RT @giffmana: Oh wow, did you guys know that torch.compile can compile numpy code? And even run it on GPU?. This is pretty neat for all kin….

RT @elsa_lighthouse: #ELSAGeneralAssembly – Day 3. Yesterday, we enjoyed presentations by @AnnaLukina, @lorenzo_baraldi, Haralampos-G. Stra….

RT @PascalMettes: We are back at #ICCV2025 for the second workshop on Hyperbolic and Hyperspherical Learning for Computer Vision. We will….

RT @tkasarla_: Want to improve content safety and NSFW detection in CLIP? Hyperbolic geometry can make this possible. Check out our #CVPR20….

RT @federicobolelli: 💥Now at #WACV2025 . We are presenting our paper "Semantically Conditioned Prompts for Visual Recognition under Missi….

RT @elias_project: 🎉 ELIAS-ELLIS-VISMAC Winter School 2025 wrapped up on Jan 31—huge thanks to all participants, speakers, co-organisers, a….

RT @sama: it is (relatively) easy to copy something that you know works. it is extremely hard to do something new, risky, and difficult wh….

RT @Cineca1969: Leonardo si conferma tra i primi 10 supercomputer nella TOP500 🚀. Un risultato che rafforza la posizione dell’Italia nell’h….

RT @jbhuang0604: Me to students: "Writing a research paper sharpens your mind, trains you to think critically, and helps you communicate ef….

RT @PascalMettes: All vision-language models should have hyperbolic embeddings. Vision and language are incredibly hierarchical in nature!….

RT @MarcoCristani: 🫵5 DEMOS 5 REASONS TO COME❕❕❕🫵Robust depth sensing, segmentation made easy for medicians, fake detection🕵️‍♂️, RT odomet….

💥 Now at #ECCV2024.Lorenzo Baraldi and Federico Cocchi are presenting our demo "Showcase: Contrasting Deepfakes Embeddings". ✨ Step by at demo booth #5 and challenge yourself to identify Deepfakes!. Joint work with Leonardo, within the ELSA project.

💥Now at #ECCV2024,. S. Poppi and T. Poppi are are presenting our paper "Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models". ✨Step by at poster #99 for more details and discussion! Paper available at: @marcella_cornia @ricucch

💥Now at #ECCV2024. L. Baraldi and F. Cocchi are presenting our paper "Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities". ✨Step by at poster #3 for more details and discussion! Paper at: @marcella_cornia @ricucch

RT @marcella_cornia: 💥Now at #ECCV2024, @sarto_sara is presenting our paper "BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stro….

RT @thegautamkamath: Some CVPR 2025 new policies: .1. Submitters must review.2. Terrible reviewers will have their submissions rejected.3.….

RT @fondazione_fair: 𝗦𝗲𝘀𝘀𝗶𝗼𝗻𝗲 𝟭 - 𝗚𝗲𝗻𝗲𝗿𝗮𝗹 𝗖𝗼𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗙𝗔𝗜𝗥 focus su #𝗠𝗨𝗟𝗧𝗜𝗠𝗢𝗗𝗔𝗟.Interventi degli esperti: @eliricci_ da @UniTrento, @lorenz….

🔥 Today we are introducing LLaVA-MORE, a family of models that enhances #LLaVA by integrating #LLaMA 3.1 as the language model. 👉 Check out the repository at F. Cocchi, N. Moratelli, D. Caffagni, @sarto_sara @marcella_cornia @ricucch.

RT @CSProfKGD: .@CVPR now ranked second under Google's annual "Top Publications"

RT @MarcoCristani: CALL-4-DEMO @eccvconf: Please hurry up! Wowy computer vision demos are required at ECCV 2024! Deadline Jul 19, 2024 11:5….