@ce-at-sea.bsky.socialLooking for a #PhD? Interested in #marine #ecosystems #plankton #ecology or #computervision? Apply to study with us and investigate The Bigger Picture: aries-dtp.ac.uk/studentships...
@pml.ac.uk @bas.ac.uk @essexuni.bsky.social
@emnullfuenf.bsky.socialThe conference season 2026 is over. My research group published on the topics 3D-Human-Pose-Estimation, CleanAir and Interactive Gaussian Splatting in Cultural Heritage at iWoar2026 and HUMAN2026 at ACM Hypertext Conference.
#gaussian_splatting #computervision #cleanair #culturalheritage #acm
@orcsgirls.bsky.socialExplore computer vision and build projects with the HuskyLens at our free class. Sign up today at www.orcsgirls.org/classes 👀
@aipulse-synestesia.bsky.social🤖 AI Models Can Learn Task-Specific Geometries and Align Latent Spaces
Contrastive learning is often measured by cosine similarity, which supplies a fixed geometry that works well across all tasks, from image retrieval to...
#Reasoning #ComputerVision #InferenceOptimization #AI #AIPulse
@jmcastagnetto.bsky.socialFrom #Nature: "An open vision-language model for diverse #medical applications" www.nature.com/articles/s41...
@aipulse-synestesia.bsky.social🤖 New Motion Capture Dataset Boosts Humanoid Robot Learning
The premise is a clear summary of the field's problem. A policy that succeeds in a training scene often breaks when object shapes, positions, or lighting change,...
@ieeesensorsalert.bsky.socialFinding flaws inside dark tubes used to be slow, but lightweight networks excel!
Read the full article on IEEE Sensors Alert.
ieee-sensorsalert.org/articles/a-l...
#ieeesensorsalert #ieeesensors #steelpipeinspection #defectdetection #industrialinspection #computervision #deeplearning
@futuregearai.bsky.socialNew arXiv work audits motion-deblurring ground truth and finds 19 of 51 "240 fps" smartphone clips actually recorded near 176 fps, a discrepancy hidden in container timing tables. Even/odd window choices and unequal frame durations…
#AI #ComputerVision #Research
https://arxiv.org/abs/2610.05298
@ai-news.at.thenote.appWhy Can't AI Tell What's in a Blurry Photo? The Real Way Computer Vision "Sees"
An AI does not "see" objects at all—it reads a flat numerical grid of pixel brightness values.
@ai-ru.at.thenote.appПочему ИИ не может распознать объекты на размытом фото? Как компьютерное зрение "видит" на самом деле
ИИ вообще не "видит" объекты — он считывает плоскую числовую сетку значений яркости пикселей.
@ananyakapoor06.bsky.socialThe Computer Vision lab at Galgotias University gives students a platform to explore image processing, visual recognition and AI-based applications through practical projects and experimentation. #GalgotiasUniversity #ComputerVision #AI
@robotcurrent.bsky.socialZeST uses VLM outputs as stochastic measurements to predict terrain traversability in unknown environments without real-world data collection. The approach enables zero-shot navigation in both indoor and outdoor…
#Robotics #AutonomousNavigation #ComputerVision #AI
https://arxiv.org/abs/2508.19131
@habiledata.bsky.socialObject Detection Explained: How Models Find and Locate Objects
Boost computer vision AI with expert data annotation, including accurate bounding boxes, object identification, and quality training datasets.
@mlscientist.bsky.socialYork University's Laboratory of Advanced Biotechnologies for Health Assessment is recruiting a PhD student to work on a project that combines AI, computer vision, and mobile software for...
@ai-bloom.warp-studio.com自然言語から自律実験へ：アルゴンヌ国立研究所が切り拓くエージェント型AI顕微鏡の全貌
アルゴンヌ国立研究所がSYNAPS-Iプロジェクトで発表した、自然言語指示とエージェント型AIによる自律型顕微鏡実験プラットフォームの技術解説。
#AgenticAI #LLM #ComputerVision #High-PerformanceComputing #AutonomousScience
@ai-ru.at.thenote.appКомпьютерное зрение: алгоритм SIFT (Scale Invariant Feature Transform)
Элегантное сопоставление объектов с нескольких точек зрения
@ai-news.at.thenote.appComputer Vision: SIFT algorithm (Scale Invariant Feature Transform)
Elegant object matching from several viewpoints
@loicaroyer.bsky.socialWhat won, broadly:
• deep detectors that cope with very sparse labels
• learned linkers, often transformers
• global optimisation (ILP) to assemble lineages (5 of the top 7)
• dedicated division models
• pseudo-labels, synthetic cells or pretraining to stretch those labels
#ComputerVision
@liambroza.bsky.socialQuite. a crazy idea of how we can make new types of apps with #ComputerVision #AI
@wak31415.bsky.social