM2 combo to do it - detect jersey numbers in real-time with RF-DETR - crop number regions - OCR the numbers with SmolVLM2 computer vision + sports:

SkalskiP

27,556 views • 1 year ago

Robotics and CV! 👓 Computer vision gives the robots a sense of vision and additional intelligence. Pralines are packed by a delta robot using computer vision. Packing chocolate pralines into a box with the delta robot. Unlike most robots, this one has a fixed TCP, and the base moves in response to vision data. To adjust the base, the vision system determines exactly where the praline is located on the conveyor belt. 🍫 Using this application, the system knows where each praline should be placed based on its orientation. A true engineering showcase!

Robotics and CV! 👓 Computer vision gives the robots a sense of vision and additional intelligence. Pralines are packed by a delta robot using computer vision. Packing chocolate pralines into a box with the delta robot. Unlike most robots, this one has a fixed TCP, and the base moves in response to vision data. To adjust the base, the vision system determines exactly where the praline is located on the conveyor belt. 🍫 Using this application, the system knows where each praline should be placed based on its orientation. A true engineering showcase!

Lukas Ziegler

79,410 views • 1 year ago

Is Perplexity Computer the most powerful AI Agent? How does it compare to OpenClaw? And what can it even do? In this 36 min video, i break down everything you need to know about Perplexity Computer

Is Perplexity Computer the most powerful AI Agent? How does it compare to OpenClaw? And what can it even do? In this 36 min video, i break down everything you need to know about Perplexity Computer

David Ondrej

40,675 views • 4 months ago

🧠 Dell is rethinking what enterprise AI can do — and where it lives. At Dell Tech World, Sam Grocott shared how Dell Technologies is deploying Glean’s Work AI Platform on-prem — blending public LLM intelligence with private infrastructure to power sensitive, high-trust use cases. The result? AI that acts on your behalf to: ✅ Write emails ✅ Prep meetings ✅ Push deals forward — autonomously This is Dell’s vision for agentic AI: a 24/7 teammate driving go-to-market productivity to new heights — securely, efficiently, and always on. Get the full story:

🧠 Dell is rethinking what enterprise AI can do — and where it lives. At Dell Tech World, Sam Grocott shared how Dell Technologies is deploying Glean’s Work AI Platform on-prem — blending public LLM intelligence with private infrastructure to power sensitive, high-trust use cases. The result? AI that acts on your behalf to: ✅ Write emails ✅ Prep meetings ✅ Push deals forward — autonomously This is Dell’s vision for agentic AI: a 24/7 teammate driving go-to-market productivity to new heights — securely, efficiently, and always on. Get the full story:

Six Five Media

92,894 views • 1 year ago