Reliable Transition Detection in Videos: A Survey and Practitioner's Guide
By Rainer Lienhart. International Journal of Image and Graphics, 2001
335 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Signal Processing
View Paper: https://www.semanticscholar.org/paper/10c8691e23dffadab19c39fb9245496efbf75b2a
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
- Andrew Zisserman
- Luc Van Gool
- Cordelia Schmid
- Jitendra Malik
- Xiaogang Wang
- Dacheng Tao
- Bernt Schiele
- Li Fei-Fei
In Signal Processing
- Andrew Zisserman
- Joon Son Chung
- Oriol Vinyals
- Andrew W. Senior
- Amir Jamaludin
- Triantafyllos Afouras
- Junichi Yamagishi
- Arsha Nagrani
Citations in the corpus
- Out of Time: Automated Lip Sync in the Wild (2016, methodology): “by comparing color histograms across consecutive frames [16].”
- You said that? (2017, methodology): “First, the shot boundaries are determined by comparing colour histograms [17] to find the within-shot frames for which tracking is to be run.”
- A Formal Study of Shot Boundary Detection (2007, background): “The related surveys with discussions on thresholding scheme can be found in [8], [9].”
- Learning realistic human actions from movies (2008, background): “We also eliminate detections due to artifacts at shot boundaries [11].”
- Movie/Script: Alignment and Parsing of Video and Text Transcription (2008, methodology): “A popular technique is to compute a set of localized color histograms for each image and use a histogram distance function to detect boundaries [6, 7].”
- Lip Reading in the Wild (2016, methodology): “This is done by comparing color histograms across consecutive frames [20].”
- Lip Reading Sentences in the Wild (2016, methodology): “tected by comparing colour histograms across consecutive frames [24].”
- Video data mining using configurations of viewpoint invariant regions (2004, background): “Examples of ‘mined’ objects are shown for a feature length film and a sitcom.”
- Video shot detection and condensed representation. a review (2006, background): “Several reviews on shot boundary detection have been published in the last decade [3]–[6], yet none later than 2001.”
- Deep Audio-Visual Speech Recognition (2018, neutral): “color histograms across consecutive frames [31].”
- LRS3-TED: a large-scale dataset for visual speech recognition (2018, neutral): “The time boundaries of a shot are determined by comparing color histograms across consecutive frames [11], and within each shot, face tracks are generated from face detections based on their positions.”