Hilde Kuehne @HildeKuehne Twitter profile

Last Seen Profiles

@KondorDZN

@RichardEngel

@woj_web3

@EndeavorAudio

@colboc_matys

@xzhd13

@_Toorauz

@P4EEsports

@hxneoneil

@bethanylouwhoo

@ay504217

@gizemlax

@museumofsex

@FQAppState

@MiL_cos

@AntigoLiberal

@taitedesco

@stwmaniax

@bokeplokalmalam

@Liam_willfollo

@kounosu_stds

@atanak74

@freduarte

@stw_pdg

@somsram

@J_sanchezz10

@Peacefuuuulllll

@bokeplokalmalam

@HistoryMttrs

@materielnet

@11jjj777jjj11

@applemintey

@_Brindacier

Hilde Kuehne

@HildeKuehne

2 months

Now that the @NeurIPSConf rebuttal is over, I finally have time to announce that in the middle of everything, I had the pleasure of starting my new position as a professor at the Tuebingen AI Center at the @uni_tue ✌️🥳🎉!

32

17

497

Hilde Kuehne

@HildeKuehne

2 years

Happy to finally share our paper about differentiable Top-K Learning by Sorting that didn’t make it to #CVPR2022 , but was accepted for #ICML2022 ! We show that you can improve classification by actually considering top-1 + runner-ups… 1/6🧵 #ComputerVision #AI #MachineLearning

8

44

372

Hilde Kuehne

@HildeKuehne

2 years

Happy to announce that our workshop on Differentiable Almost Everything #diffxyz got accepted to #ICML2023 Check out the website: @FHKPetersen @CuturiMarco @Mniepert @Michael_A_Kagan @willieneis @StefanoErmon CfP coming soon!

4

49

308

Hilde Kuehne

@HildeKuehne

6 months

Ever asked yourself what's the best explainability method for ViT Transformer at the moment? 🚨 We present you LeGrad, a Layerwise Explainability GRADient method for large ViT transformer architectures. 🚨 So, grab your ☕️ and 🥐, release your inner 🇫🇷, and join us on our

4

47

250

Hilde Kuehne

@HildeKuehne

2 years

Hi! I have a phd position in video understanding to fill! If you are interested in research, have a MSc in CS, #ML etc. and ideally already a bit of publication experience in #cv / ML, reach out! Also if you think about applying to #ellis and need a backup!

11

65

233

Hilde Kuehne

@HildeKuehne

8 months

I never thought there would come a day when people would dare to consider SVD to be anything but Singular Value Decomposition …

mkshing

@mk1stats

8 months

SVD 1.1 seems to have been released 👀 HF: For those who can't wait for the official announcement, you can try it on this colab for free. Colab: 1/3 #SVD

6

51

174

8

10

218

Hilde Kuehne

@HildeKuehne

2 years

Looking for PhD students! 👩‍🎓/👨‍🎓 If you're around at #CVPR2022 (or not) and interested in a PhD in multimodal video understanding, feel free to pm me, drop by at our poster, or just drop me a mail. @cvpr @MITIBMLab #ComputerVision #AI #MachineLearning

9

33

208

Hilde Kuehne

@HildeKuehne

2 months

🚨 New Paper Alert! 🚨 *Mask Inversion* What it does? -> It learns a token representation for a specific region in an image (e.g. a token for a mask, a BBox etc.) project page: paper: code:

4

38

171

Hilde Kuehne

@HildeKuehne

1 year

On my way to #ICCV2023 ! Looking forward to an exciting week packed with workshops, talks, and posters. Here's where you will find me on the first day: We are organizing two workshops on Oct 2 (morning): * What is Next in Multimodal Foundation Models? - P01 - 8:30-12:30 ->

3

20

154

Hilde Kuehne

@HildeKuehne

2 years

So proud to be awarded the Mark Everingham Prize at #ECCV2022 for our work on HMDB51, but even happier to share this prize with my dear colleagues Mubarak Shah and @wjscheirer Big kudos to my collaborators Hueihan & @tserre 🙌 Couldn't have done it without you!

14

6

125

Hilde Kuehne

@HildeKuehne

1 year

Best summary of #Academia vs. #industry ever! by Bill Freeman 😁 at the Quo vadis, Computer Vision Workshop @ICCVConference #ICCV2023

1

21

124

Hilde Kuehne

@HildeKuehne

6 months

Let’s face it… Just because you don’t know what’s in your training data, you can not just call it zero-shot 🤷‍♀️ 1) We just relabeled the old concept of zero-shot learning from attributes to “I have not checked my training data “ resp. “ I have not seen the dataset” (and even

Gary Marcus

@GaryMarcus

6 months

So much for emergent magic. If VCs understood the significance of this paper, they would make radically different choices. It really is driverless cars all over again.

