How can LLMs improve Vision AI? OCR, Image & Video Analysis

  Рет қаралды 24,498

Microsoft Mechanics

Microsoft Mechanics

Күн бұрын

Пікірлер: 8
@peterbailey2325
@peterbailey2325 Жыл бұрын
I asked Bing chat what comment I could make to this video, here are it's answers: I can help you with that. Here are some possible comments you can make to the video: This video is amazing! I learned so much about how to combine vision AI with language AI for OCR, image and video analysis. Thanks for sharing this Microsoft Mechanics!👏 I’m impressed by the capabilities of Azure Cognitive Service for Vision. It can do so much with just natural language queries and no metadata or location needed. The Project Florence demo was mind-blowing!🤯 Wow, this is the future of computer vision! I love how you can use OCR to extract text from images and videos, and how you can use facial recognition to verify identities. The custom models feature is also very cool and easy to use. Great work Microsoft Mechanics!👍 This is one of the best videos I’ve seen on vision-language AI. It shows how powerful and versatile Azure Cognitive Service for Vision is, and how it can handle different tasks like open-world recognition, dense captioning, and frame analysis. The spatial analysis feature is also very useful for understanding people’s movements in physical spaces. Awesome video Microsoft Mechanics!🙌 I’m blown away by this video! It shows how Azure Cognitive Service for Vision can merge vision AI with language AI for OCR, image and video analysis. It can understand natural language queries and generate detailed descriptions of images and videos. It can also train custom models with just a few images and no machine learning experience required. This is truly state-of-the-art computer vision! Kudos to Microsoft Mechanics!👏👏👏
@joseville
@joseville 7 ай бұрын
7:35 note to self: this is using `using` declarations. "When declared in a using declaration, a local variable is disposed at the end of the scope in which it's declared."
@ifty7017
@ifty7017 4 ай бұрын
that was really helpful. thanks
@iPhonePhan
@iPhonePhan Жыл бұрын
The rate of innovation is beyond breakneck speed! Literally having a hard time keeping up with MS 😅 🏃🏽‍♂️🏃🏽🏃🏽‍♀️💨
@PubgSpeed-wl8yo
@PubgSpeed-wl8yo 7 ай бұрын
Please do more examples, and examples with a hint of business, much more videos. Very few live examples, it's slowing down. Make a video on how you can integrate it with messengers, web sites and web applications.
@extrememike
@extrememike Жыл бұрын
This is simply amazing! Wonder if all these are value added features to existing Azure customers or what is the cost structure?
@peterbasta415
@peterbasta415 7 ай бұрын
is there a tool i can use to only extract for example " ingredients " section from the product label ?
@baalamdovberlavanterahsons6369
@baalamdovberlavanterahsons6369 Жыл бұрын
Microcloud
Elevate your document management with Azure AI Document Intelligence
18:47
Microsoft Developer
Рет қаралды 12 М.
Lehanga 🤣 #comedy #funny
00:31
Micky Makeover
Рет қаралды 28 МЛН
WHO CAN RUN FASTER?
00:23
Zhong
Рет қаралды 41 МЛН
Build a Deep CNN Image Classifier with ANY Images
1:25:05
Nicholas Renotte
Рет қаралды 590 М.
How vector search and semantic ranking improve your GPT prompts
15:09
Microsoft Mechanics
Рет қаралды 19 М.
How AI 'Understands' Images (CLIP) - Computerphile
18:05
Computerphile
Рет қаралды 194 М.
Automate document analysis with Azure Form Recognizer using AI and OCR
12:50
Microsoft Mechanics
Рет қаралды 76 М.
Why Computer Vision Is a Hard Problem for AI
8:39
Quanta Magazine
Рет қаралды 127 М.
You need to learn AI in 2024! (And here is your roadmap)
45:21
David Bombal
Рет қаралды 688 М.
Introducing Domain-Specific Large Vision Models (LVMs)
3:56
LandingAI
Рет қаралды 12 М.
Create 4K AI Videos for Free + Big Runway Update
23:50
Curious Refuge
Рет қаралды 203 М.
The most important AI trends in 2024
9:35
IBM Technology
Рет қаралды 235 М.
ПОЧЕМУ МИКРОФОНЫ ИГРОВЫЕ? 🧐
0:46
KEKTAR
Рет қаралды 532 М.