Large-Scale Video Summarization Using Web-Image Priors

By Aditya Khosla, Raffay Hamid, Chih-Jen Lin, Neel Sundaresan. 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

308 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/e4b1fd34dabc3bc37aad39279bae9fa06b4a9dac

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].”
TVSum: Summarizing web videos using titles (2015, methodology): “[25] learn canonical viewpoints using a multi-class SVM, while Kim et al.”
Multi-task deep visual-semantic embedding for video thumbnail selection (2015, methodology): “For the input thumbnails, we leverage the deep convolutional neural network (CNN) architecture as discussed in [7] by adapting their publicly released C++ implementation 2 .”
Video Summarization with Long Short-Term Memory (2016, methodology): “The results suggest that with sufficient annotated data, our model can capture temporal structures better than prior methods that lack explicit temporal structures [11,15,17,30,35] as well as those that consider only pre-defined ones [2,16].”
Unsupervised Semantic Parsing of Video Collections (2015, unknown): “These collections are also used to choose important scenes for keyframe selection [24] and further extended to video clip selection [25, 48].”
Diverse Sequential Subset Selection for Supervised Video Summarization (2014, background): “, to generate learned region saliency metrics [8] or train classifiers for canonical viewpoints [10]), but they do not train/learn the subset selection procedure itself.”
Ranking Domain-Specific Highlights by Analyzing Edited Videos (2014, background): “Similarly, given a video uploaded to ecommerce websites for selling cars and trucks, [8] propose to use web-image priors (i.”
Viewpoint-Aware Video Summarization (2018, background): “Unsupervised summarization [28, 25, 24, 26, 1, 8, 43, 14, 17, 18, 36, 27, 6] that creates a summary using specific selection criteria, has been conventionally studied.”
Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward (2017, methodology): “2011), Web image (Khosla et al. 2013), Online sparse coding (Zhao and Xing 2014), Co-archetypal (Song et al.”
Category-Specific Video Summarization (2014, unknown): “A few previous works [3,6,5] produced summaries using features crafted for specific visual categories.”
Textually Customized Video Summaries (2017, unknown): “[12] and Yang et al .”
Video summarization by learning submodular mixtures of objectives (2015, background): “Methods that go in this direction typically cluster the video into events and select the most important segment(s) per event [15, 11], following a kind of successive optimization of the objectives.”
Unsupervised Video Summarization with Adversarial LSTM Networks (2017, methodology): “These domains have been addressed with unsupervised methods, which typically use heuristic criteria for ranking and selecting key frames [21, 41, 15, 44, 34].”
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].”