Conference on Computer Vision and Pattern Recognition
ConferenceWikipedia
12
MENTIONS
8
EPISODES
5
PODCASTS
Search complete. 12 mentions across 8 episodes found for "Conference on Computer Vision and Pattern Recognition".
Nov 20, 2026
PhotoSketch: A Photo-Centric 3D Modeling Tool
G
21:04George WolbergGUEST
And then furthermore, we can take these 3D edges and these 2D images and have them go through a 2D image to 3D model registration.
G
21:14George WolbergGUEST
So some of that work is best described in a 2005 CVPR paper by Professor Stamos and Lingyun Liu.
G
21:22George WolbergGUEST
And Lingyun is now here working at Google.
G
21:26George WolbergGUEST
And basically, what that does is says that from all of these images, there are a subset of images from which you can extract 2D lines and match them to the 3D lines here so that you can recover the camera positions directly from that.
33 MINS LATER
G
54:42George WolbergGUEST
No, no, we pick six here and we try to find six here and we keep, it's kind of like a brute force, it's iterative, finding six and six.
G
54:49George WolbergGUEST
And it's actually the 25th anniversary of the introduction of RANSAC, which I think was 1982 or maybe 1981.
G
54:59George WolbergGUEST
And there was a venue at CVPR last year which talked about the advances of RANSAC.
G
55:04George WolbergGUEST
But I would direct you to how RANSAC works, those papers on how it works.
High Fidelity Image-Based Modeling
Y
31:30Yasutaka FurukawaGUEST
So, I've shown you, like, pictures of movies.
Y
31:33Yasutaka FurukawaGUEST
And of course, people are interested in asking, so how are they accurate? And our, so fortunately, there are some quantitative evaluation of multivisory algorithms, which was our published last year, CVPR.
Y
31:44Yasutaka FurukawaGUEST
So, basically, provide some data sets, then people run their own algorithm, then submit results.
Y
31:51Yasutaka FurukawaGUEST
They're going to evaluate your accuracy of the results, compare with the ground truth, and show you the how much accurate your results are.
Understanding and Mitigating Copying in Diffusion Models
G
22:40Gowthami SomepalliGUEST
Okay.
G
22:42Gowthami SomepalliGUEST
So that concluded the first paper, which we presented at CVPR.
G
22:50Gowthami SomepalliGUEST
And so basically, we had this mainly from our analysis.
G
22:54Gowthami SomepalliGUEST
What we found is there seems to be two factors which are strongly responsible for memorization.
Stanford Seminar - Microsoft's Harry Shum on the Bing Dialog Model
H
57:40Harry ShumGUEST
I don't know what is the latest conference coming up.
H
57:42Harry ShumGUEST
When is the CVPR deadline? It just passed.
H
57:45Harry ShumGUEST
The CVPR, if you type CVPR now versus CVPR later, and which CVPR you're looking for actually can be very different.
H
57:53Harry ShumGUEST
So this is time dimension here.
H
57:56Harry ShumGUEST
Certainly, this is the location in the spatial dimension here.
What If AI Could Build the Next AI Model | Professor of AI Explains
D
9:00Damian BorthGUEST
So there are two different things how you could think about that.
D
9:02Damian BorthGUEST
We had one paper that was published at Computer Vision and Pattern Recognition Conference, CVPR, where we had a very particular use case for remote sensing data.
D
9:12Damian BorthGUEST
So satellite data and so-called foundational models that are able to analyze satellite data.
D
9:19Damian BorthGUEST
And we now took our approach, trained it on the entire remote sensing neural networks that we could find on platforms like Hugging Face and, you know, had the pre-training on computer vision models and took this to generate foundation models in remote sensing.
D
10:50Damian BorthGUEST
And now please predict checkpoint number 10.
D
10:53Damian BorthGUEST
So you kind of jump ahead in transfer learning or fine tuning.
D
10:58Damian BorthGUEST
For the numbers, the CVPR paper showed that we can be we can train comparable remote sensing models with 20 times less compute needed as compared to state of the art models trained from scratch.
V
11:10Vit LyoshinHOST
Wow, that's amazing.
VLA 2.0, Robotaxis, and Physical AI | XPENG’s AI Chief Dr. Xianming Liu
K
1:14Kim IsenbergHOST
Jiangming holds a PhD in electrical and commuter engineering from the University of Illinois, and before Xpeng, he worked at Matter at Cruise.
K
1:25Kim IsenbergHOST
He reports directly to XPeng's CEO and he is just back from CDPR, the world's top computer vision conference, where he laid out XPeng's roadmap for what the computer company calls physical AI.
K
1:38Kim IsenbergHOST
Where he laid out XPeng's roadmap for what the company calls physical AI, XPeng describes itself as an AI company that happens to build cars and that's exactly what I want to get into today.
K
1:51Kim IsenbergHOST
Jeremy, welcome and thank you for making the time.
X
1:57Xianming LiuGUEST
I mean, the warm introduction makes me feel it.
K
2:01Kim IsenbergHOST
I don't often have the pleasure to meet such great researchers, so it's a pleasure for me to meet you finally in person.
K
2:07Kim IsenbergHOST
So as I was saying, you just came back from CVPR, the world's top computer vision research conference, right? Basically, the frontline of teaching machines to see what's the one idea from there that will actually change what Xpeng ships in the next 12 months.
X
2:24Xianming LiuGUEST
Yeah, so we started working on something called VLA 2.0 from last year.
Stanford Seminar - Self-Supervised Pseudo-Lidar Networks
A
40:44Adrien GaidonGUEST
Again, this is our network, better than the best self-supervised, better than the best semi-supervised or fully supervised, right? LiDAR, you don't have LiDAR points in the sky, so you have some issues with that, right? So that's also one reason.
A
40:59Adrien GaidonGUEST
This is like last year's CVPR, no, two years CVPR.
A
41:05Adrien GaidonGUEST
So just for your information like that, That versus that.
A
41:10Adrien GaidonGUEST
The pace of the field is crazy.
Inside Runway's $5.3B Playbook
A
57:42Anastasis GermanidisGUEST
Like, are we actually going to be able to, you know, do we have the resources or do we have the skillset to actually win against Sora? And at the end of it, people figure out that We, in fact, did and we put out a model out there that was better than Sora in a few months.
A
57:59Anastasis GermanidisGUEST
And I remember we released it at CVPR, which is one of the big computer vision conferences.
A
58:05Anastasis GermanidisGUEST
And it was very gratifying for the team that everyone was talking about Gen 3 and the model that we'd released.
A
58:13Anastasis GermanidisGUEST
So I think it was one of those formative moments of the company where people realized that...