Serge Belongie
København, Region Hovedstaden, Danmark
5 t følgere
500 forbindelser
København, Region Hovedstaden, Danmark
5 t følgere
500 forbindelser
Om
Specialties: Computer Vision and Machine Learning
Artikler af Serge
-
Call for Applications - Startup Postdoc at Cornell Tech in NYC
Call for Applications - Startup Postdoc at Cornell Tech in NYC
Af Serge Belongie
Aktivitet
-
Happy to announce the next edition of the workshop "Self-Supervised Learning: What is Next?" is coming to #ECCV2024 organized with Mert Bülent…
Happy to announce the next edition of the workshop "Self-Supervised Learning: What is Next?" is coming to #ECCV2024 organized with Mert Bülent…
Serge Belongie synes godt om dette
-
Want to work on the latest cutting edge AI? If you are excited about Graph Neural Networks, RAGs, and Knowledge Graphs, apply here:…
Want to work on the latest cutting edge AI? If you are excited about Graph Neural Networks, RAGs, and Knowledge Graphs, apply here:…
Serge Belongie synes godt om dette
-
Looking to advance the state-of-the-art in crowd counting computer vision? I have an exciting opening - PhD position in Revolutionizing Crowd…
Looking to advance the state-of-the-art in crowd counting computer vision? I have an exciting opening - PhD position in Revolutionizing Crowd…
Serge Belongie synes godt om dette
Erfaring
Uddannelse
Udgivelser
-
Learning to Match Aerial Images with Deep Attentive Architectures
2016 IEEE Conference on Computer Vision and Pattern Recognition
-
Wet fingerprint recognition: Challenges and opportunities
IEEE Computer Society Washington, DC, USA
-
Approximate Thin Plate Spline Mappings
European Conference on Computer Vision - ECCV
The thin plate spline (TPS) is an effective tool for modeling coordinate transformations that has been applied successfully in several computer vision applications. Unfortunately the solution requires the inversion of a p × p matrix, where p is the number of points in the data set, thus making it impractical for large scale applications. As it turns out, a surprisingly good approximate solution is often possible using only a small subset of corresponding points. We begin by discussing the…
The thin plate spline (TPS) is an effective tool for modeling coordinate transformations that has been applied successfully in several computer vision applications. Unfortunately the solution requires the inversion of a p × p matrix, where p is the number of points in the data set, thus making it impractical for large scale applications. As it turns out, a surprisingly good approximate solution is often possible using only a small subset of corresponding points. We begin by discussing the obvious approach of using the subsampled set to estimate a transformation that is then applied to all the points, and we show the drawbacks of this method. We then proceed to borrow a technique from the machine learning community for function approximation using radial basis functions (RBFs) and adapt it to the task at hand. Using this method, we demonstrate a significant improvement over the naive method. One drawback of this method, however, is that is does not allow for principal warp analysis, a technique for studying shape deformations introduced by Bookstein based on the eigenvectors of the p × p bending energy matrix .T o address this, we describe a third approximation method based on a classic matrix completion technique that allows for principal warp analysis as a by-product. By means of experiments on real and synthetic data, we demonstrate the pros and cons of these different approximations so as to allow the reader to make an informed decision suited to his or her application.
Udmærkelser og priser
-
Medlem
Videnskabernes Selskabs
Member, The Royal Danish Academy Of Sciences And Letters
Flere aktiviteter af Serge
-
Have fun with our open source reproduction of the Clarity AI upscaler / enhancer!
Have fun with our open source reproduction of the Clarity AI upscaler / enhancer!
Serge Belongie synes godt om dette
-
“The things that I worry about in AI are just amplifications of what worries me about people.” Sådan sagde Serge Belongie, Professor and Director of…
“The things that I worry about in AI are just amplifications of what worries me about people.” Sådan sagde Serge Belongie, Professor and Director of…
Serge Belongie synes godt om dette
-
We reproduced the amazing Clarity AI Upscaler https://lnkd.in/eTQDNuxy using the Refiners framework: https://lnkd.in/eT-YDHSn. I wrote a new article…
We reproduced the amazing Clarity AI Upscaler https://lnkd.in/eTQDNuxy using the Refiners framework: https://lnkd.in/eT-YDHSn. I wrote a new article…
Serge Belongie synes godt om dette
-
This week at [ICML] Int'l Conference on Machine Learning catch up with Anders Christensen and Nooshin Mojab at the GRaM Workshop…
This week at [ICML] Int'l Conference on Machine Learning catch up with Anders Christensen and Nooshin Mojab at the GRaM Workshop…
Serge Belongie synes godt om dette
-
If you know any great product managers - please encourage them to apply to iNaturalist https://lnkd.in/gxWphcX7 Speaking of product - I had a great…
If you know any great product managers - please encourage them to apply to iNaturalist https://lnkd.in/gxWphcX7 Speaking of product - I had a great…
Serge Belongie synes godt om dette
-
Will be giving a talk at Indian Institute of Science (IISc) later today, with hopes of setting up collaborations related to my ongoing research.
Will be giving a talk at Indian Institute of Science (IISc) later today, with hopes of setting up collaborations related to my ongoing research.
Serge Belongie synes godt om dette
-
The Caltech Division of Engineering and Applied Science Trailblazers Symposium seeks to recognize and provide professional development opportunities…
The Caltech Division of Engineering and Applied Science Trailblazers Symposium seeks to recognize and provide professional development opportunities…
Serge Belongie synes godt om dette
-
New paper shows that xLSTM excels in times series prediction. "Our xLSTMTime model demonstrates excellent performance against state-of-the-art…
New paper shows that xLSTM excels in times series prediction. "Our xLSTMTime model demonstrates excellent performance against state-of-the-art…
Serge Belongie synes godt om dette