Kostas Daniilidis
@KostasPenn
Followers
4,353
Following
1,075
Media
127
Statuses
1,038
Ruth Yalom Stone Professor @Penn @PennEngineers @PennCIS @GRASPlab
Joined December 2012
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
MOONLIT FLOOR OUT NOW
• 278575 Tweets
JUMP
• 209033 Tweets
Mets
• 165541 Tweets
Falcons
• 68220 Tweets
天使の日
• 54669 Tweets
Diana
• 43227 Tweets
#PowerGhost
• 31032 Tweets
Kirk Cousins
• 28753 Tweets
Bucs
• 28066 Tweets
MerzAesthetics x KTMP
• 27655 Tweets
Hayırlı Cumalar
• 23766 Tweets
SB19 IS ACER READY
• 21614 Tweets
#PowerBook2Ghost
• 19438 Tweets
HAVE A SAFE FLIGHT JIN
• 18587 Tweets
Mooney
• 18185 Tweets
ワートリ
• 16914 Tweets
Tariq
• 16380 Tweets
感謝マルチガチャ
• 15832 Tweets
Cane
• 14655 Tweets
PRABOWOsiapkan YangTERBAIK
• 13648 Tweets
Bleed
• 13113 Tweets
KEKUATANkita PERSATUANkita
• 13046 Tweets
最大4体ゲット
• 12656 Tweets
人達同士
• 12616 Tweets
#يوم_الجمعه
• 12502 Tweets
33 years of deadlines since my first submission for ECCV’90. So grateful for being healthy and fit to stay late and for having these wonderful students! Good luck everybody!
9
6
462
NVIDIA’s job applicants should have excellent knowledge of theory and practice of LLM’s and foundation models. I am honestly looking for papers on theory of foundation models. Could academic twitter reply with any links? I would be very grateful.
23
31
372
#CVPR2022
Motion 3: "Any reviewer who has accepted an invitation to review but violates the reviewing guidelines set forth by the conference will be prohibited from submitting any papers to CVPR for up to two
years." My vote is a resounding NO! 1/n
12
28
288
@ylecun
++: "damage to the language system within an adult human brain leaves most other cognitive functions intact." There is ample evidence that reasoning can happen after language ability disappears:
16
40
197
Best Fall present ever: the new book by Tristan Needham. Thanks to
@ch402
for tweeting about it.
@CSProfKGD
Wish we had more diffgeom in the past so that we understand faster
@TacoCohen
's recent papers :-)
9
20
199
#CVPR2024
Such a great effort by my wonderful students. Excellent finish. Good luck to all of you. What a great feeling, 31 years of CVPR deadlines :-)
2
6
186
This is really fascinating. Nina Miolane
@ninamiolane
showing how biological brains encode Lie groups!
#CVPR
Equivision workshop
5
29
192
🌟FisherRF introduces a novel approach for view selection & uncertainty in 3D Gaussian Splatting & NeRFs. Fisher information can be computed without altering model architecture, and it is as cheap as back-propagation! 🚀More details:
2
23
169
Congratulations to my amazing student Georgios Pavlakos
@geopavlakos
for receiving the Best Computer Science Dissertation Award at Penn, the 2021 Morris and Dorothy Rubinoff Award.
7
8
161
This is a must read for every computer vision student. And it is a joy to always feel like a student when you read an article like this!
1
19
150
ICLR23 AC: "....impressive performance on recovering dense reconstruction from a single point cloud, while also enabling zero-shot generalization to multi-object scenes. " SE(3)-Equivariant Attention is what you need!
4
16
146
TRAM recovers 3D human pose in a global world frame with 60% root trajectory error reduction wrt SotA!
Watch the video on our project page
arxiv:
Thanks to my amazing coauthors:
@YufuWang_
,
@ZiyunClaudeWang
,
@LingjieLiu1
.
2
32
160
Mens sana in corpore sano! Back in the game, after 7 years, I finished my 6th half-marathon. I am so grateful today, in particular, to my wife for urging me to do it.
9
0
139
Congratulations on the new differential geometry book by colleague Jean Gallier and Jocelyn Quaintance. It was written with computer vision and robotics in mind.
