Skin color-based video segmentation under time-varying illumination
By Leonid Sigal, Stan Sclaroff, Vassilis Athitsos. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
296 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/1556eb6251a5972a3442deb66c2143d64dea6ca1
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
- Kris M. Kitani
- Luc Van Gool
- José Manuel Álvarez
- Kristen Grauman
- Antonio M. López
- Nikolaos G. Bourbakis
- Cheng Li
- Praveen K. Kakumanu
Citations in the corpus
- Vision based hand gesture recognition for human computer interaction: a survey (2012, background): “TDNN Sigal et al. (2004), Wohler and Anlauf (1999) is based on time delays which gives individual neurons the ability to store the history of their input signals.”
- Pixel-Level Hand Detection in Ego-centric Videos (2013, methodology): “Color models have also been combined with trackers to take into account both the static and dynamic appearance of skin [16, 23, 1, 11].”
- Road Detection Based on Illuminant Invariance (2011, background): “In fact, works on other types of applications suggest the superiority of histograms compared with parametric models [12], [21].”
- Pixel-Level Hand Detection with Shape-Aware Structured Forests (2014, unknown): “Mixture of Gaussians [3] is commonly used to model colors of skin and non-skin regions for hand localization [4] and hand tracking [5, 6].”
- A survey of skin-color modeling and detection methods (2007, methodology): “This has been used by Brand and Mason [47], Chai and Bouzerdoum [36], Fleck et al. [56], Gomez and Morales [52], Gomez et al. [43], Jones and Rehg [54], Marcel and Benigo [57], Schwerdt and Crowley [18], Sigal et al. [95], Srisuk and Kuritach [58], Zarit et al. [33].”
- Model Recommendation with Virtual Probes for Egocentric Hand Detection (2013, background): “Previous work has explored the use of dynamic models to handle the gradual change in appearance [17] but may be prone to drifting when the change in the illumination is extreme.”