14

34

197

2

18

121

Hilde Kuehne

@HildeKuehne

7 months

We welcome submissions to our Multimodal Foundation Models and their applications Workshop (MMFM2) at @CVPR 2024. We have archival and non-archival tracks (including works accepted to CVPR without modification to the paper). We expect a large attendance, and it’s a great

1

18

91

Hilde Kuehne

@HildeKuehne

3 years

🥳🥳🥳 @ Hueihan Jhuang , Estibaliz Garrote , Tomaso Poggio , @tserre ... so honored to be given the chance to work with you on that! #ICCV2021 @MIT_CSAIL @MITIBMLab @goetheuni

ICCV2021

@ICCV_2021

3 years

PAMI Helmholtz Prize in @ICCV2021 to papers from #ICCV2011 with significant impact on computer vision research ** ORB: An efficient alternative to SIFT or SURF and ** HMDB: A large video database for human motion recognition and ** DTAM: Dense tracking and mapping in real-time

1

12

68

17

6

90

Hilde Kuehne

@HildeKuehne

5 months

Working on Multimodal foundation models (MMFMs)! Busy with NeurIPS? ... and ... want to go to @CVPR ? Check out our @CVPR MMFM Challenge on understanding multimodal data etc: Have some VL/MM model around? Give it a try! @MIT_CSAIL @berkeley_ai

MMFM 2nd Workshop - Challenge

News Update: The winners for the CVPR 2024 iteration of the challenge are announced here. Congratulations to all the teams!

sites.google.com

1

8

84

Hilde Kuehne

@HildeKuehne

5 months

Join us at the beach 🏝️…

#ICCV2023

@ICCVConference

7 months

#ICCV2025 will be in Honolulu, Hawaii 🇺🇸 🌴

3

23

392

1

0

78

Hilde Kuehne

@HildeKuehne

9 months

Andrew Zissermann is giving a talk at the BMVA symposium on vision language about how to generate textual descriptions for movies. Great talk and great line of work to make movies accessible for everyone. Check out the papers: 📽️

0

12

75

Hilde Kuehne

@HildeKuehne

9 months

This is how you party against hate and racism! #frankfurtstehtauf #wirsindmehr #Frankfurt

17

8

68

Hilde Kuehne

@HildeKuehne

3 months

Kudos to the @CVPR social media team! You’re doing a terrific great job 👏

2

10

68

Hilde Kuehne

@HildeKuehne

1 year

Just as everyone is waiting for #iccv2023 #decisions , happy to announce the Open Fine-grained Activity Detection Challenge (OpenFAD) in conjunction with the 2nd Workshop on Fine Grained Activity Detection @ICCVConference

1

12

62

Hilde Kuehne

@HildeKuehne

5 days

Happy to announce that I will have open PhD slots for the IMPRS-IS program @uni_tue ! You can apply here: Deadline is Nov 15th. Ask me @eccvconf for any details!

Intelligent Systems

@MPI_IS

7 days

Researching #AI #MachineLearning #Robotics #HCI ? Join our elite doctoral program - a partnership with MPI-IS, @uni_stuttgart & @uni_tue ! Applications accepted until Nov 15, 2024 at

1

13

27

0

14

61

Hilde Kuehne

@HildeKuehne

2 years

Happy to announce that I've joined @Hessian_AI as a member! Looking forward to working together with so many great colleagues in the area @kerstingAIML @m_mezini @stefanroth @mundt_martin and many more!

4

3

60

Hilde Kuehne

@HildeKuehne

2 years

Call for Women in Computer Vision #WiCV workshop organizer at #ICCV2023 If you want to be an organizer for the #WiCV workshop at ICCV 2023, please fill out the form by Jan 20, 2023: Please RT and share. We look forward to your application. #CVPR2023

WiCV@ICCV2023 Organizer Application

We are recruiting organizers for the Women in Computer Vision Workshop (WiCV) held in conjunction with ICCV 2023. This will be a great opportunity to get experience organising a workshop and working...

docs.google.com

1

33

60

Hilde Kuehne

@HildeKuehne

1 year

Great first talk at the Anticipating Human Behavior Workshop by Jürgen Gall happening today @UniBonn ! Looking forward to more talks today i.a. By @SvenBehnke and @dimadamen