3
23
138
Student: "What are the three most important problems in computer vision?"
Takeo Kanade: "Correspondence, correspondence, correspondence!"
The first question that I ask when I read a DeepX geometry paper is which step solves the correspondence problem.
Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence
tl;dr: 6D (x-y-scale1, x-y-scale2) correlation ->scale max-pool -> refine -> softargmax -> correspondences.
Juhong Min, Seungwook Kim, Minsu Cho
3
25
126
2
20
131
Our
#CVPR2022
paper introduces a representation of canonical shape for deformed humans, animals and articulated objects via neural homeomorphisms. Very proud of first paper with my student
@Jiahui77036479
:
arxiv:
Project:
4
16
118
Incorporating stronger geometric bias within the architectural design and taking advantage of the inductive bias provided by the vision foundation models enables really fast and robust tracking: Yunzhou Song,
@JiahuiLei1998
@ZiyunClaudeWang
@LingjieLiu1
!
2
15
117
While drinking coffee at starbucks a delivery robot happens to ride by … 2022 Tempe, AZ
3
7
113
[Code now available!] Gaussian Articulated Template Model (GART) captures humans and animals from monocular videos (ZJU MoCap and PeopleSnapshot in 30s), renders novel poses and views at 150fps, on a laptop, and facilitates text-to-3D generation.
Project:
0
19
111
Guess the dance! Produced by the amazing notebook developed by
@nikoskolot
@geopavlakos
based on our
#ICCV2021
ProHMR. (So easy to run that even I an old professor can run it. Video cut to hide the name of the dance).
4
12
109
There is a progress in linear algebra education. I always keep asking this question in the vision class: How many of you have never heard of SVD. It was 1-2 out of approx 120 students (40 undergrad + 80 grad) this semester. 10 years ago, it was half of the class. .
@CSProfKGD
5
4
106
The recordings of the talks of our Workshop on Equivariance and Data Augmentation are now here:
0
22
101
In this
#ICML2022
paper, we exploit the sparsity in the spectrum of tensor field networks to derive a novel nonlinearity/activation and provide an alternative derivation of TFN kernels.
@_onionesque
@TacoCohen
@maurice_weiler
@wellingmax
@mariogeiger
3
20
99
Congratulations to our continuous source of inspiration, Ruzena Bajcsy, for receiving the 2021 Rosenfeld Lifetime Achievement Award
@iccv2021
,
@PennEngineers
@GRASPlab
1
9
92
Great homework for my Spring 2023 CIS 580 class, all the steps spelled out.
3
8
85
Segment fast independent motion with an event camera without training labels! 📷 Un-EvMoSeg runs in real-time without heavy optimization and requires zero segmentation annotation. 📷 Check out the project:
3
6
85
Birds of a Feather, our CVPR'21 paper; 3D vision in the service of biology (
@akanazawa
,
@Michael_J_Black
,
@FuaPv
,
@silvia_zuffi
,
@KordingLab
);
5
15
84
So blessed to have had Dr. Kolotouros
@nikoskolot
as a student! Look at his widely cited SPIN and ProHMR results. Thank you
@Michael_J_Black
@dineshjayaraman
@pratikac
and Jianbo Shi for the very educational questions.
@GRASPlab
@CIS_Penn
3
6
82
We usually teach vanishing points. What about the opposite: When does a set of lines intersecting in R^2 project to a set of exactly parallel lines or why it is worth teaching P^2 (and P^3) in a vision class.
3
14
81
Our post
#eccv2020
workshop on equivariance and data augmentation has an incredible line-up of speakers and is free. Register at
1
21
78
Congratulations to Dr. Karl Schmeckpeper. Sooo proud of you! Thank you
@chelseabfinn
, for mentoring and working with Karl and being on his committee.
5
3
77
Today England will face Germany in a match with a history in computer vision and not only. Reid and Zisserman
@oxford_VGG
wrote one of the most elegant papers in geometric vision at ECCV'96. I devote one of my courser lectures to this pearl:
1
5
76
Congratulations to Dr. Kenneth Chaney, the best engineer I have ever met! So lucky to have met him during the DARPA Robotics challenge when he was doing his CoOp and convinced him to do a PhD! I am so proud of you Ken!
