Unsupervised Video Summarization with Adversarial LSTM Networks

By Behrooz Mahasseni, Michael Lam, Sinisa Todorovic. Computer Vision and Pattern Recognition, 2017

569 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/620fe6c786d15efca7f553ad70f295e2b693b391

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

Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward (2017, methodology): “Inspired by (Mahasseni, Lam, and Todorovic 2017), we minimize the following term during training, where (cid:15) determines the percentage of frames to be selected.”
Listen to Look: Action Recognition by Previewing Audio (2019, background): “Video summarization work also aims to select keyframes or clips [36, 25, 38, 75], but with the purpose of conveying the gist of the video to a human viewer.”
Deep Attentive Video Summarization With Distribution Consistency Learning (2020, methodology): “For example, SUM-GAN [9] proposes to formulate video summarization in the framework of generative adversarial network (GAN), where the LSTM is applied as generator and discriminator.”
A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos (2018, background): “Although video summarization techniques [4, 14] provide quick access to videos’ information, they only return segmented clips or single images of the relevant moments.”
A Practical Online Framework for Extracting Running Video Summaries under a Fixed Memory Budget (2021, methodology): “Mahassen et al [22] took the unsupervised approach and employed deep adversarial LSTM networks for video summarization.”
Bidirectional Conditional Generative Adversarial Networks (2017, methodology): “ive modeling of data from complex distributions for a variety of applications such as image editing [23], image synthesis from text descriptions [24], image super-resolution [14], video summarization [17] and others [2,8,10,11,15,26,28,29,30, 32,34,35], with very promising results. The core methodol”
Video Summarization Using Deep Neural Networks: A Survey (2021, methodology): “To train a video summarization network in a fully unsupervised manner, the use of GANs seems to be the central direction thus far ([31], [46], [47], [48], [49], [50], [51]).”
CLIP-It! Language-Guided Video Summarization (2021, methodology): “Other notable unsupervised approaches include an adversarial LSTM based method [23], a generative adversarial network to learn from unpaired data [31], and a cycle consistent learning objective [41].”
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.”
SCSampler: Sampling Salient Clips From Video for Efficient Action Recognition (2019, background): “For example, video summarization [18, 19, 29, 37, 56, 57, 58] and the automatic production of sport highlights [30, 31] entail creating a much shorter version of the original video by concatenating a small set of snippets corresponding to the most informative or exciting moments.”