2

8

53

Hilde Kuehne

@HildeKuehne

2 years

Happy to share the video to our #ICML2022 paper on top-K classification learning via sorting loss! Check it out 👇 Paper: Spotlight: Wed 1:25-1:30 p.m. EDT @ Ballroom 1 & 2 Poster: Wed 6:30-8:30 p.m. EDT @ Hall E #328 @MITIBMLab

Differentiable Top-k Classification Learning

The top-k classification accuracy is one of the core metrics in machine learning. Here, k is conventionally a positive integer, such as 1 or 5, leading to to...

proceedings.mlr.press

0

5

53

Hilde Kuehne

@HildeKuehne

3 years

Our #NeurIPS2021 paper on Algorithmic Supervision #AlgoVision got features in in Yannic Kilchers @ykilcher ML News #mlnews #ai Check it out: Congrats @FHKPetersen @OliverDeussen Christian Borgelt! Paper: @MITIBMLab @goetheuni

2

9

49

Hilde Kuehne

@HildeKuehne

2 years

Happy to announce our #iclr2023 paper Contrastive Audio-Visual Masked Autoencoder CAV-MAE Paper: Code (incl. checkpoints ): Details below 👇 #computervision #machinelearning #ai @MIT_CSAIL @MITIBMLab

GitHub - YuanGongND/cav-mae: Code and Pretrained Models for ICLR 2023 Paper "Contrastive Audio-Vi...

Code and Pretrained Models for ICLR 2023 Paper "Contrastive Audio-Visual Masked Autoencoder". - YuanGongND/cav-mae

github.com

1

8

49

Hilde Kuehne

@HildeKuehne

1 year

Currently happening at the poster session in Foyer Sud. Drop by our posters 4 + 5 … and yes, we have two posters right next to each other, and no, we didn’t plan for that 😁😁 @ICCVConference #ICCV2023 @ninashv__ @anna_kukleva_

0

4

50

Hilde Kuehne

@HildeKuehne

3 years

How to integrate #algorithms into end-to-end trainable #neuralnetwork based on general approximation of discrete conditions? Accepted to #NeurIPS2021 Great work @FHKPetersen @OliverDeussen ! @MITIBMLab @goetheuni @UniKonstanz

1

13

46

Hilde Kuehne

@HildeKuehne

1 year

Starting a series here #ICCV2023 ... @ICCVConference @WiCVworkshop

3

2

48

Hilde Kuehne

@HildeKuehne

1 year

Sometimes you just have to get out and enjoy the beauty around you #CVPR2023 #Vancouver

0

1

45

Hilde Kuehne

@HildeKuehne

6 months

@ylecun People always forget how closely first computers were interweaved with textile industry…

6

3

45

Hilde Kuehne

@HildeKuehne

1 year

Info especially for the junior folks in the #computervision community 👉 Please subscribe to the PAMI TC newsletter: It’s a monthly email with all relevant information about conferences and calls. NO SPAM! Just everything important in one place from the

0

12

44

Hilde Kuehne

@HildeKuehne

2 years

On my way to the Vision and Sports #SummerSchool in Praha #vs3 ! Looking forward to a week of science, sports , and fun 🤩 with Ondrej Chum, @VittoFerrariCV Christoph Lampert Patrick Perez @davnov134 Jiri Matas. #ml #computervision #AI

3

0

44

Hilde Kuehne

@HildeKuehne

2 months

Just some random theory I wanted to share for a while ... the "ACADEMIC IKEA" effect: Idea: The more your supervisor is directly involved in your work, the more he/she will like it.

Sketchplanations - A weekly explanation in a sketch

We love it more if we made it. Or, more scientifically perhaps, the IKEA effect is ‘the increase in valuation of self-made products,’ when we have put more effort into it. Turns out, if we’ve put...

sketchplanations.com

2

1

42

Hilde Kuehne

@HildeKuehne

1 year

The @LamarrInstitute at the @UniBonn welcomes applications for assistant W1(TTW3) and full professorships in #ArtificialIntelligence and #MachineLearning ! Checkt out details here: W1TTW3: W3: Deadline: November 15, 2023 #ML #AI

0

13

42

Hilde Kuehne

@HildeKuehne

2 years

Check out our #CVPR2022 paper! We improve multimodal zero-shot text-to-video retrieval on Youcook2/MSR-VTT by leveraging fusion transformer and combinatorial loss. 1/🧵 #ComputerVision #AI #MachineLearning @MITIBMLab @goetheuni @MIT_CSAIL @IBMResearch

1

8

41

Hilde Kuehne

@HildeKuehne

3 years

Just citing this to celebrate … two papers accepted to #cvpr2022 🎉 ! First glimpse on how to get multimodal fusion transformer to work: Will post more details after #eccv2022 deadline 👻

Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval

Multi-modal learning from video data has seen increased attention recently as it allows to train semantically meaningful embeddings without human annotation enabling tasks like zero-shot retrieval...

arxiv.org

#CVPR2024

@CVPR

3 years

#CVPR2022 facts: CVPR is ranked #4 among ALL publications on Google Scholar.

