๐ Are you at #ICCV2025?
Check out Poster #125 where we present ScanDiff:
โ
Generates diverse, realistic human scanpaths
โ
Uses diffusion + ViTs + optional text conditioning
โ
Beats SOTA in free-viewing & task-driven tasks
Come talk with us!
#DiffusionModels #GazePrediction #ICCV2025
23.10.2025 01:38 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Wrapping up an inspiring HiCV 2025 Workshop edition ๐บ
Thanks to all speakers, authors & participants who made it happen!
See you in the next edition... ๐๐ป
#HiCV2025 #ICCV2025
20.10.2025 23:10 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Final oral session!
โข Co-visibility reasoning on sparse scenes ๐
โข Semantic-aware EEG-based visual decoding ๐ง ๐ผ๏ธ
โข OscNet v1.5 for energy-efficient Hopfield networks โก
#HiCV2025 #ICCV2025
20.10.2025 22:10 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Continuing with Massimiliano Mancini โ Rethinking Multimodal Tasks with Human Eyes.
Inspiring discussion on integrating perceptual cues into multimodal AI ๐๏ธ๐งฉ
#HiCV2025 #ICCV2025
20.10.2025 21:37 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Back from the break with Phillip Isola @phillipisola.bsky.social on
โOn the Perceptual Distance Between Images and Text.โ
A fascinating and interactive look at how models (and humans!) measure similarity ๐๐ป
#HiCV2025 #ICCV2025 #VisionLanguage
20.10.2025 21:09 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Posters + coffee โ โ best combo for deep conversations and new collaborations!
Amazing diversity of topics blending neuroscience, cognition, and computer vision.
#HiCV2025 #ICCV2025
20.10.2025 20:39 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0
Time for Oral Session 1!
Short but packed with human-inspired insights:
โข Biological reservoirs for pattern recognition ๐งฌ
โข Human-inspired scene summarization ๐ฅ
โข Vision-constrained super-resolution ๐๏ธ
#HiCV2025 #ICCV2025
20.10.2025 19:52 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Next up: Yen-Ling Kuo โ Human-Inspired Learning for Interactive Robotics.
Robots that learn with and from people ๐ค๐ก
#HiCV2025 #Robotics #ICCV2025
20.10.2025 19:18 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
Kicking off Keynote 1: Vittorio Murino on
โSupervised and Unsupervised Bias Mitigation in Modern ML Modelsโ
Thought-provoking talk on fairness and interpretability!
#HiCV2025 #ICCV2025 #BiasMitigation
20.10.2025 18:49 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
๐บ Good morning from Honolulu!
The 2nd HiCV Workshop 2025 @ ICCV officially started!โ exploring Human-inspired Computer Vision ๐ง ๐๏ธ
[Room 309] โ full day ahead with great keynotes, orals & posters!
#ICCV2025 #HiCV2025 #ComputerVision
20.10.2025 18:38 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0
At the Human-inspired Computer Vision #HiCV2025 workshop, I will present a poster with recent results on comparing video-based ANNs and the primate visual system. Ongoing project at the ViTA lab @yorkuniversity.bsky.social led by @kohitij.bsky.social
๐ Oct 20th, 8:30 - 12:30
๐Room 309
2/3
18.10.2025 15:59 โ ๐ 2 ๐ 1 ๐ฌ 1 ๐ 0
The 2nd Human-inspired Computer Vision (HiCV) Workshop will take place on Oct 20, 2025, in conjunction with @iccv.bsky.social!
โจ 25 contributions (oral & poster)
๐ค Keynotes: @vmurino.bsky.social, @phillipisola.bsky.social, Massimiliano Mancini, Yen-Ling Kuo
๐ Special Issue on IJCV (Springer)
15.10.2025 08:55 โ ๐ 7 ๐ 5 ๐ฌ 1 ๐ 0
๐ข New dataset!
Sanctuaria-Gaze [now in ACM JOCCH] captures how people see & move within sacred spaces using Meta Project Aria glasses.
๐ง Framework: github.com/aimagelab/Sa...
๐ฆ Dataset: huggingface.co/datasets/aim...
๐ Paper: dl.acm.org/doi/10.1145/...
#EgocentricVision #Gaze #AI #CulturalHeritage
15.10.2025 07:30 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
๐จ Call for Extended Abstracts!
