Exploring Relationships Between Ground and Aerial Views by Synthesis and Matching
Explore relationships between ground and aerial views through synthesis and matching techniques, focusing on architecture, evaluation methods, and practical applications in image retrieval and GPS data.
Object Detection in Computer Vision - Lecture 21
Explore advanced object detection techniques, including precision-recall metrics, mean average precision, and multitask networks for computer vision applications.
Training Neural Networks - Part II - Lecture 11
Explore advanced neural network training techniques, including loss functions, learning rates, momentum, and strategies to prevent overfitting for improved computer vision model performance.
Training Neural Networks for Computer Vision - Part I - Lecture 10
Explore neural network training techniques, including gradient descent, loss functions, and backpropagation, for effective computer vision model optimization and performance improvement.
Introduction to Convolutional Neural Networks - Part I - Lecture 8
Introduction to convolutional neural networks, covering architecture, applications in computer vision and natural language processing, with examples like AlexNet and super-resolution techniques.
Introduction to Neural Networks - Part II - Lecture 8
Explore neural network fundamentals, including activation functions, multi-class classification, and multi-layer perceptrons. Learn about their implementation and performance on image datasets like MNIST.
Edge Detection in Computer Vision - Part II - Lecture 7
Explore advanced edge detection techniques, including Canny algorithm and deep learning approaches, for improved computer vision applications in image processing and analysis.
Keras Tutorial - Neural Network Architectures and Advanced Concepts - Part 2
Learn advanced deep learning concepts including neural networks, VGG, residual connections, autoencoders, and GANs. Explore batch processing, reproducibility, and practical implementation in Keras.
Computer Vision - Administrative and Course Overview - Lecture 1
Introduction to graduate-level computer vision, covering mathematical foundations, deep learning applications, and advanced topics like object detection and image segmentation.
CAP6412 - Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
Explore skip connections in ResNets, their impact on adversarial examples, and implications for model robustness and transferability in deep learning.
Towards Deep Learning Models Resistant to Adversarial Attacks - CAP6412 Spring 2021
Explore strategies for developing robust deep learning models that can withstand adversarial attacks, focusing on minmax functions, saddle points, and experimental results.
Imagen: Text-to-Image Generation Using Diffusion Models - Lecture 9
Explore Imagen, a text-to-image diffusion model, covering its architecture, efficiency improvements, and key techniques like thresholding and upsampling.
Spatio-Temporal Learning from Limited Labels for Video Action Detection
Explore spatio-temporal learning techniques for video action detection with limited labels, focusing on semi-supervised methods and temporal coherence for improved performance.
Geo-localization Framework for Real-world Scenarios - Defense Presentation
Explore advanced geo-localization techniques using vision transformers and novel loss functions for improved accuracy in real-world scenarios, with a focus on bridging domain gaps.
Visual Question Answering: Grounded Systems and Transformer Capsules
Learn about Grounded Visual Question Answering systems, their limitations, and innovative approaches using Transformers with Capsules for improved performance in image-text understanding tasks.
Video Action Understanding - Action Classification, Temporal Localization and Detection
Explore video action understanding techniques, including classification, temporal localization, and detection methods for analyzing and interpreting human actions in video content.
Applications of Deep Neural Networks for TensorFlow and Keras
Comprehensive exploration of deep neural networks using TensorFlow and Keras, covering image processing, GANs, transfer learning, NLP, reinforcement learning, and practical applications.
Digital Signal Processing Lectures, Fall 2014
Comprehensive lectures on digital signal processing, covering signals, systems, transforms, filtering, and advanced topics. Ideal for engineering students seeking in-depth understanding of DSP concepts and applications.
GPU Accelerated Data Curation for Large Language Models
Explore GPU-accelerated data curation techniques for large language models in this 30-minute talk by Ryan Wolf, a Deep Learning Algorithm Engineer at NVIDIA. Learn about the importance of well-curated datasets in scaling LLMs and discover how to create h…
Automatic Image Captioning with Vision Transformer and GPT-2
Learn how to generate descriptive captions for images using Python and PyTorch in this 16-minute tutorial. Explore the process of automatic image captioning with the pre-trained 'nlpconnect/vit-gpt2-image-captioning' model from Hugging Face. Set up the V…
EfficientML.ai Lecture - Introduction to Efficient Machine Learning
Dive into the world of efficient machine learning with this comprehensive lecture from MIT HAN Lab. Explore cutting-edge techniques and strategies for optimizing ML models, reducing computational costs, and improving overall performance. Learn from exper…