1

45

252

2

40

Hilde Kuehne

@HildeKuehne

1 year

What is Next in Multimodal Foundation Models? Workshop is starting now with a talk by @trevordarrell ! Don’t miss it! #ICCV2023 @ICCVConference

0

5

39

Hilde Kuehne

@HildeKuehne

3 years

Just because I'm back to academia ... Could we have a flag for ML conferences which says "Industry resources used? yes/no" to convey why we did not train 3 months on 1024 GPUs to search for good parameters for this "one" model? Also, not every company has FAAGN scale resources.

2

0

37

Hilde Kuehne

@HildeKuehne

1 year

Love the talk 🤩 , but I have to answer that ...

Jon Barron

@jon_barron

1 year

A bunch of people have requested the slides for my "Scholars & Big Models" CVPR workshop talk. I didn't have a script, but I wrote a rough version of what I probably said at the bottom of each slide. Feedback is welcome!

3

61

403

0

5

36

Hilde Kuehne

@HildeKuehne

1 year

Shoutout 🎉and applause 👏 for this year’s #CVPR2023 @WiCVworkshop team for organizing such a great workshop! Kudos to Doris Antensteiner @halawa_marah @ivakshi_s @xinw_ai @sunniesuhyoung @AsraAslam14 @ziqi_huang_ Sachini Herath Aparna Akula

WiCV

@WiCVworkshop

1 year

Come say hi to our organizers on ground, collect a tote bag and talk with our sponsors at 10.50 am @CVPR #WICV

0

4

15

2

6

37

Hilde Kuehne

@HildeKuehne

2 years

Happy to share our #NeurIPS2022 paper on differentiable logic gates! Want to find out how to run Neural Network only on binary decisions 0/1? How to make logic gate networks differentiable? Here is a :thread:1/4 paper: #computervision #machinelearning #ai

2

3

37

Hilde Kuehne

@HildeKuehne

2 years

#ECCV2022 paper stats: 2 accepted, 2 rejected, 1 withdrawn. Check it out👇! @AishaUroojKhan : VQA Grounding in Vision Language Transformers @WeiLinCV : Domain Adaptation from Image to Video: Big congrats to both first authors!

CycDA: Unsupervised Cycle Domain Adaptation from Image to Video

Although action recognition has achieved impressive results over recent years, both collection and annotation of video training data are still time-consuming and cost intensive. Therefore,...

arxiv.org

1

36

Hilde Kuehne

@HildeKuehne

1 year

Let’s blow them… no more retweets or likes for industry accounts. Let’s start featuring Phds like never before! #cvpr2023

Shashank Tripathi

@sha2nk_t

1 year

<-- Follower counts --> GoogleAI - 1.9M OpenAI - 2.3M MetaAI - 409K Famous CV Researchers - ~15K Me - 448 Let the competition begin. 🥲

7

6

95

0

1

35

Hilde Kuehne

@HildeKuehne

1 year

🤩🙏

chiaraplizzari

@chiaraplizzari

1 year

Only great talks in S04! 🤗 #WiCV #ICCV2023 @HildeKuehne

1

38

0

1

35

Hilde Kuehne

@HildeKuehne

1 year

Super crowded poster session at the MMF Workshop… and the main conference hasn’t even started 🙃 @ICCVConference #ICCV2023

0

1

35

Hilde Kuehne

@HildeKuehne

7 months

We could make this a new metric for faculty hiring… how many papers (absolute or ratio, whatever you want) of your scholar stack have a female first author that’s not you 👩 … ?

F. Güney

@ftm_guney

7 months

no better way to celebrate women’s day than submitting a paper with a female student as the first author. I’m sorry but it’s a big deal, it doesn’t happen very often. in fact, the first in 4.5 years! let’s hope, first of many 🤞🏽

4

2

89

4

2

34

Hilde Kuehne

@HildeKuehne

6 months

I thought this was funny first… now I’m thinking about writing a thread about how research papers (which should first be out there to communicate new findings and to share knowledge with your community) being used as a pseudo metric for various performance measures where your

Alexander Terenin

@avt_im

6 months

The NeurIPS high school track has made its way to Chinese social media. The collaborator who sent me this said there is at least one example of a professor asking their PhD student to help write a paper for one of their kids so that it can help their college admissions abroad.

