• Publications
  • Influence
Learning Spatiotemporal Features with 3D Convolutional Networks
We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. OurExpand
  • 3,443
  • 798
  • PDF
Intriguing properties of neural networks
Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason theyExpand
  • 5,195
  • 702
  • PDF
Visualizing and Understanding Convolutional Networks
Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark Krizhevsky et al. [18]. However there is no clear understanding of whyExpand
  • 8,313
  • 638
  • PDF
Indoor Segmentation and Support Inference from RGBD Images
We present an approach to interpret the major surfaces, objects, and support relations of an indoor scene from an RGBD image. Most existing work ignores physical interactions or is applied only toExpand
  • 2,477
  • 526
  • PDF
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
Predicting depth is an essential component in understanding the 3D geometry of a scene. While for stereo images local correspondence suffices for estimation, finding depth relations from a singleExpand
  • 1,577
  • 345
  • PDF
Spectral Hashing
Semantic hashing[1] seeks compact binary codes of data-points so that the Hamming distance between codewords correlates with semantic similarity. In this paper, we show that the problem of finding aExpand
  • 2,170
  • 333
  • PDF
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implementedExpand
  • 3,615
  • 295
  • PDF
Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories
Current computational approaches to learning visual object categories require thousands of training images, are slow, cannot learn in an incremental manner and cannot incorporate prior informationExpand
  • 1,946
  • 254
  • PDF
Object class recognition by unsupervised scale-invariant learning
We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. AExpand
  • 2,482
  • 221
  • PDF
Regularization of Neural Networks using DropConnect
We introduce DropConnect, a generalization of Dropout (Hinton et al., 2012), for regularizing large fully-connected layers within neural networks. When training with Dropout, a randomly selectedExpand
  • 1,697
  • 207
  • PDF