Multi-stream dynamic video Summarization

@article{Elfeki2022MultistreamDV,
  title={Multi-stream dynamic video Summarization},
  author={Mohamed Elfeki and Liqiang Wang and Ali Borji},
  journal={2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
  year={2022},
  pages={185-195}
}
With vast amounts of video content being uploaded to the Internet every minute, video summarization becomes critical for efficient browsing, searching, and indexing of visual content. Nonetheless, the spread of social and egocentric cameras creates an abundance of sparse scenarios captured by several devices, and ultimately required to be jointly summarized. In this paper, we discuss the problem of summarizing videos recorded independently by several dynamic cameras that intermittently share… 

Figures and Tables from this paper

Distributed Multi-agent Video Fast-forwarding
TLDR
This paper presents a consensus-based distributed multi-agent video fast-forwarding framework, named DMVF, that fast-forwards multi-view video streams collaboratively and adaptively and significantly improves the coverage of important frames and also reduces the number of frames processed in the system.
A General Approach for Meeting Summarization: From Speech to Extractive Summarization
TLDR
The motivation of the study is to catch the important points that may escape the attention of the individuals at the meeting and to summarize the main agenda items for the personnel who could not attend the meeting.

References

SHOWING 1-10 OF 59 REFERENCES
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.
Multi-View Surveillance Video Summarization via Joint Embedding and Sparse Optimization
TLDR
A novel unsupervised framework via joint embedding and sparse representative selection that can summarize multi-view videos without assuming any prior correspondences/alignment between them, e.g., uncalibrated camera networks.
Multi-View Video Summarization
TLDR
A spatio-temporal shot graph is constructed and the summarization problem is formulated as a graph labeling task, which encodes the correlations with different attributes among multi-view video shots in hyperedges and generates a result based on shot importance evaluated using a Gaussian entropy fusion scheme.
Video summarization in a multi-view camera network
TLDR
This work proposes a novel framework for summarizing multi-view videos by exploiting both intra- and inter-view content correlations in a joint embedding space that clearly out-performs the state-of-the-art.
Hypergraph dominant set based multi-video summarization
Video Summarization Via Multiview Representative Selection
TLDR
This paper presents the multiview sparse dictionary selection with centroid co-regularization method, which optimizes the representative selection in each view, and enforces that the view-specific selections to be similar by regularizing them towards a consensus selection.
Improving Sequential Determinantal Point Processes for Supervised Video Summarization
TLDR
A new probabilistic distribution is designed such that, when it is integrated into SeqDPP, the resulting model accepts user input about the expected length of the summary, and significantly extend a popular video summarization dataset.
Predicting Important Objects for Egocentric Video Summarization
TLDR
The proposed video summarization approach is neither camera-wearer-specific nor object-specific; that means the learned importance metric need not be trained for a given user or context, and it can predict the importance of objects and people that have never been seen previously.
Multi-View Video Summarization Using Bipartite Matching Constrained Optimum-Path Forest Clustering
TLDR
A graph-theoretic solution to the task of multi-view video summarization to efficiently represent the most significant information from a set of videos captured for a certain period of time by multiple cameras is proposed.
...
...