13

47

360

2

34

Hilde Kuehne

@HildeKuehne

19 days

Shout out to @MattNiessner for tapping the barrel in one hit at the GCPR dinner tonight! @gcpr_by_dagm Thanks to everyone for being there! It was a great evening! 🍻🍗🥨

1

2

33

Hilde Kuehne

@HildeKuehne

2 years

You know you have the best collaborators in the world when every great paper comes with an even better shirt! 🙏 @FHKPetersen #ICLR2023 Paper: @sutter_tobias Christian Borgelt @dongsunghuh Yuekai Sun @OliverDeussen #AI #MachineLearning

0

2

34

Hilde Kuehne

@HildeKuehne

9 months

Super interesting talk by @frank_e_keller at the sold-out vision language BMVA symposium today: Big thanks to @TengdaHan @davmoltisanti and @mwray0 for organizing this event! 🥳🙏

1

2

34

Hilde Kuehne

@HildeKuehne

6 months

I'm not sure if this is the best possible outcome. I thought a lot about if I should write about this or not, but I hope there is some value in thinking about this a bit more. A longer 🧵 ...

David Picard

@david_picard

6 months

And this is why I never appeal. The only valid reason is AC hit the wrong button, but there's a reason we have triplets...

3

1

16

1

2

32

Hilde Kuehne

@HildeKuehne

2 months

If you made it till here, I'm also looking for some great PhDs and PostDocs 👀 to work on everything from data generation to large-scale multimodal retrieval. If you have a solid Top-A track record (PostDoc) or just some first paper(s) and want to do more (PhD), please ping me

5

9

33

Hilde Kuehne

@HildeKuehne

2 years

To my fellow #CVPR #CVPR2023 AC (after finishing my paper assignments): Please do NOT just click the first 10 ones with highest affinity score. Too much noise in the system. We all know how important communities are, so match the right papers with the right reviewers. Please rt!

1

6

33

Hilde Kuehne

@HildeKuehne

1 year

The CfP for our @NeurIPSConf Workshop on Associative Memory & Hopfield Networks is out! The deadline is Sep 29th! Details: Speakers: @HopfieldJohn @DimaKrotov @HochreiterSepp @carlolucibello @kchorolab @FieteGroup @MITIBMLab @Harvard @IBMResearch

AMHN Workshop @NeurIPS 2023

Associative Memory & Hopfield Network Worshop @NeurIPS 2023. Discuss the latest multidisciplinary developments in Associative Memory and Hopfield Networks. Imagine new tools built around memory as...

amhn.vizhub.ai

0

12

33

Hilde Kuehne

@HildeKuehne

3 years

Ever wondered how 3D differentiable rendering can work on real world images? Check out our #WACV2022 paper on 3D Reconstruction via Style Transfer! Paper: Video: Great work @FHKPetersen @OliverDeussen ! @goetheuni @MITIBMLab

1

5

31

Hilde Kuehne

@HildeKuehne

2 years

@PhD_Genie Once gave a talk in the lab of a close collaborator. Head of the group introduced me to the folks with “… you can talk with her about everything. I 100% trust her.“ … biggest compliment I ever got in academia.

0

31

Hilde Kuehne

@HildeKuehne

1 year

Going to @ICCVConference ? Drop by at our posters! I'll be around at all of them! #ICCV2023 MAXI: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge Paper: Code: Wed 4th, 10:30-12:30, Foyer Sud – ID

0

3

29

Hilde Kuehne

@HildeKuehne

4 months

Hi @NeurIPSConf ! Just to get this out off my system ... would there be any way to replace those checklists at the end of the paper with questions that you have to click and fill during submission? Just the same information in a more organized way ...

2

0

30

Hilde Kuehne

@HildeKuehne

2 years

Very glad and honored to join as a mentor to discuss aspects of industry vs. academia and how to manage your supervisor 😇 ... sign up and let's chat! #CVPR2022

#CVPR2024

@CVPR

2 years

Our #CVPR2022 Social Activities Chairs have created a speed-mentoring event curated for our student attendees. Details:

5

7

36

1

3

30

Hilde Kuehne

@HildeKuehne

1 year

I stand with my point to keep the social media ban for CVPR! #CVPR2023 Having a paper on arxiv is a different story than having a full blown social media campaign as we have seen before.