0
1
76
Four generations of my academic tree at U of Minnesota, Maryland, and Drexel! And Vishnu PhD student at UMD. Could not be prouder!
@AgriRobot
@ptokekar
@Lifeng917
3
5
74
Our equivariant transformer for 3D-reconstruction in function space presented by
@EChatzipantazis
,
@stefanos_pert
,
@EdgarDobriban
at
#ICLR2023
.
0
15
72
Congratulations to Program Chairs of
#CVPR2022
@richasingh26
@KristinJDana
@ganghua1
and Samaras. This CVPR has set a new standard of checks and balances cross AC decisions and reviews with greater granularity and maximum consistency. It felt like unit tests in decision making.
2
7
69
Kourosh Durmohamadi Bagi arrived in a refugee camp in Lesbos in 2019 and this year he ranked 2nd in the STEM Panhellenic entry exam (the gaokao of Greece). He wants to study EE in Thessaloniki. Congratulations Kyros!!!
0
5
68
Our Equivariant Vision workshop features five great speakers
@erikjbekkers
@HaggaiMaron
@ninamiolane
@_machc
, and Leo Guibas, spotlight talks, posters, and a tutorial prepared for the vision audience. Come tomorrow, Tuesday, at 8:30am in Summit 321! Thank you
@CongyueD
for
0
15
67
The finest of computer vision:
2
2
62
How nature performs dense pose annotation :-) Watch it in full screen.
@silvia_zuffi
@akanazawa
@Michael_J_Black
@CSProfKGD
2
5
63
Congratulations to the organizers of
@neur_reps
for an inspiring workshop full of geometry, topology, and neuroscience!
2
4
62
The culmination of my first NeurIPS could not have been more rewarding: The Neural Wave Machines talk by
@wellingmax
. We started working on equivariance inspired by Max and
@TacoCohen
6 years ago. Thank you and your group (
@maurice_weiler
and all).
1
5
58
I am really puzzled by the almost 3000 paper registrations without submission. Is it strict last minute self-criticism or naive optimism that a miracle will happen in the experiments during the last week or might be plain opportunism that hyper parameter tuning will make it work?
11
1
62
At
#CPAL2024
with
@YiMaTweets
! Thank you for being the inspiration and the host of the first
@cpalconf
. I remember sitting next to Yi during the summer of 1998 at Berkeley when
@jana_kosecka
and Yi conceived the self-calibration for SfM that received the ICCV'99 Marr Prize!
0
3
59
Hey hey, my my
The essential matrix can never die
There's more to the picture
Than meets the eye.
Hey hey, my my.
#eccv2022
2
7
58
Bad reviewing is indeed a problem but it can be mitigated with training (taking online courses) and positive incentives. I would be very happy to contribute to such a course creation. 6/n
1
4
57
With rampant mental health issues among doctoral students and researchers you will be penalized for any regression of your issues. What do they expect the student to do: submit a certificate from the counseling office ?? 3/n
1
3
57
I found this piece in Horn's Robot Vision. Read the fairy tale attributed to Kermit Klingteil. The moral: "When you have difficulty in classification, do not look for ever more esoteric mathematical tricks; instead, find better features." The triumph of DL stated in the 80's.
0
6
57
Would you like to know how to define and realize an equivariant convolution and attention on a light field / feature field? Come to listen to
@xu_yinshua86846
and
@JiahuiLei1998
presenting our spotlight at 10:45am at poster
#309
@NeurIPSConf
1
7
56
This is an amazing dataset showing the triumph of COLMAP "COLMAP, a mature photogrammetry framework, provides 3D annotations that are treated as ground truth"
@mapo1
@SattlerTorsten
1
3
56
More ICCV nostalgia
#ICCV2021
: I had the privilege to do the clerical work at the in-person meeting of the PCs of ICCV 1993. Hans-Hellmut Nagel, Yoshiaki Shirai, and the late Tom Huang met on a very cold weekend in Karlrsuhe to make paper decisions. 1/3
2
3
53
DynMF is a sparse trajectory decomposition that enables robust per-point tracking. In addition to NVS, it allows us to control trajectories, enable/disable them, leading to new ways of video editing, dynamic motion decoupling, and novel motion synthesis.