Extended Abstracts are still welcome for the 2nd Workshop on Human-inspired Computer Vision @ #ICCV2025 @iccv.bsky.social - dual submissions allowed.
๐ง ๐๏ธ Deadline: Aug 18, 2025
๐ sites.google.com/view/hcvwork...
#ICCV #NeuroAI #CognitiveVision #ComputerVision
17.07.2025 08:30 โ ๐ 5 ๐ 1 ๐ฌ 0 ๐ 0
๐ช๐บ ELLIOT is a Horizon Europe project developing the next generation of open and trustworthy Multimodal Generalist Foundation Models โ advancing open, general-purpose AI rooted in European values. ๐ค๐
Associate Professor at Unimore.
Interested in Computer Vision, Language, and Multimedia.
Computer Vision/Agritech researcher designing a vineyard/orchard many-camera scanner (Gaussian Splatting-based).
Radiance fields, 3D recognition, FP fan (Haskell).
Running, rock climbing, dog friends.
ucvision.org - University of Canterbury, New Zealand
From Physics to Vision Neuroscience & AI | PhD Candidate @InstVisionParis & @ENS_ULM | Enjoyed my time @FlatironCCN, @CERN | co-organizer @neurreps
Internet Scientist. ๐ฌ๐จโ๐ป President, ED & CTO @ooni.org Foundation - Vice-President @hermescenter.org - volunteer @torproject.org
twitter/X: @hellais
Physicist by training, PhD in ML, engineer, enthusiast and optimist.
I like all things black ๐ด ๐ค โซ โฌ โ ๏ธ โฃ๏ธ
#Science #MachineLearning #Physics #Math #Bayesian #Jazz #Metal #Loud #Gaming #Cycling #Munich #Europe #Bread #Kebap #Theorist #Optimist
Father. AI Freelancer @ ๐ฎ๐น. Ph.D. @KAUST_AEx. @AdobeResearch @Qualcomm_EU @samsungresearch Wandering Caribbean ๐จ๐ด, โฎ๏ธโค๏ธโโ๏ธ
Research Director @ Inria, Grenoble
Strengthening Europe's Leadership in AI through Research Excellence | ellis.eu
NeuroAI Prof @EPFL ๐จ๐ญ. ML + Neuro ๐ค๐ง . Brain-Score, CORnet, Vision, Language. Previously: PhD @MIT, ML @Salesforce, Neuro @HarvardMed, & co-founder @Integreat. go.epfl.ch/NeuroAI
Student Researcher @ RAI Institute, MSc CS Student @ ETH Zurich
visual computing, 3D vision, spatial AI, machine learning, robot perception.
๐Zurich, Switzerland
Principal Scientist at Naver Labs Europe, Lead of Spatial AI team. AI for Robotics, Computer Vision, Machine Learning. Austrian in France. https://chriswolfvision.github.io/www/
Researching computer vision stuff at Stack AV in Pittsburgh. Also on Twitter @i_ikhatri
Professor in computer vision and robotics at the Universitรฉ Bourgogne Europe
Professor of Computer Vision/Machine Learning at Imagine/LIGM, รcole nationale des Ponts et Chaussรฉes @ecoledesponts.bsky.social Music & overall happiness ๐ณ๐ชป Born well below 350ppm ๐ฌ mostly silly personal views
๐Paris ๐ https://davidpicard.github.io/
Docent, associate professor. Machine learning & computer vision. Umeรฅ University, Sweden.
Professor for Art History and Digital Humanities; working on computer vision and cultural heritage; social art history; Renaissance
Professor at GWU, Developer of @traffickcam and @projectRephoto. Computer vision/AI researcher with mercenary interest in glitter and contemporary art.
http://www2.seas.gwu.edu/~pless
History and Epistemology of Science | Technology
#histsci #histech #histstm #SciCom
Practices of observation in Science | History of Computing, AI and Computer Vision | HistTech and Comics
https://dinahpfau.medientheater.org/
Mostly she/her
I'm the Director of AI and Computer Vision at Simbe Robotics. I also professionally neglect my YouTube channel (Jack of Some) and make far too many plugins for the Steam Deck.