VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method

By Sandra Eliza Fontes de Avila, Ana Paula Brandão Lopes, Antonio da Luz Jr., Arnaldo de Albuquerque Araújo. Pattern Recognition Letters, 2011

719 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/c18b4d6767d5a5fa69a1c12bf141f85670fee1b6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Creating Summaries from User Videos (2014, methodology): “human comparison has already been used successfully for keyframes [1,15].”
COIN: A Large-Scale Dataset for Comprehensive Instructional Video Analysis (2019, background): “(2) The video summarization datasets [15, 22, 30, 38] contain long videos arranging from different domains.”
Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward (2017, methodology): “In addition to these two datasets, we exploit two other datasets, OVP 1 that has 50 videos and YouTube (De Avila et al. 2011) that has 39 videos excluding cartoon videos, to evaluate our method in the settings where training data is augmented (Zhang et al. 2016b; Mahasseni, Lam, and Todorovic 2017).”
Video Summarization With Attention-Based Encoder–Decoder Networks (2017, methodology): “Thus, the corresponding selection criteria for summaries include content frequency [27] [28], coverage [29] [30], relevance [4] [24] [25], and user’s attention [3] [26], etc.”
Video Summarization with Long Short-Term Memory (2016, methodology): “Researchers have designed heuristic criteria such as relevance [10,13,14,31,36], diversity or coverage [1,12,28,30,34], and representativeness [5,6,9,10,11,33,35].”
A Practical Online Framework for Extracting Running Video Summaries under a Fixed Memory Budget (2021, background): “In the literature, static summarization has often been approached in the oﬄine setting [7, 18, 10].”
Deep Attentive Video Summarization With Distribution Consistency Learning (2020, methodology): “1) Data Sets: We evaluate the proposed ADSum method on three publicly available benchmark data sets of video summarization: SumMe [12], TVSum [13], and YouTube [21].”
Video Summarization Using Deep Neural Networks: A Survey (2021, methodology): “OVP and Youtube both contain 50 videos, whose annotations are sets of key-frames, produced by 5 users.”
A Dataset for Telling the Stories of Social Media Videos (2018, background): “Other related work includes visual summarization of Flickr photo albums (Sigurds-son et al., 2016a) or videos (De Avila et al., 2011; Zhang et al., 2016) where the idea is to pick the key images or frames that summarize the visual content.”
CLIP-It! Language-Guided Video Summarization (2021, methodology): “Note that this result is from applying our method in the wild, as the video was not a part of any dataset and was downloaded from YouTube.1 This shows that our method can generalize to out-of-distribution data.”