Exploring the influence of feature representation for dictionary selection based video summarization

Mingyang Ma, Shaohui Mei, Jingyu Ji, Shuai Wan, Zhiyong Wang, Dagan FengICIP 2017 · OpenReview

Abstract

Dictionary selection based video summarization (VS) algorithms, in which keyframes are considered as a dictionary to reconstruct all the video frames, have been demonstrated to be effective and efficient for video summarization. It has been noticed that the feature representation of video plays a great impact of the performance of VS. In this paper, the influence of feature representation of video frames on the performance of dictionary selection-based VS is for the first time investigated. In addition to the traditional hand-crafted features used in VS, such as color histogram, the deep features learned through deep neural networks are firstly used to represent video frames for dictionary selection-based VS. The impact of dimensionality reduction to the high-dimensional deep learning features on VS is further discussed. Experimental results on a benchmark video dataset demonstrate that deep learning features are able to achieve better performance than traditional hand-crafted features for dictionary selection-based VS. Moreover, the dimensionality of deep learning features can be reduced to decrease the computational cost without the degradation of VS performance.
BibTeX
@inproceedings{ma2017exploring,
  author = {Mingyang Ma and Shaohui Mei and Jingyu Ji and Shuai Wan and Zhiyong Wang and Dagan Feng},
  title = {{Exploring the influence of feature representation for dictionary selection based video summarization}},
  booktitle = {ICIP},
  year = {2017},
  url = {https://openreview.net/forum?id=nO57rij_LV},
}

Loading related content...

Figure