BP4D-Spontaneous: a high-resolution spontaneous 3D dynamic facial expression database

By Xing Zhang, Lijun Yin, Jeffrey F. Cohn, Shaun J. Canavan, Michael J. Reale, Andy Horowitz, Peng Liu. Image and Vision Computing, 2014

831 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/b04a21a795de1901c336c787d89490bebf610770

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Experimental and Cognitive Psychology

Citations in the corpus

Multimodal Spontaneous Emotion Corpus for Human Behavior Analysis (2016, methodology): “We also performed a cross-database test by training on data extracted from the BP4D-Spontaneous database [35] and testing on the new data.”
Facial Expression Recognition by De-expression Residue Learning (2018, methodology): “We choose the spontaneous expression database BP4D [31] for”
Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild (2017, background): “BP4DSpontaneous [47] contains plenty of images from 41 subjects revealing a range of spontaneous expressions elicited through eight tasks.”
Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution (2020, methodology): “For the k-NN graph implemented in the SCC layer, we set k = 5 for the BP4D database and k = 7 for the DISFA database, which were determined by grid searching.”
Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-related Applications (2016, methodology): “issue with authentic emotion induction tasks [38].”
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]).”
OpenFace 2.0: Facial Behavior Analysis Toolkit (2018, methodology): “Our models are trained on DISFA [48], SEMAINE [51], BP4D [80], UNBC-McMaster [44], Bosphorus [59] and FERA 2011 [66] datasets.”
A Brief Review of Facial Emotion Recognition Based on Visual Information (2018, background): “Performance Evaluation of It contains of 1650 recordings of 50 persons posing for 33 different facial expressions and emotions [33].”
OpenFace: An open source facial behavior analysis toolkit (2016, methodology): “The challenge organizers evaluated it on an unseen (and unreleased) subset of SEMAINE and BP4D datasets.”
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 Expression Analysis under Partial Occlusion (2018, methodology): “12) The Binghamton Pittsburgh 4D spontaneous expression Database (BP4D) [Zhang et al. 2014c] was collected to analyze facial actions that are not deliberately posed.”
Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace (2019, neutral): “BP4DS and BP4D+ datasets correspond to the ones used in the FERA 2015 [41] and 2017 [42] Challenges, respectively.”
A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances (2022, background): “Meanwhile, some large-scale visual databases such as BU-4DFE and BP4D can be employed to pre-train target model to recognize facial expressions [261] or micro-expressions [409].”
Automatic Analysis of Facial Actions: A Survey (2019, neutral): “2466[218] X. Zhang, et al., “BP4D-spontaneous: A high-resolution sponta2467neous 3D dynamic facial expression database,” Image Vis.”
Reliable Crowdsourcing and Deep Locality-Preserving Learning for Unconstrained Facial Expression Recognition (2019, background): “BP4D-Spontaneous [80] contains abundant images with high resolution from 41 subjects displaying a range of spontaneous expressions elicited through eight tasks.”