Creating Summaries from User Videos

By Michael Gygli, Helmut Grabner, Hayko Riemenschneider, Luc Van Gool. European Conference on Computer Vision, 2014

826 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Sociology and Political Science

View Paper: https://www.semanticscholar.org/paper/799bf307438ec2171e6f0bd5b8040f678d5b28da

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 Sociology and Political Science

Citations in the corpus

Video Summarization Using Deep Neural Networks: A Survey (2021, methodology): “The evaluation approach and benchmark datasets of [19] and [20] were jointly used to evaluate the summarization performance in [21].”
Detecting Engagement in Egocentric Video (2016, background): “, zoom [4], [12]–[14]) are absent in passive wearable camera data.”
Deep Attentive Video Summarization With Distribution Consistency Learning (2020, methodology): “2) Evaluation Metric: We apply the popular F-measure to evaluate the performance of automated generated summary compared with the ground-truth summary [1]–[3], [9], [12], [13], [28].”
Enhancing Video Summarization via Vision-Language Embedding (2017, methodology): “Note that there exist other popular benchmarks for video summarization, including SumMe [8] and TVSUM [34] datasets.”
TVSum: Summarizing web videos using titles (2015, methodology): “Datasets: We evaluated our approach on two real-world datasets: SumMe [20] and our TVSum50.”
DevNet: A Deep Event Network for multimedia event detection and evidence recounting (2015, background): “It is unlike traditional video summarization tasks [24, 27, 12], which mainly seek to reduce the redundancy of the videos.”
Making 360° Video Watchable in 2D: Learning Videography for Click Free Viewing (2017, background): “Video summarization Video summarization aims to generate a concise representation for a video by removing temporal redundancy while preserving the important events [8, 14–16, 24, 27, 32, 33, 38, 42].”
CLIP-It! Language-Guided Video Summarization (2021, methodology): “Generic video summarization datasets such as TVSum [37] and SumMe [7] provide ground-truth annotations in the form of frame or shot-level importance scores specified by multiple annotators.”
Multimodal Abstractive Summarization for How2 Videos (2019, background): “Video summarization is the task of producing a compact version of the video (visual summary) by encapsulating the most informative parts (Money and Agius, 2008; Lu and Grauman, 2013; Gygli et al., 2014; Song et al., 2015; Sah et al., 2017).”
Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward (2017, methodology): “Gygli et al. (Gygli et al. 2014) learned a linear regressor to predict the degree of interest-ingness of video frames and selected keyframes with the highest interestingness scores.”
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.”
Viewpoint-Aware Video Summarization (2018, background): “However, owing to the subjective property of this task, a supervised approach [21, 38, 32, 23, 12, 31, 13, 19, 9, 42], that trains a summarization model which takes human-created summaries as the supervision, became standard because of its better performance.”
A Practical Online Framework for Extracting Running Video Summaries under a Fixed Memory Budget (2021, methodology): “A detailed description of the data is given in Gygli et al. [11].”
Video Summarization with Long Short-Term Memory (2016, methodology): “However, on SumMe , our methods underperform the state-of-the-art.”
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding (2023, background): “There have been miscellaneous time-sensitive video tasks, including temporal video grounding [27, 49], dense video captioning [46, 52, 62], video summarization [1, 8, 41, 58], video highlight detection [15, 30], and step localization [5, 39, 55], etc.”
Visual Motif Discovery via First-Person Vision (2016, methodology): “Each video shot is evaluated for its significance using the presence of important persons and objects [10] or interestingness [12].”