0
7
52
How does convolution or attention work on feature fields defined on the space of rays?
@xu_yinshua86846
@Jiahui77036479
revised our paper and make a great case for generalized convolution/attention
@TacoCohen
@maurice_weiler
@mario1geiger
@_onionesque
2
15
52
#cvpr2022
I am very grateful to all in-time reviewers but also to all late reviewers who informed the AC about an ETA or even that they are unable to do it. And to all emergency reviewers who are stepping in this week.
Reviewing load this year is insane. 🙏🙏🙏
0
0
51
@JiahuiLei1998
and
@WenJiang_PL
finishing intrinsic calibration. Ready to capture the cowbird mating season in 4D with 8 cameras and 24 microphones in our smart aviary, a project with Marc Schmidt from
@PennSAS
Biology/Neuroscience and
@PennCIS
@GRASPlab
.
0
3
49
and my students and I are eternally blessed to have Professor Gallier sitting two doors away from me. Stand by: Harmonic analysis is next!!!
At 2100+ (not a typo) pages 🤯, this is almost all the Math you need for Machine Learning without dumbing it down! PDF link:
169
2K
11K
1
4
50
Google Lens fails here. Friends, what is this utensil and what is the name of this delicious food?
5
2
50
What a delight to see Professor Sugihara performing again a geometry mastery! The first year of my PhD, my advisor had passed me on his book on Algebraic approach to the recovery of three-dimensional shapes from single images. It was an eye opener to realize how constraint
杉原先生ｷﾀ―――(ﾟ∀ﾟ)―――― !!
Professor Sugihara's visit
4
61
235
0
6
48
Live streaming now of our Event-based CVPR Workshop and tons of related info in the workshop site:
1
10
47
Twitter: Sam is out.
Me: When my students will finally learn that you have to use \varSigma to have "greek" matrices appear in italic...
1
2
47
I am filled with a sense of wonder and admiration when I think about this incredible computer engineering accomplishment of NASA. It is still one of the most fulfilling places to work and my answer when people ask me what I would do if I were not in academia. I experience this
Amazing that a chip bricked in 46-yr-old Voyager I, preventing it from sending data, and NASA figured out how to split up and reallocate its functions to other hardware, sending code 15 billion miles away (45 hours round trip!)--and Voyager's back online.
218
3K
16K
0
1
45
So proud to be advisor together with
@vijay_r_kumar
of Wenxin Liu who defended today with an amazing presentation! Check her TLIO inertial neural ofometry! Thank you
@davsca1
,
@loiannog
,
@dineshjayaraman
, Jianbo and CJ!
1
2
45
It was clarified by the motion authors that one of the violations will be being late. This means that your PhD will be pretty much jeopardized if you happen to be late for any reason. 2/n
4
4
44
"Reviewers with an active penalty will be placed on a
list". Creating black lists is not a tradition in democratic organizations. It will also open pandora's box in terms of legal challenges and violates the academic freedom of scientific communication. 5/n
1
4
43
Hi ChatGPT, Please propose 12 potential reviewers based on the following paper abstract........
3
2
42
Many students and colleagues ask me why I am so obsessed with teaching (and publishing on) optical flow: I now have the right answer: Because a $69.99 COSTCO drone uses it !!!
@Michael_J_Black
@davsca1
@CSProfKGD
2
2
43
When you try to simultaneously review 5 papers for CVPR while driving….
1
1
43
We can't wait to welcome Lingjie in 2023! An amazing success for
@CIS_Penn
and the Penn vision community/graphics community!
Thrilled to announce that I will be joining the University of Pennsylvania as an Assistant Professor in January 2023! I'm extremely grateful to all those who have supported me all the way and I look forward to working with students and colleagues at Penn!
@PennEngineers
@CIS_Penn
54
21
514
1
0
41
"The most powerful companies in the world are shaping what artificial intelligence will become—but they’ll never get it right without the ethos and values of university scientists." Fei-fei Li
3
7
39
The experience of suggesting reviewers for
#cvpr2022
was so rewarding. I spent hours and hours visiting more than 100 GS pages, reading papers by potential reviewers, and learning better our exponentially growing community. Back to writing letters!
