Large-scale Video Classification with Convolutional Neural Networks, CVPR 2014

Andrej Karpathy · Intermediate ·📐 ML Fundamentals ·12y ago

To Appear at CVPR 2014. More information on http://cs.stanford.edu/people/karpathy/deepvideo Note that the temporal smoothing is applied in a 200-Frame (~6 second) gaussian window centered on the frame that is shown. In other words, the network is making its decision at time t based on frames [t-100...t+100].

Watch on YouTube ↗ (saves to browser)

Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from Andrej Karpathy · Andrej Karpathy · 1 of 19

← Previous Next →

Large-scale Video Classification with Convolutional Neural Networks, CVPR 2014

Large-scale Video Classification with Convolutional Neural Networks, CVPR 2014

Andrej Karpathy

ConvNet forward pass demo

ConvNet forward pass demo

Andrej Karpathy

CS231n Winter 2016: Lecture1: Introduction and Historical Context

CS231n Winter 2016: Lecture1: Introduction and Historical Context

Andrej Karpathy

CS231n Winter 2016: Lecture 2: Data-driven approach, kNN, Linear Classification 1

CS231n Winter 2016: Lecture 2: Data-driven approach, kNN, Linear Classification 1

Andrej Karpathy

CS231n Winter 2016: Lecture 3: Linear Classification 2, Optimization

CS231n Winter 2016: Lecture 3: Linear Classification 2, Optimization

Andrej Karpathy

CS231n Winter 2016: Lecture 4: Backpropagation, Neural Networks 1

CS231n Winter 2016: Lecture 4: Backpropagation, Neural Networks 1

Andrej Karpathy

CS231n Winter 2016: Lecture 5: Neural Networks Part 2

CS231n Winter 2016: Lecture 5: Neural Networks Part 2

Andrej Karpathy

CS231n Winter 2016: Lecture 6: Neural Networks Part 3 / Intro to ConvNets

CS231n Winter 2016: Lecture 6: Neural Networks Part 3 / Intro to ConvNets

Andrej Karpathy

CS231n Winter 2016: Lecture 7: Convolutional Neural Networks

CS231n Winter 2016: Lecture 7: Convolutional Neural Networks

Andrej Karpathy

CS231n Winter 2016: Lecture 8: Localization and Detection

CS231n Winter 2016: Lecture 8: Localization and Detection

Andrej Karpathy

CS231n Winter 2016: Lecture 9: Visualization, Deep Dream, Neural Style, Adversarial Examples

CS231n Winter 2016: Lecture 9: Visualization, Deep Dream, Neural Style, Adversarial Examples

Andrej Karpathy

CS231n Winter 2016: Lecture 10: Recurrent Neural Networks, Image Captioning, LSTM

CS231n Winter 2016: Lecture 10: Recurrent Neural Networks, Image Captioning, LSTM

Andrej Karpathy

CS231n Winter 2016: Lecture 11: ConvNets in practice

CS231n Winter 2016: Lecture 11: ConvNets in practice

Andrej Karpathy

CS231n Winter 2016: Lecture 12: Deep Learning libraries

CS231n Winter 2016: Lecture 12: Deep Learning libraries

Andrej Karpathy

CS231n Winter 2016: Lecture 13: Segmentation, soft attention, spatial transformers

CS231n Winter 2016: Lecture 13: Segmentation, soft attention, spatial transformers

Andrej Karpathy

CS231n Winter 2016: Lecture 14: Videos and Unsupervised Learning

CS231n Winter 2016: Lecture 14: Videos and Unsupervised Learning

Andrej Karpathy

CS231n Winter 2016: Lecture 15: Invited Talk by Jeff Dean

CS231n Winter 2016: Lecture 15: Invited Talk by Jeff Dean

Andrej Karpathy

Introducing arxiv-sanity

Introducing arxiv-sanity

Andrej Karpathy

Pong AI with Policy Gradients

Pong AI with Policy Gradients

Andrej Karpathy

Related AI Lessons

My First Python Program and What I Learned

Learn from a beginner's first Python program and their key takeaways from the experience

Medium · Programming

We had the tools to see the war coming! We just weren’t looking.

Apply game theory and historical analysis to predict conflicts, making them less unpredictable

Hierarchical Clustering — A Dendrogram Instead of a Number

Learn hierarchical clustering using dendrograms for unsupervised learning in Python

Hierarchical Clustering — A Dendrogram Instead of a Number

Learn hierarchical clustering using Python to group similar data points without specifying the number of clusters, and understand how dendrograms visualize the clustering process

Medium · Python

Advanced Data Structures and Problem-Solving Techniques