3

4

30

Hilde Kuehne

@HildeKuehne

3 years

In case you have a female PhD, encourage her to submit here 👇 It’s great opportunity to get to know folks and to present your work!

WiCV

@WiCVworkshop

3 years

DEADLINE EXTENDED for the Women in Computer Vision (WiCV) workshop @ #CVPR2022 . Updated submission deadline: March 10, 2022 11:59 pm PT More details here: @CVPR Please RT/amplify

1

19

32

1

4

30

Hilde Kuehne

@HildeKuehne

2 years

Check out our paper "Augmentation Learning for Semi-Supervised Classification" at #GCPR2022 , the German Conference on Pattern Recognition. #imageprocessing #patternrecognition #computervision

Augmentation Learning for Semi-Supervised Classification

Recently, a number of new Semi-Supervised Learning methods have emerged. As the accuracy for ImageNet and similar datasets increased over time, the performance on tasks beyond the classification...

arxiv.org

3

29

Hilde Kuehne

@HildeKuehne

7 months

Did you know that a pretrained VL foundation model is all you need for open vocabulary localization and segmentation ? ❗️No training needed❗️Just get your favorite model and localize everything! 💎 Pro-tip: try meta-clip All you need to know is below 👇 Grounding

0

1

28

Hilde Kuehne

@HildeKuehne

1 year

@MushtaqBilalPhD Equally can feel like discrimination for those who where profiting from the inequality … But shoutout for the young woman who had the courage to stand up against a full panel at such an event. nsf or eu, give that woman a grant!

1

28

Hilde Kuehne

@HildeKuehne

2 years

Check out our new work, where we analyze how much zero-shot learning current VL models are actually capable of! paper: #CLIP #machinelearning #ai #computervision 1/3

VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of...

Vision-language models trained on large, randomly collected data had significant impact in many areas since they appeared. But as they show great performance in various fields, such as...

arxiv.org

1

0

28

Hilde Kuehne

@HildeKuehne

9 months

It was an honor to organize #WACV2024 conference with you! @MajiSubhransu @CSProfKGD and Vlad!

Kosta Derpanis at #ECCV2024 Milan 🇮🇹

@CSProfKGD

9 months

That’s a wrap for your #WACV2024 Program Chairs. On behalf of @MajiSubhransu @HildeKuehne and Vlad Morariu, it was an honour and pleasure 😅

1

3

59

0

2

27

Hilde Kuehne

@HildeKuehne

2 years

@MattNiessner Dancefloor at #eccv2018 … #ECCV just knows how to party 🎉 @CSProfKGD

1

3

26

Hilde Kuehne

@HildeKuehne

1 year

Why the #EUAIAct might be bad for #AI #Research in the #EU and why we should care. A long 🧵 1/15 Disclaimer: *I’m not a legal expert, but I work with #AI models *I’m happy to discuss if you have some insights that I have missed *I am part of #LAION *All opinions are my own

Daniel Leufer

@djleufer

1 year

The Committee text from May was basically adopted without changes, so this is the text that the Parliament has now approved, which is this:

1

4

14

2

7

25

Hilde Kuehne

@HildeKuehne

8 months

Last push for @CVPR rebuttals … we are almost there

1

3

25

Hilde Kuehne

@HildeKuehne

4 months

🚨 @CVPR Challenge alert!🚨 Think you have a good MML for documents, infographics and text-rich images? Challenge “What is Next in Multimodal Foundation Models?” extended the deadline and opened for all: $10K in prizes Deadline: 5th June 2024 (11 days)!

MMFM 2nd Workshop

News: The program is set at: Program We are hosting the 🏆MMFM Challenge focused on multimodal document understanding. 🥳New information about the poster session. More information under Call for...

sites.google.com

0

9

26

Hilde Kuehne

@HildeKuehne

11 months

Getting closer to #CVPR2024 deadline ...

