Ranking Domain-Specific Highlights by Analyzing Edited Videos

By Min Sun, Ali Farhadi, S. M. Seitz. 2014

218 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Summarization, Signal Processing

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 Summarization

In Signal Processing

Citations in the corpus

Unsupervised Learning from Narrated Instruction Videos (2015, background): “While summarization is a subjective task, we here aim to extract the key steps required to achieve a concrete task that consistently appear in the same sequence in the input set of 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].”
Learning Temporal Regularity in Video Sequences (2016, background): “The availability of large numbers of uncontrolled videos gives rise to the problem of watching long hours of mean-ingless scenes [1].”
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.”
QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries (2021, methodology): “For the second task of ‘highlight detection’, many datasets [38, 12, 36, 8] are query-agnostic, where the detected highlights do not change for different input user queries.”
Title Generation for User Generated Videos (2016, background): “[36] automatically harvest user preference to learn a model for identifying highlights in each domain.”
Summarization of Egocentric Videos: A Comprehensive Survey (2017, methodology): “[23] outperform all the baselines (also including an HoG/HoG Fisher Vector-based SVM and a consumer video state-of-the-art summarization method [55]), proving the importance of knowing the video context.”
Pano2Vid: Automatic Cinematography for Watching 360° Videos (2016, methodology): “Among these, our proposed AutoCam shares with [10–12, 18, 19] the idea of using user-generated visual content from the web as exemplars for informative content.”
Textually Customized Video Summaries (2017, methodology): “We use the popular performance metric, mean Average Precision (mAP) [35].”
A Practical Online Framework for Extracting Running Video Summaries under a Fixed Memory Budget (2021, background): “In Gygli et al. [11], Sun et al. [28], and Herranz and Martinez [13] video snippets are selected according to their quality score measuring various aspects of a video (e.g., interestingness and rep-resentativeness).”
TVSum: Summarizing web videos using titles (2015, background): “Recent work has addressed this issue by using images and videos collected from the web, learning a predictive model tailored to a predefined set of categories [28, 38, 43] or constrained to a limited object domain [25]; while promising, it remains as a challenge to deal with the variety of topics in”
Learning from Narrated Instruction Videos (2015, methodology): “Our work is also related to video summarization and in particular to the recent work on category-specific video summarization [32], [37].”