Differentiating Between Posed and Spontaneous Expressions with Latent Regression Bayesian Network

Authors: Quan Gan, Siqi Nie, Shangfei Wang, Qiang Ji

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on two benchmark databases demonstrate the advantages of the proposed approach in modeling spatial patterns as well as its superior performance to the existing methods in differentiating between posed and spontaneous expressions.
Researcher Affiliation Academia 1School of Computer Science and Technology, University of Science and Technology of China 1{gqquan@mail., sfwang@}ustc.edu.cn 2Department of Electrical, Computer and Systems Engineering, Rensselaer Polytechnic Institute 2{nies, jiq}@rpi.edu
Pseudocode Yes Algorithm 1 Parameter Learning for an LRBN.
Open Source Code No The paper does not provide CONCRETE ACCESS TO SOURCE CODE (specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described in this paper.
Open Datasets Yes We want to conduct experiments in the general case instead of in the case of being given a specific expression, thus we adopted the SPOS database and the NVIE database in our experiments. ... (Pfister et al. 2011b) ... (Wang et al. 2010)
Dataset Splits Yes For the SPOS database, we adopt leave-one-subject-out cross-validation. For the NVIE database, we divide subjects into 10 groups, and each group contains 8 subjects, then we apply leave-one-group-out cross validation.
Hardware Specification No The paper does not provide SPECIFIC HARDWARE DETAILS (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide SPECIFIC ANCILLARY SOFTWARE DETAILS (e.g., library or solver names with version numbers like Python 3.8, CPLEX 12.4) needed to replicate the experiment.
Experiment Setup No The paper does not contain SPECIFIC EXPERIMENTAL SETUP DETAILS (concrete hyperparameter values, training configurations, or system-level settings) in the main text beyond stating general approaches like limiting latent nodes or the number of samples for log-likelihood estimation.