0

1

26

Hilde Kuehne

@HildeKuehne

2 years

Our work on pretraining action classification backbones with synthetic data was featured in MIT News: in collaboration with Yo-whan Kim, @samarthm44 , SouYoung Jin, @rpanda89 , @leokarlin , @Saligrama_Lab , @kate_saenko_ , @AudeOliva , @RogerioFeris 1/4

In machine learning, synthetic data can offer real performance improvements

Machine-learning models trained to classify human actions using synthetic data can outperform models trained using real data in certain situations. This could help scientists identify when it’s...

news.mit.edu

1

6

26

Hilde Kuehne

@HildeKuehne

2 years

Hi everybody! As the new year is finally here 🎊, what was your coolest paper (with link if you want) of 2022? And what do you think will be the most exciting topics in CV in 2023? 🌅 #ml #computervision

5

25

Hilde Kuehne

@HildeKuehne

3 months

Gem demo at work. Prompt was „phone“ 😁 GEM💎: Grounding Everything (in particular grounding VLM transformers) at Demo #13 at @CVPR @BousselhamWalid @HildeKuehne @VittoFerrariCV

0

1

25

Hilde Kuehne

@HildeKuehne

1 year

Big congrats 🥳🥳 to @mamatathota for passing her PhD! And to @geleonti for graduating such a great PhD! It was an honor and a pleasure to be part of this committee!

Georgios Leontidis

@geleonti

1 year

Delighted that @mamatathota passed her PhD viva today with minor corrections! Mamatha did a great PhD that focused on (continual & un/self-supervised) domain adaptation - Mamatha is the third PhD student of mine graduating this year & last one from my days at Lincoln University

2

15

2

3

24

Hilde Kuehne

@HildeKuehne

4 months

This is important! 👇Please drop by if you’re interested in where the community is going! @CVPR

Walter Scheirer

@wjscheirer

4 months

Attending #CVPR2024 ? Consider attending the PAMI TC meeting (4pm Thurs. Summit Flex Hall ABC) where we'll be discussing important potential changes to the review process and the location of #ICCV2029 . The TC meeting gives the community a voice on conference operations.

1

12

32

0

3

24

Hilde Kuehne

@HildeKuehne

1 year

@dimadamen Fundation Models 😁 it’s still just fancy sounding pretrained backbones

4

1

24

Hilde Kuehne

@HildeKuehne

2 years

Interested in organizing a tutorial related to #ComputerVision ? We are welcoming proposals for tutorials at the 2022 Asian Conference on Computer Vision! Details under Join us by submitting your proposal until June 8th! #ACCV2022 #CVPR #ICCV #ECCV

0

7

23

Hilde Kuehne

@HildeKuehne

8 months

🚨Call for #WiCV workshop organizer at #ECCV2024 is open! 🚨 Please consider applying 👇it's a great event and a lot of fun! @eccvconf

WiCV

@WiCVworkshop

8 months

Call for Women in Computer Vision #WiCV workshop organizer at #ECCV2024 If you want to be an organizer for the #WiCV workshop at ECCV 2024, please fill out the form by Feb 04, 2024: Please RT and share. We look forward to your application.

0

17

29

0

9

21

Hilde Kuehne

@HildeKuehne

3 years

With #ICCV2021 just around the corner, I'm happy to present our paper on Detector-Free Weakly Supervised Grounding (DF-WSG) Ses. 2 - Tue, 11 - 12 , Thu, 6 – 7 Check out the paper: See you there! #computervision #computerscience #machinelearning #AI

2

13

21

Hilde Kuehne

@HildeKuehne

2 years

Aloha ... 🐢 PCs at work to finalize the last details for #WACV2024 CfP. Stay tuned! Hope to bring you a great conference in wonderful #Hawaii 🏝️🌊🏝️ ! @MajiSubhransu @CSProfKGD and Vlad Morariu

Kosta Derpanis at #ECCV2024 Milan 🇮🇹

@CSProfKGD

2 years

#WACV2024 Hawaii planning meeting among your Program Chairs @HildeKuehne @MajiSubhransu Vlad Morariu and me. Call for papers coming out VERY soon!

0

48

0

2

22

Hilde Kuehne

@HildeKuehne

4 months

Deadline for GCPR 2024 just got extended! New deadline: June 5, 23:59 CEST Come to Munich! 🍻🥨 @gcpr_by_dagm #ML #computervision

GCPR 2024

@gcpr_by_dagm

6 months

The German Conference on Pattern Recognition (GCPR) will take place in Munich, Germany, September 10 - September 13, 2024

2

9

25

0

3

21

Hilde Kuehne

@HildeKuehne

7 months

It was a pleasure to be there! 🤩Thanks so much for inviting me!

