A user attention model for video summarization

By Yufei Ma, Lie Lu, HongJiang Zhang, Mingjing Li. MULTIMEDIA '02, 2002

623 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/9f1df97b5829485c1b1312301b4a8a54ce123285

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

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.”
Saliency detection by multi-context deep learning (2015, background): “It has a wide range of applications in computer vision and image processing tasks, such as image/video compression and summarization [38], content-aware image resizing [6], and photo collage [53].”
Large-Scale Video Summarization Using Web-Image Priors (2013, background): “To address these challenges, there have been some recent approaches that take into account interesting objects [17], events [32], user preferences [2], and attention models [21] to summarize videos.”
A visual attention model for adapting images on small displays (2003, methodology): “As illustrated in [17], the saliency attention is determined by the number of saliency regions and their brightness, area, and position in the gray saliency map, as shown in Fig.”
Video Summarization with Long Short-Term Memory (2016, background): “Informative criteria include relevance [10,13,14,31,36], representativeness or importance [5,6,9,10,11,33,35], and diversity or coverage [1,12,28,30,34].”
Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, methodology): “In computer graphics, SOD has been used tasks such as non-photo-realist rendering [15], [16], automatic image cropping [17], image retargeting [18], [19], video summarization [20], [21], etc .”
Towards Scalable Summarization of Consumer Videos Via Sparse Dictionary Selection (2012, methodology): “For instance, [15] proposed a user attention model and [16] used mosaic-based image representation for video summarization.”
Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods (2019, background): “Nevertheless, this task can be seen very close to the well researched area of video summarization (Ma et al., 2002) using only videos.”
Video Summarization With Attention-Based Encoder–Decoder Networks (2017, background): “During these years, many approaches have been developed by exploring cues ranging from low-level visual inconsistency [10] [11], attention [3] [5] [26], to high-level semantic change of concepts [6] [13] and entities in videos [12] [34].”
TVSum: Summarizing web videos using titles (2015, background): “Much work has been devoted to unsupervised video summarization, assessing the importance of frames using visual attention [16, 5], interestingness [21, 20], user engagement [33, 35], content frequency [52] and nonredundancy [30, 50].”
Egocentric Video-Language Pretraining (2022, background): “Egocentric video has received increasing interests from the academia (e.g., activity recognition [11], activity anticipation [12], and video summarization [13]) and industry (various applications in robotics and augmented reality).”
Diverse Sequential Subset Selection for Supervised Video Summarization (2014, background): “These include representativeness (the frames should depict the main contents of the videos) [1, 2, 10], diversity (they should not be redundant) [4, 11], interestingness (they should have salient motion/appearance [2, 3, 6] or trackable objects [5, 12, 7]), or importance (they should contain importa”
Contrast-based image attention analysis by using fuzzy growing (2003, methodology): “In [18], we present a comprehensive solution for user attention analysis in video, which integrates a series of algorithms of video, audio and image attention analysis.”
A generic framework of user attention model and its application in video summarization (2005, methodology): “Compared to the original user attention model in [4], the static attention model is replaced by our latest work [3], camera motion estimation also employs our latest work [44], instead of classical affine model.”
Deep Contrast Learning for Salient Object Detection (2016, background): “Though early work primarily focused on predicting eye-fixations in images, research has shown that salient object detection, which emphasizes object-level integrity of saliency prediction results, is more useful and can serve as a pre-processing step for a variety of computer vision and image proces”
Instance-Level Salient Object Segmentation (2017, methodology): “ in computer vision and has served as a pre-processing step to facilitate a wide range of vision applications including content-aware image editing [4], object detection [38], and video summarization [36]. Recently the accuracy of salient object detection has been improved rapidly [29,30,33,45] due ”
Detecting Engagement in Egocentric Video (2016, methodology): “• Saliency Map: Following [17], [21], we compute the saliency map for each frame and take the average saliency value.”
Unsupervised extraction of visual attention objects in color images (2006, background): “Lately, some confirmed conclusions on visual attention have been applied to a few multimedia applications, including handwritten digit recognition and face recognition [6], video summary [7], as well as image adaptation [8].”
Video summarization: methods and landscape (2003, background): “[25] evaluated enjoyability and informativeness value of summaries.”