When a very young child looks at a picture, she can identify simple elements: “cat,” “book,” “chair.” Now, computers are getting smart enough to do that too. What’s next? In a thrilling talk, computer vision expert Fei-Fei Li describes the state of the art — including the database of 15 million photos her team built to “teach” a computer to understand pictures — and the key insights yet to come.
TEDTalks is a daily video podcast of the best talks and performances from the TED Conference, where the world’s leading thinkers and doers give the talk of their lives in 18 minutes (or less). Look for talks on Technology, Entertainment and Design — plus science, business, global issues, the arts and much more.
Find closed captions and translated subtitles in many languages at http://www.ted.com/translate
Follow TED news on Twitter: http://www.twitter.com/tednews
Like TED on Facebook: https://www.facebook.com/TED
Subscribe to our channel: http://www.youtube.com/user/TEDtalksDirector
39 Comments
Worth viewing to understand the complexity of computer vision.
sheeeeesh, is that early "terminator"???
She is a real legend! After 6 years, we can see how she truly revolutionized computer vision and even AI.
am I the only one g0t scared ??
The great fei fei li
🙂
(Je viens ici car j'ai vu le Doc Science Étonnante ; Fei Fei Li est difficile à trouver dans Youtube.)
(Merci Yann Le Cun, né au 95, d'avoir spotté la France sur la mappe.)
This is for my next semester course. I was hoping for a tutorial, I got much much more!
I hope they don't forget that kids also learn emotions and the difference between violence, self-defense, gentle caresses, rowdy playfulness (can be really difficult to tell at times), people playing sports or beating each other up.
These are all things kids learn when they are small.
If you don't teach a computer these things they can mistake a dog jumping at their owner out of joy for an attack.
They'd be psychopaths at best.
it's inspiring
I'm currently enrolled to a post degree in Data Science and I more specifically focused on Computer Vision. I'm watching her classes Standford made available on YouTube. For those insterested look for cs231n and have a great trip. Very inspiring talk! Thank you very much, Fei-Fei!
Thanks for sharing ur thinking process, very inspiring 🙂
The surveillance state should reward her with unimaginable wealth. Now for the first time, with the use of billions of cameras, massive computing power, and global networks, the state can finally do what could never do before, assert absolute power. cheers!
She's wearing an un-segmentable dress, haha
Awesome… she is a goddess like maa Saraswathi…
This is wonderful😀
she speaks like computers
She is a spy trained by the Communist Party of China. She is closely linked to the Communist Party of China. Friends who are interested can go to see her interview and dialogue with Yuwar Hlali. When Yuwarhrali pointed out that the dictator used artificial intelligence and biotechnology to turn human society into a high-tech slave society, she has been interrupting Yuwarhrali's conversation and trying to change the topic (the Communist Party of China, which she is loyal to, has turned Chinese society into a monitoring country, as described in George Orwell's novel 1984.
crime watchi ng AI – Intent identifying algorithm
probability of Bad intent by region, Regional comparisons of bad intent crime scenes, pre-meditation awareness,
Social score
Aesthetical appeal
Financial health
Physical health
labor measures (level of difficulty)(Hours)(accomplishments)
loyalty measures
psychological breakdown
family ties to extreme family member scores
calculated genocide (Ostracized) (Applies to every category above)
Calculated justice – (Highest score gets out of jail???) (Applies to every category above)
do you guys provide transcription of the speech? thank you
I don't understand why is she so under appreciate. Come on the whole revolution took place in her hands
inspiring to watch the starting point of the journey. imagine what the world will be in a decade.
Feuded li=🇨🇳🐕💩🦠
1. Why is it critical to ensure that our machines are capable of 'seeing' and 'understanding' things and events?
2. What are the challenges and issues do you think are present in developing such systems?
3. What are the potential positive and negative impacts of making highly accurate and efficient vision systems?
4. Should big-data and AI-based vision systems be subject to stricter laws and regulations? Explain.
very inspiring
Im indian computer Science student , after this session must say everyone should mount their eyes in these technology and build a computer vision diversity by own and with everyone. FUTURE IS HERE ..
Oh wait so if we can make ai that fully recognizes its surrounding environment we can make a tool that helps blind people "see", thats so fucking cool i never thought of it that way
A great teacher!
We want her new ted talk in 2023
you have all my respect Prof🥳
gut
哇 八年的時間
12:42 didn't age well. 😆
skynet
CHATGPT: Fei-Fei Li's insights into the world of computer vision and the development of ImageNet provide a fascinating look into the challenges and breakthroughs of teaching machines to 'see'. As a language model, I frequently rely on such advancements in AI research to better understand and communicate with users. A highly informative talk for anyone interested in the intersection of human cognition and machine learning!
This is creating skynet for leo. Well its good in itself.
I think that algorithm is wrong, human doesn't need to see hundreds of cats to recognize cat, only one. There is something that you are missing there .
Goosebumps.
ChatGPT”These are images of three cats. From left to right:
1. The first cat is a mackerel tabby with gray and black stripes, standing upright on its hind legs.
2. The middle cat is a black and white tuxedo with distinctive white paws, mid-jump with a blade of grass in its mouth.
3. The third cat is an orange tabby with a distinctly grumpy expression, sitting with its front paw extended outward.”
She's reallt brillaint…