0
0
40
@Michael_J_Black
@geopavlakos
@nikoskolot
Today SPIN reached 1000 citations. A very powerful idea to leverage geometric model optimization in the training loop. It can be applied to other geometric problems natively solvable using optimization, too.
3
2
39
Penn Engineering Announces First Ivy League Undergraduate Degree in Artificial Intelligence
0
4
39
Do we really need scene supervision? Not really! Equivariant shape priors suffice for segmenting 3D objects. Great work,
@Jiahui77036479
@CongyueD
, and Karl S. !!!
Happy to introduce our new
#CVPR2023
paper EFEM with
@CongyueD
, Karl Schmeckpeper ,
@GuibasLeonidas
,
@KostasPenn
:
- Learn Equivariant object shape prior on ShapeNet;
- Directly Inference for scene object segmentation!
- A new dataset "Chairs and Mugs"!
2
12
65
2
2
38
Mitch Marcus hired Benjamin Pierce,
@RajeevAlur
and me, among many others between 1996-2001. But most importantly, he created the Penn Treebank more than 30 years ago, the first golden annotation of a large corpus.
0
2
38
Thank you
@rodneyabrooks
for the in-person talk at
@GRASPlab
and for sharing your views on computation. It is such a pleasure to listen to something different!
2
5
38
with Petros Marangos and Nikos Paragios at the HIAS Inaugural Symposium: ECCV 2010 Program Chairs Reunion! Hope everybody still has great memories from beautiful Crete!
0
0
38
Apparently, the motion targets senior researchers. Why should my students submit their papers without my name? How will it look in their CV? Will they have to put an asterisk (advisor blacklisted) ? 4/n
2
4
37
#ECCV2020
How can you predict video from both interaction and observation? Karl Schmeckpeper's paper with
@_oleh
Annie Xie Steven Tian
@svlevine
@chelseafinn
will be presented at 9a and 7p ET.
1
8
36
@NikolaiMatni
and I could not have been prouder today!
@KendallJQueen21
(now Dr. Kendall Queen) has defended his dissertation on the first event-vision-only lane following ground vehicle.
@GRASPlab
@PennEngineers
4
9
37
This was an amazing presentation by
@erikjbekkers
on equivariant neural fields and neural ideograms at the Equivision Workshop. I want to go and read all his 2024 papers now!
Looking forward to this! I'll talk about
Neural Ideograms and Geometry-Grounded Representation Learning
... and cats and dogs and owls!
Thank you
@KostasPenn
@CongyueD
and co for organizing this! Excited to be part of the program!
1
10
94
2
7
39
Come to poster
#73
at the NW corner of the hall to listen to
@Jiahui77036479
. Point clouds do not need supervision.
0
2
37
"Cross-Domain 3D Equivariant Image Embeddings" accepted at
#ICML2019
! Regression-free intra-class “mental rotation”.
1
7
35
Proud to announce the workshop that
@EdgarDobriban
and I are organizing on Sep 4. If you are excited about invariance, symmetry, equivariance, data augmentation register here:
0
15
34
Why we teach optical flow in computer vision. In the moving cubes illusion, take the middle row for 100 first frames and plot it as xt-slice: optical flow is orientation in space-time. Speed is inverse of slope. Rest of the illusion motions will be homework
#CIS580
.
Astonishing family of illusions. It's caused by the pixels at the edges of each segment, which change from white to black or vice-versa in synch with the reversal of the segment itself. The w-to-w or b-to-b jump from segment to edge is seen as movement.
0
333
1K
2
2
35
Students in Greece: The Archimedes Scholarship is a unique opportunity to do a PhD in Greece on foundational problems in AI. If you are interested in geometric problems and/or neuromorphic methods in vision and learning contact me for more information.
3
14
40
We knew that you can implement convolution with optics. Now ReLUs with optics:
Optics may perform deep learning calculations more efficiently than electronics, but most work only performs linear operations optically. Here, Marandi’s group at Caltech realizes a very promising all-optical ReLU nonlinear activation. (1/3)
6
32
148
0
5
32