• Corpus ID: 239615962

Fast Graph Sampling for Short Video Summarization using Gershgorin Disc Alignment

@article{Sahami2021FastGS,
  title={Fast Graph Sampling for Short Video Summarization using Gershgorin Disc Alignment},
  author={Sadid Sahami and Gene Cheung and Chia-Wen Lin},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.11420}
}
We study the problem of efficiently summarizing a short video into several keyframes, leveraging recent progress in fast graph sampling. Specifically, we first construct a similarity path graph (SPG) G, represented by graph Laplacian matrix L, where the similarities between adjacent frames are encoded as positive edge weights. We show that maximizing the smallest eigenvalue λmin(B) of a coefficient matrix B = diag(a) + μL, where a is the binary keyframe selection vector, is equivalent to… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 26 REFERENCES
Fast Graph Sampling Set Selection Using Gershgorin Disc Alignment
TLDR
The dual problem is reinterpreted as an intuitive disc coverage problem bearing strong resemblance to the famous NP-hard set cover (SC) problem and a fast approximation scheme is derived from a known SC error-bounded approximation algorithm.
Video summarization via minimum sparse reconstruction
TLDR
This paper formulate the video summarization task with a novel minimum sparse reconstruction (MSR) problem, where the original video sequence can be best reconstructed with as few selected keyframes as possible.
L2,0 constrained sparse dictionary selection for video summarization
TLDR
A simultaneous orthogonal matching pursuit (SOMP) based method is proposed to obtain an approximate solution for the proposed model without smoothing the penalty function, and thus selects keyframes in a global point of view.
Diversity promoting online sampling for streaming video summarization
TLDR
This paper proposes a memory efficient and computationally fast, online algorithm that uses competitive learning for diverse sampling for streaming video summarization and is a generalization of online K-means such that the cost function reduces clustering error, while also ensuring a diverse set of samples.
Keyframe-based video summarization using Delaunay clustering
TLDR
A novel video summarization technique by using Delaunay clusters that generates good quality summaries with fewer frames and less redundancy when compared to other schemes is proposed.
Video summarization using singular value decomposition
  • Yihong Gong, Xin Liu
  • Computer Science
    Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)
  • 2000
TLDR
From this SVD, the authors are able, to not only derive the refined feature space to better cluster visually similar frames, but also define a metric to measure the amount of visual content contained in each frame cluster using its degree of visual changes.
Diversity-Aware Multi-Video Summarization
TLDR
This work develops a novel diversity-aware sparse optimization method for multi-video summarization by exploring the complementarity within the videos, and shows that the proposed approach clearly outperforms the state-of-the-art methods on the two problems—topic-oriented video summarization and multi-view video summarizations in a camera network.
Patch Based Video Summarization With Block Sparse Representation
TLDR
This paper designs a simultaneous version of block-based OMP (Orthogonal Matching Pursuit) algorithm, namely SBOMP, to solve the VS problem with such video frame representation as block sparse representation by considering each video frame as a block containing a number of patches.
Adaptive Greedy Dictionary Selection for Web Media Summarization
TLDR
This paper designs a new dictionary selection model via l2,0 norm and proposes two methods: the standard forward-backward greedy algorithm, which is not suitable for large-scale problems; the other is based on the gradient cues at each forward iteration and speeds up the process dramatically.
Random Walk Graph Laplacian-Based Smoothness Prior for Soft Decoding of JPEG Images
TLDR
This paper combines three image priors-Laplacian prior for DCT coefficients, sparsity prior, and graph-signal smoothness prior for image patches-to construct an efficient JPEG soft decoding algorithm that outperforms the state-of-the-art soft decoding algorithms in both objective and subjective evaluations noticeably.
...
1
2
3
...