Understanding Social Interpersonal Interaction via Synchronization Templates of Facial Events

Authors: Rui Li, Jared Curhan, Mohammed Hoque

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We test our model on two different dyadic conversations of negotiation and job-interview. Based on the discovered facial event coordination, we are able to predict their conversation outcomes with higher accuracy than HMMs and GMMs.
Researcher Affiliation Academia Rui Li College of Computing & Info. Sciences Rochester Institute of Technology Rochester, New York 14623 Email: rxlics@rit.edu Jared Curhan Sloan School of Management Massachusetts Institute of Technology Cambridge, Boston 02139 Email: curhan@mit.edu Mohammed Ehsan Hoque Department of Computer Science University of Rochester Rochester, New York 14627 Email: mehoque@cs.rochester.edu
Pseudocode No The paper contains figures depicting the approach and probabilistic graphical model (Figure 1 and Figure 2), but no structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link regarding the public availability of its source code.
Open Datasets No The paper describes using custom datasets collected from 'Mechanical Turkers' and 'student participants' but does not provide concrete access information (link, DOI, or proper citation for a publicly available dataset).
Dataset Splits Yes Their cardinality numbers are determined via fivefold cross-validation. We use cross-validation scheme to recursively assign random 60% conversation videos of the two datasets into the training set and the rest into the testing set for the performance comparison.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory specifications, or cloud instances) used for running experiments are mentioned in the paper.
Software Dependencies No The paper mentions 'Computer Expression Recognition Toolbox (CERT)' and comparison models like 'HMMs and GMMs', but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes We specify a noninformative uniform base measure B0 as in Figure 2, and compute the posterior by initializing 4 chains of 10,000 sampling iterations on the training data.