Xi
@xiwang1212
Established researcher @cvg_ethz & Junior group leader at @tumcvg; formerly @INSAITinstitute @CVL_ETH @ait_eth @TUBerlin @AdobeResearch Oliva lab at @MIT_CSAIL
Can we match vision and language representations without any supervision or paired data? Surprisingly, yes! Our #CVPR2025 paper with @neekans and Daniel Cremers shows that the pairwise distances in both modalities are often enough to find correspondences. ⬇️1/4
I had the pleasure of visiting Dima's group last week, and it was truly stimulating and exciting to speak with the team. There are many fascinating projects currently underway — looking forward to seeing what comes next!
Thanks @xiwang1212 for visiting @BristolUni presenting your work @ETH_en and @TU_Muenchen at the MaVi Seminar Series. We very much enjoyed your 2-day visit and great ego-rich talk!
Join us on Wednesday, May 21, at 4 pm CEST, for a talk by @HildeKuehne on Advances in self-supervised multimodal learning as part of our talk series! Zoom: ethz.zoom.us/j/63716670526S……: More talks robotics-talks.com
Join us today, Wednesday, at 4 pm CEST, for a talk by @LingjieLiu1 on Towards Next-Gen 3D Reconstruction and Generation: From Visual Fidelity to Multimodal and Physical Understanding as part of our talk series! Zoom: ethz.zoom.us/j/63716670526S…: More talks robotics-talks.com
Join us this Friday (Feb. 28), 4 pm CET, for a talk by Kevin Chen (MIT) on insect-scale aerial robots driven by soft artificial muscles as a part of our MaP Robotics, Vision, and Control Talks! Zoom link: ethz.zoom.us/j/63716670526 Details & Full Schedule: robotics-talks.com
I am honored to give a keynote talk at the upcoming GenEAI workshop at ETRA in Toyko. Looking forward to talking about some of our recent work on this!
🚀 Join GenEAI (🔗geneai.edu.sot.tum.de) at @ETRA_conference on the fusion of GenAI and Eye Tracking with keynotes by @xiwang1212 (@ETH_en), @xucong_zhang (@tudelft) and Stein Dolan (@Meta) 🙏 to co-organizers from @UTokyo_News_en @RiceUniversity @TU_Muenchen 📄⌛March 10
We are organizing the third version of the Rhobin workshop at this year's CVPR, and have an outstanding lineup of speakers! Join us at @CVPR in June.
📢#CVPR workshop call for papers. Are you working on: - 3D humans - 3D objects - interactions for humans & objects Welcome to submit to our 3rd RHOBIN workshop! We have an amazing line of speakers! @CVPRConf @CVPRConf details see: rhobin-challenge.github.io
I am giving a talk at ZurichCV#8 event tonight at 18:00! You are more than welcome to join us! lnkd.in/ewrJirNg
Join us today for the first talk in this semester's Robotics, Vision, and Controls Talk series at ETH Zurich. Angela Dai @angelaqdai kicks it off; you can join in person or via Zoom. Details: robotics-talks.com
What a great pleasure of having Taein @taeinkwon1 presenting our poster ❤️
Poster #019 is up. Come and chat if you are interested in egocentric vision and action prediction!
Reconstructing 3D human-object interactions from images/videos is a key step towards realistic #3D humans for #AR/#VR and assistive #robots/#AI. To tackle this challenging problem my team and I have received an ERC Starting Grant 🎉 #ERCStG 📢 We look for 3x #PhD candidates!…
Come and join Anton’s talk of our work on multi-agent interior design system.
I will talk about I-Design in ECCV's CV4Metaverse workshop tomorrow (29th) at 10:10 in Amber 1 x.com/AntonObukhov1/…
🪗The submission deadline has been extended to July 18th anywhere on earth! 🪗
📜 Call for Papers 📜 The Women in Computer Vision (WiCV) workshop @eccvconf 2024 invites you to submit your research papers/extended abstracts! Deadline: July 12th, 2024 Authors can get partial refunds for registration/travel. #ECCV2024 Milan🇮🇹 #WiCV sites.google.com/view/wicveccv2…
That is what happens if you win RHOBIN challenge at CVPR 😉 You get accepted to ECCV :) Congrats to the authors for their nice work and big thanks for choosing our challenge as a benchmark!
Multi-HMR has been accepted to #ECCV2024🤸. With Multi-HMR, we won the ROBIN challenge on 3D human reconstruction at #CVPR2024. Today, we're releasing the training code on top of the existing demo code: github.com/naver/multi-hmr See you in Milano 👋