A high-resolution 3D dynamic facial expression database

By Lijun Yin, Xiaochen Chen, Yi Sun, T. Worm, Michael J. Reale. 2008

549 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology

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 Experimental and Cognitive Psychology

Citations in the corpus

Generating 3D faces using Convolutional Mesh Autoencoders (2018, background): “Existing large scale datasets [14, 16, 50, 49, 38] do not contain high resolution extreme facial expressions.”
Static and dynamic 3D facial expression recognition: A comprehensive survey (2012, methodology): “The same institution continued the effort and recorded BU-4DFE [51], the first database consisting of 4D faces (sequences of 3D faces).”
The MUG facial expression database (2010, background): “This is a high-resolution 3D dynamic facial expression database captured at a video rate.”
A FACS valid 3D dynamic action unit database with applications to 3D dynamic morphable facial modeling (2011, background): “We provide the first quantitative assessment of such 3D facial mesh registration techniques and show how our proposed method provides more reliable correspondence.”
Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-related Applications (2016, background): “BU-4DFE is a high-resolution 3D dynamic FE dataset [207].”
Capture, Learning, and Synthesis of 3D Speaking Styles (2019, background): “3D face datasets: Several 3D face datasets have been released that focus on the analysis of static 3D facial shape and expression (e.g. [13, 47, 65]) or dynamic facial expressions (e.g. [2, 15, 18, 44, 64, 68, 69]).”
A Survey on Human Motion Analysis from Depth Data (2013, methodology): “3D Dynamic Facial Expression [110] 6 facial expressions, 60k 3d models 101 83 facial points”
Painful data: The UNBC-McMaster shoulder pain expression archive database (2011, background): “From initial focus on posed images recorded from a frontal view, current efforts extend to posed data recorded from multiple views [4], [5], 3D imaging [6], and, increasingly, non-posed facial behavior in real-world settings in which non-frontal pose and head motion are common [7], [8].”
Facial Expression Analysis under Partial Occlusion (2018, methodology): “The BU-3DFE was later extended to a high-resolution 3D dynamic database – BU-4DFE [Yin et al. 2008].”
BP4D-Spontaneous: a high-resolution spontaneous 3D dynamic facial expression database (2014, methodology): “The CMU Multi-PIE database [34], 3Ddynamic AU database [35], Bosphorus database [9], KDEF [33], BU 3D facial expression databases [14,15], and ICT-3DRFE database [24] begin to address the need for 3D (or multi-view) data but are limited to posed facial behavior.”
Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild (2019, methodology): “We test our method on three human face datasets: CelebA [33], 3DFAW [20, 25, 67, 64] and BFM [43].”
Facial Landmark Detection: A Literature Survey (2018, methodology): “– XM2VTSDB(Messer et al. 1999):TheExtendedM2VTS database contains videos of 295 subjects with speech and Table 3 Summary of the databases Databases Video (v)/image (i) Gray (g)/color (c) Amount of data Variations Number of landmark points BioID (https://www.bioid. com/About/BioID-FaceDatabase) i g 1”
Aff-Wild: Valence and Arousal ‘In-the-Wild’ Challenge (2017, methodology): “Some representative datasets, which are still used in many recent works [18], include the Cohn-Kanade database [33, 24], the MMI database [29, 35], the Multi-PIE database [17] and the BU-3D and BU-4D databases [41, 40].”
The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression (2010, methodology): “When comparing the individual SPTS and CAPP features, the SPTS features yielded the higher detection rates for AUs 1, 2, 4, 23, 25 and 27, while the CAPP features gained better performance for AUs 5, 6, 7, 9, 11, 12, 15, 17, 20, 24 and 26.”
3D Constrained Local Model for rigid and non-rigid facial tracking (2012, methodology): “In order to create such a training set we use the 4DBUFE [30] as our starting point.”
Multilinear Wavelets: A Statistical Shape Space for Human Faces (2014, methodology): “Figure 7 shows some results for a selection of frames from three sequences from the BU4DFE database [32].”
Geometry-Contrastive GAN for Facial Expression Transfer. (2018, methodology): “BU-4DFE contains 101 subjects, each one displaying six acted categorical facial expressions with moderate head pose variations.”