A discriminative CNN video representation for event detection

@article{Xu2014ADC,
  title={A discriminative CNN video representation for event detection},
  author={Zhongwen Xu and Yi Yang and Alexander G. Hauptmann},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2014},
  pages={1798-1807}
}
In this paper, we propose a discriminative video representation for event detection over a large scale video dataset when only limited hardware resources are available. The focus of this paper is to effectively leverage deep Convolutional Neural Networks (CNNs) to advance event detection, where only frame level static descriptors can be extracted by the existing CNN toolkits. This paper makes two contributions to the inference of CNN video representation. First, while average pooling and max… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 282 CITATIONS, ESTIMATED 99% COVERAGE

A Fine Granularity Object-Level Representation for Event Detection and Recounting

VIEW 25 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Scalable Video Classification using Bag of Visual Words on Spark

VIEW 17 EXCERPTS
CITES RESULTS & METHODS
HIGHLY INFLUENCED

Discovering Latent Discriminative Patterns for Multi-Mode Event Representation

VIEW 10 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Exploring Temporal Information for Improved Video Understanding

VIEW 6 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

Hierarchical Concept Score Postprocessing and Concept-Wise Normalization in CNN-Based Video Event Recognition

VIEW 15 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Large-scale video analysis and understanding

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND

The Many Shades of Negativity

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS

Beyond caption to narrative: Video captioning with multiple sentences

VIEW 8 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Bidirectional Multirate Reconstruction for Temporal Modeling in Videos

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND

FILTER CITATIONS BY YEAR

2015
2020

CITATION STATISTICS

  • 41 Highly Influenced Citations

  • Averaged 53 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 45 REFERENCES

Action Recognition with Improved Trajectories

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

The AXES submissions at TrecVid 2013

VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

Product Quantization for Nearest Neighbor Search

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Evaluating Color Descriptors for Object and Scene Recognition

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

On Space-Time Interest Points

  • Ivan Laptev
  • Computer Science
  • International Journal of Computer Vision
  • 2005
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

CMU-Informedia at TRECVID 2013 Multimedia Event Detection

  • Z.-Z. Lan, L. Jiang, S.-I. Yu
  • In TRECVID 2013 Workshop,
  • 2013
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL