From Images to Text: New Forms of Human-AI Interaction
Explore cutting-edge techniques connecting computer vision and natural language processing, focusing on image-to-text generation, AI controllability, and embodied AI applications.
Generative Models: Controllable Generation and Learning
Dive into advanced generative AI models with Prof. Patras, exploring controllable generation techniques and learning mechanisms for creating more precise and manageable AI-generated content.
3D Computer Vision for Animals - Lecture 28
Explore cutting-edge techniques in 3D computer vision applied to animal modeling and analysis through an expert lecture on advanced AI applications for understanding animal forms and movement.
From Handcrafted to End-to-End Learning and Back: A Journey Through Multi-Object Tracking Paradigms
Explore the evolution of multi-object tracking paradigms, from tracking-by-detection to end-to-end learning approaches, examining their effectiveness and current state-of-the-art status.
The Unreasonable Effectiveness of Large Language-Vision Models for Video Domain Adaptation - Lecture 31
Explore the groundbreaking potential of large language-vision models in video domain adaptation through Prof. Ricci's expert analysis of their effectiveness and applications.
Using AI Computer Vision in OSINT Data Analysis
Discover how to leverage AI computer vision tools in Azure and AWS to accelerate OSINT data analysis, perform object detection, facial recognition, and chronolocation analysis for forensic investigations.
AI and Vision Technology in Webb Telescope Planet Discovery
Explore how AI analyzes vast astronomical data from Webb, Hubble, and other telescopes to uncover the mysteries of planetary formation around young stars.
Transfer Learning and Transformers - Full Stack Deep Learning - Spring 2021
Explore transfer learning's evolution from computer vision to NLP, diving into embeddings, language models, and the revolutionary Transformer architecture. Gain insights into various models and their applications.
Computer Vision Applications - Full Stack Deep Learning - Spring 2021
Comprehensive overview of deep learning applications in computer vision, covering ConvNet architectures, detection methods, and advanced tasks like 3D shape inference and style transfer.
Introduction to the Text Recognizer Project - Full Stack Deep Learning - March 2019
Hands-on labs introducing text recognition project, covering setup, data handling, model creation, training, and deployment in a full-stack deep learning context.
Setting Up Machine Learning Projects - Full Stack Deep Learning - March 2019
Learn best practices for planning and setting up machine learning projects, including prioritizing projects, choosing metrics, and creating baselines. Gain insights into the lifecycle of ML projects and practical examples.
Computer Vision Dog Breed Classification with Convolutional Neural Networks, TensorFlow and Kubeflow
Develop a dog breed classification system using TensorFlow, Kubeflow, and convolutional neural networks. Compare AI predictions with DNA results for accuracy.
Res-UNet for Melanoma Segmentation - TensorFlow Tutorial
Step-by-step guide to implement and train a Res-UNet model for Melanoma detection using TensorFlow and Keras. Learn to build, train, test, and visualize results for accurate skin lesion segmentation.
Interactive Map Using Computer Vision
Learn to create an interactive map using computer vision techniques. Develop projects like country identification, flight time calculation, and a Q&A game while mastering polygon creation and corner point detection.
Improving Stable Diffusion Images with FreeU - Optimizing SDXL, LCM, and Turbo Models
Optimize Stable Diffusion images using FreeU hyperparameters. Learn to leverage ComfyUI API for grid searching ideal parameters in SDXL, LCM, and Turbo models. Practical demonstrations and comparisons included.
Feature Detection for Games - Automating System Requirements
Explore how feature detection can automate game compatibility checks, improve user experience, and make Linux gaming more accessible through community-driven system requirement data.
Google Gemini - Technical Report on Model Architecture, Dataset, and Training
Explore Google's Gemini AI model family: architecture, datasets, and performance across text, image, video, and speech benchmarks. Learn how it advances multimodal AI and sets new records.
Convergence of Vision and Language in AI - Recent Developments and Projects
Explore the convergence of vision and language in AI with Lucas Beyer from Google DeepMind, covering topics like ViT, PaLI, and the future of multimodal AI architectures.
MagicAnimate: Temporally Consistent Human Image Animation Using Diffusion Model - Full Tutorial
Learn to create temporally consistent human image animations using Magic Animate, DensePose, and CodeFormer. Master installation, video processing, and face restoration techniques for high-quality AI-driven animations.
SDXL Turbo - Instant High-Quality Text-to-Image Generation with One-Step AI Model
Explore SDXL Turbo, a fast text-to-image AI model. Learn setup, key parameters, and generate high-quality images across various themes. Discover its versatility and speed in creating stunning visuals.
Google Gemini AI: Comprehensive Overview and Capabilities
Explore Google's Gemini AI: a multimodal model excelling in programming, scientific analysis, math reasoning, and creative tasks. Witness its capabilities in understanding diverse data types and generating innovative solutions.