Cees Snoek

@cgmsnoek

7 months

Finally we have a video-native lecture at the #FoMo winterschool, by @HildeKuehne

1

0

21

0

22

Hilde Kuehne

@HildeKuehne

4 months

I will also cover a bit of Whisper-Flamingo at the @CVPR Sight and Sound workshop today ()

Andrew Rouditchenko 🇺🇦

@arouditchenko

4 months

Excited to introduce Whisper-Flamingo! Check out the demo video; Whisper-Flamingo can transcribe and translate speech with heavy background noise! Paper: Code, Pre-trained models, Colab:

2

3

32

0

5

21

Hilde Kuehne

@HildeKuehne

10 months

Happy to share our latest project: GEM 💎 ! Check it out! 👇

Walid BOUSSELHAM

@BousselhamWalid

10 months

Happy to announce our latest paper: Grounding Everything: Emerging Localization Properties in Vision-Language Transformers 🎉🎉🎉 GEM allows a training-free adaptation of Vision-Language models (e.g., CLIP ...) to perform zero-shot open-vocabulary segmentation.

5

15

88

0

1

21

Hilde Kuehne

@HildeKuehne

10 months

GEM 💎 ... finding #beer in #Boston Paper: Code: Demo: @BousselhamWalid @FHKPetersen @VittoFerrariCV @MITIBMLab #CV #AI

WelcomeToDot

@WelcomeToDot

10 months

"Create an image of local Boston culture." "OK, make it more Boston." "Make it even more Boston." "Make it so Boston it hurts"

22

65

537

0

4

20

Hilde Kuehne

@HildeKuehne

3 months

Just to chime in here a bit why this might not be correct ... 1) We have reason to assume that web scrap data includes samples from or very similar to the used dataset, including INet () ... you can not do better than training on test data.

Does CLIP's Generalization Performance Mainly Stem from High...

Foundation models like CLIP are trained on hundreds of millions of samples and effortlessly generalize to new tasks and inputs. Out of the box, CLIP shows stellar zero-shot and few-shot...

arxiv.org

Lucas Beyer (bl16)

@giffmana

3 months

Finally someone did the only correct baseline and ta da, synthetic images don’t actually help!

14

20

236

2

4

19

Hilde Kuehne

@HildeKuehne

7 months

Hi @CVPR ! I know everyone is busy with ECCV, but is there already a time plan on how and when to handle appeals? Asking as author and AC…

3

2

18

Hilde Kuehne

@HildeKuehne

11 months

Ready for the last major deadline of the year @CVPR ? We almost made it folks! #CVPR2024

0

1

17

Hilde Kuehne

@HildeKuehne

2 years

This works with any differentiable sorting framework: NeuralSort: SoftSort: SinkhornSort: DiffSortNets: 5/6🧵 @CuturiMarco @adityagrover_ @SebastianPrillo

Differentiable Sorting Networks for Scalable Sorting and Ranking...

Sorting and ranking supervision is a method for training neural networks end-to-end based on ordering constraints. That is, the ground truth order of sets of samples is known, while their absolute...

arxiv.org

1

3

16

Hilde Kuehne

@HildeKuehne

4 months

This is it! With @NeurIPSConf D&B, the last deadline for a major conference in 2024 is done! Congrats to everybody who gave it a try!🥳 ... and now up to the 500 add-on evaluations promised for the supplementary! 🤣

0

17

Hilde Kuehne

@HildeKuehne

7 months

Happy to represent academic AI research at this year’s reception for the 2024 annual report of the Commission of Experts for Research and Innovation In german: @EFI_Kommission @UniBonn

0

17

Hilde Kuehne

@HildeKuehne

23 days

@Michael_J_Black TLDR: As long as we rely on voluntary reviewing, we can not enforce bans for paper submissions for bad reviewers. Long version: I’m not sure if the reviewer system can be steered by negative extrinsic feedback. The natural reaction to this is that less people sign up for review

0

16

Hilde Kuehne

@HildeKuehne

2 years

Check out our paper about monotonic differentiable sorting at #ICLR22 ! It really works! Great work by @FHKPetersen with @OliverDeussen and Christian Borgelt! 👇Happening now! @goetheuni @MITIBMLab

Felix Petersen

@FHKPetersen

2 years

Come and meet me at our #ICLR2022 poster session on #differentiable #sorting . It is right now ;) (spot E0). ... or watch our presentation on YouTube

0

8

0

3

15

Hilde Kuehne

@HildeKuehne

2 years

@taiyasaki There was no big motivation to cheat bc there was not the same level of funding as today and no paper would get you anywhere near a 6-figure job. Things changed when papers were used as surrogate metric for big hiring, and a few years we’re still not ready for this DDOS attack.

0

15

Hilde Kuehne

@HildeKuehne

4 months

I think it might be worth discussing of a system between @CVPR and @ICCVConference or @eccvconf to allow to pass on previous reviews for the submission, but 100% optional. This is not the same as a rolling submission, but even implementing this will take time as conferences