Incomplete Multimodality-Diffused Emotion Recognition

Authors: Yuanzhi Wang, Yong Li, Zhen Cui

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We perform extensive experiments on publicly available MER datasets and achieve superior or comparable results across different missing modality patterns.
Researcher Affiliation Academia Yuanzhi Wang, Yong Li, Zhen Cui PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China. {yuanzhiwang, yong.li, zhen.cui}@njust.edu.cn
Pseudocode No The paper describes the method using equations and text but does not include any structured pseudocode or algorithm blocks.
Open Source Code Yes Codes are released at https://github.com/mdswyz/IMDer.
Open Datasets Yes We consider two standard MER datasets to conduct experiments, including CMU-MOSI [32] and CMU-MOSEI [33].
Dataset Splits Yes CMU-MOSI consists of 2199 monologue video clips. Where 1284, 229, and 686 samples are used as training, validation, and testing set. CMU-MOSEI contains 22856 samples of movie review video clips. Where 16326 samples are used for training, the remaining 1871 and 4659 samples are used for validation and testing.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions software tools like BERT, Facet, and COVAREP but does not specify their version numbers.
Experiment Setup Yes The optimal setting for β is set to 0.1 via the performance on the validation set.