• Publications
  • Influence
Learning Spatiotemporal Features with 3D Convolutional Networks
TLDR
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. Expand
  • 3,611
  • 824
  • PDF
A Closer Look at Spatiotemporal Convolutions for Action Recognition
TLDR
In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Expand
  • 579
  • 103
  • PDF
Nonrigid Structure-from-Motion: Estimating Shape and Motion with Hierarchical Priors
TLDR
This paper describes methods for recovering time-varying shape and motion of nonrigid 3D objects from uncalibrated 2D point tracks using a Probabilistic Principal Components Analysis (PPCA) shape model. Expand
  • 440
  • 78
  • PDF
Efficient Object Category Recognition Using Classemes
TLDR
We introduce a new descriptor for images which allows the construction of efficient and compact classifiers with good accuracy on object category recognition. Expand
  • 437
  • 55
  • PDF
C3D: Generic Features for Video Analysis
TLDR
We propose Convolution 3D feature, a generic spatio-temporal feature obtained by training a deep 3-dimensional convolutional network on a large annotated video dataset comprising objects, scenes, actions, and other frequently occurring concepts. Expand
  • 287
  • 54
  • PDF
Tracking and modeling non-rigid objects with rank constraints
TLDR
This paper presents a novel solution for flow-based tracking and 3D reconstruction of deforming objects in monocular image sequences. Expand
  • 310
  • 29
  • PDF
Feature Correspondence Via Graph Matching: Models and Global Optimization
TLDR
In this paper we present a novel graph matching optimization technique, which we refer to as dual decomposition (DD), and demonstrate on a variety of examples that this method outperforms existing graph matching algorithms. Expand
  • 394
  • 29
  • PDF
Exploiting weakly-labeled Web images to improve object classification: a domain adaptation approach
TLDR
We investigate and compare methods that learn image classifiers by combining very few manually annotated examples (e.g., 1-10 images per class) and a large number of weakly-labeled Web photos retrieved using keyword-based image search. Expand
  • 228
  • 26
  • PDF
Large Margin Component Analysis
TLDR
We propose a method that solves for the low-dimensional projection of the inputs, which minimizes a metric objective aimed at separating points in different classes by a large margin. Expand
  • 229
  • 24
  • PDF
Weakly supervised discriminative localization and classification: a joint learning process
TLDR
We propose a novel method for learning a discriminative subwindow classifier from examples annotated with binary labels indicating the presence of an object or action of interest, but not its location. Expand
  • 186
  • 21
  • PDF