Video abstraction: A systematic review and classification

By B. T. Truong, Svetha Venkatesh. TOMCCAP, 2007

937 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/37e084cdf8b8704b497b2d8e7547380c09468c7b

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

Visual to Text: Survey of Image and Video Captioning (2019, background): “[30] discussed the video abstraction techniques that target videos from various domains, including documentaries, movies, home recordings, etc.”
TVSum: Summarizing web videos using titles (2015, background): “The sheer amount of video available online has increased the demand for efficient ways to search and retrieve desired content [46].”
Towards Scalable Summarization of Consumer Videos Via Sparse Dictionary Selection (2012, background): “As motioned in [6], much previous work in video summarization has been focused on sports and news videos, such as the TRECVID dataset [8]–[12].”
Video Summarization With Attention-Based Encoder–Decoder Networks (2017, background): “Video summarization has been studied over two decades [1]–[6].”
Unsupervised Semantic Parsing of Video Collections (2015, background): “Early works in the area are summarized in [59] and mostly focus on choosing keyframes for visualization.”
Enhancing Video Summarization via Vision-Language Embedding (2017, background): “Automatic video summarization techniques [36] can facilitate more rapid video search [40, 42] and ease the burden of editing a long video by hand [35].”
Multi-View Video Summarization (2010, background): “A comprehensive review of the state-of-the-art video summarization methods can be found in [21].”
Textually Customized Video Summaries (2017, neutral): “[38].”
Summarizing surveillance videos with local-patch-learning-based abnormality detection, blob sequence optimization, and type-based synopsis (2015, methodology): “Although some methods extracted important video clips instead of frames to keep the temporal information [25], their summary efficiency will be poor if there exist important events in each frame of a video.”
A Practical Online Framework for Extracting Running Video Summaries under a Fixed Memory Budget (2021, background): “Indeed, this problem has gained signiﬁcant traction in recent years [29].”
Category-Specific Video Summarization (2014, background): “Most shot boundary detection methods focus on diﬀerences between consecutive frames [24], relying on image descriptors (pixel color histograms, local or global motion [7], or bag-of-features descriptors [25]).”
VSUMM: A mechanism designed to produce static video summaries and a novel evaluation method (2011, methodology): “The existing evaluation methods for video summarization are grouped into three different categories (Truong and Venkatesh, 2007): result description, objective metrics and user studies.”
Video Summarization Using Deep Neural Networks: A Survey (2021, methodology): “[3] discuss a variety of attributes that affect the outcome of a summarization process, such as the video domain, the granularity of the employed video fragments, the utilized summarization methodology, and the targeted type of summary.”
Concept-Based Video Retrieval (2009, methodology): “Extensive overviews of methods for summarization are presented in [153] and [239].”
Superpixels and Supervoxels in an Energy Optimization Framework (2010, background): “In particular, for video processing, there is an interest in coherent 3D segmentation for video abstraction and animation [25, 26].”
Pano2Vid: Automatic Cinematography for Watching 360° Videos (2016, background): “Video summarization Video summarization methods condense videos in time by identifying important events [7].”
Large-Scale Video Summarization Using Web-Image Priors (2013, background): “Video summarization has been looked at from multiple perspectives [28].”