Hands-on Data Centric Visual AI Course on Coursera

• 🔍 Discover different labeling approaches, from manual to fully automated
• 🛠️ Master annotation quality for object detection tasks and fix common issues
• 📊 Analyze how bounding box quality impacts model performance and boosts label consistency
• ⚙️ Use advanced tools like FiftyOne and CVAT to explore datasets and refine annotations
• 💡 Tackle complex computer vision challenges like occlusions and small object detection
• 🧠 Implement data augmentation techniques to improve model robustness

🔎 ECCV 2024 Redux

• Fast and Photo-realistic Novel View Synthesis from Sparse Images - Avinash Paliwal at Texas A&M University
• Robust Calibration of Large Vision-Language Adapters - Balamurali Murugesan at École de technologie supérieure
• Tree-of-Life Meets AI - Mridul Khurana at Virginia Tech & NSF

• Closing the Gap Between Satellite and Street-View Imagery Using Generative Models - Ningli Xu at The Ohio State University
• High-Efficiency 3D Scene Compression Using Self-Organizing Gaussians - Wieland Morgenstern at Fraunhofer Heinrich Hertz Institute HHI
• Skeleton Recall Loss for Connectivity Conserving and Resource Efficient Segmentation of Thin Tubular Structures - Maximilian R. and Yannick Kirchhoff at Medical Image Computing (MIC) @DKFZ German Cancer Research Center and Heidelberg University

• Zero-shot Video Anomaly Detection: Leveraging Large Language Models for Rule-Based Reasoning - Yuchen Yang at John Hopkins University
• Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models- Xiaoyu Zhu at Carnegie Mellon

🎙️ Good Listens

🗓️. Upcoming In-Person Events

🗓️. Upcoming Virtual Events