World of Bits: An Open-Domain Platform for Web-Based Agents

no code implementations • ICML 2017 • Tianlin Shi, Andrej Karpathy, Linxi Fan, Jonathan Hernandez, Percy Liang

While simulated game environments have greatly accelerated research in reinforcement learning, existing environments lack the open-domain realism of tasks in computer vision or natural language processing, which operate on artifacts created by humans in natural, organic settings.

reinforcement-learning Reinforcement Learning (RL)

PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications

7 code implementations • 19 Jan 2017 • Tim Salimans, Andrej Karpathy, Xi Chen, Diederik P. Kingma

1) We use a discretized logistic mixture likelihood on the pixels, rather than a 256-way softmax, which we find to speed up training.

Density Estimation Image Generation

DenseCap: Fully Convolutional Localization Networks for Dense Captioning

1 code implementation • CVPR 2016 • Justin Johnson, Andrej Karpathy, Li Fei-Fei

We introduce the dense captioning task, which requires a computer vision system to both localize and describe salient regions in images in natural language.

Dense Captioning Image Captioning +4

Visualizing and Understanding Recurrent Networks

3 code implementations • 5 Jun 2015 • Andrej Karpathy, Justin Johnson, Li Fei-Fei

Recurrent Neural Networks (RNNs), and specifically a variant with Long Short-Term Memory (LSTM), are enjoying renewed interest as a result of successful applications in a wide range of machine learning problems that involve sequential data.

Deep Visual-Semantic Alignments for Generating Image Descriptions

3 code implementations • CVPR 2015 • Andrej Karpathy, Li Fei-Fei

Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and visual data.

Cross-Modal Retrieval Image Captioning +3

ImageNet Large Scale Visual Recognition Challenge

12 code implementations • 1 Sep 2014 • Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, Li Fei-Fei

The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images.

General Classification Image Classification +4

Large-Scale Video Classification with Convolutional Neural Networks

1 code implementation • 2014 IEEE Conference on Computer Vision and Pattern Recognition 2014 • Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas Leung, Rahul Sukthankar, Li Fei-Fei

We further study the generalization performance of our best model by retraining the top layers on the UCF-101 Action Recognition dataset and observe significant performance improvements compared to the UCF-101 baseline model (63. 3% up from 43. 9%).

Action Recognition Classification +3

Deep Fragment Embeddings for Bidirectional Image Sentence Mapping

no code implementations • NeurIPS 2014 • Andrej Karpathy, Armand Joulin, Li Fei-Fei

We introduce a model for bidirectional retrieval of images and sentences through a multi-modal embedding of visual and natural language data.

Referring Expression Comprehension Retrieval +1

Grounded Compositional Semantics for Finding and Describing Images with Sentences

no code implementations • TACL 2014 • Richard Socher, Andrej Karpathy, Quoc V. Le, Christopher D. Manning, Andrew Y. Ng

Previous work on Recursive Neural Networks (RNNs) shows that these models can produce compositional feature vectors for accurately representing and classifying sentences or images.

Sentence

Emergence of Object-Selective Features in Unsupervised Feature Learning

no code implementations • NeurIPS 2012 • Adam Coates, Andrej Karpathy, Andrew Y. Ng

Recent work in unsupervised feature learning has focused on the goal of discovering high-level features from unlabeled images.

Clustering