An Entanglement-driven Fusion Neural Network for Video Sentiment Analysis
Authors: Dimitris Gkoumas, Qiuchi Li, Yijun Yu, Dawei Song
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Comprehensive evaluation on two benchmarking datasets for video sentiment analysis shows that the model achieves significant performance improvement. We also show that the degree of non-separability between modalities optimizes the post-hoc interpretability. |
| Researcher Affiliation | Academia | Dimitris Gkoumas1,2 , Qiuchi Li3 , Yijun Yu1 and Dawei Song1,4 1The Open University, Milton Keynes, UK 2School of Electronic Engineering and Computer Science, Queen Mary University of London, UK 3University of Padua, Padua, Italy 4Beijing Institute of Technology, Beijing, China |
| Pseudocode | No | The paper describes the architecture and procedures in text and diagrams (Figure 1), but does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement about releasing source code or a link to a code repository. |
| Open Datasets | Yes | We performed experiments on two widely used benchmarking video sentiment analysis datasets: CMU Multimodal Opinion-level Sentiment Intensity (CMU-MOSI) [Zadeh et al., 2016], and the largest available dataset for multimodal sentiment analysis, CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) [Zadeh et al., 2018c]. |
| Dataset Splits | Yes | A grid search for the best hyper-parameters was conducted for all models. At each search, the models were trained for 100 epochs. Out of 50 searches, the model with the lowest validation loss was used to produce the test performance. |
| Hardware Specification | No | The paper does not explicitly describe the specific hardware used for experiments (e.g., GPU/CPU models, memory). |
| Software Dependencies | No | The paper mentions using "convolutional neural networks" (CNN), "Rectified Linear Unit (ReLU) as the activation function", "Adam as the optimization algorithm", and implicitly neural network frameworks like PyTorch or TensorFlow, but does not provide specific version numbers for any software dependencies like Python, PyTorch, etc. |
| Experiment Setup | Yes | A grid search for the best hyper-parameters was conducted for all models. At each search, the models were trained for 100 epochs... The parameters in the proposed EFNN model were determined by the set of hyper-parameters Θ = {D, K}, where D is the embedding dimension of input features into same dimensional spaces and K is the number of measurement vectors... All the parameters were trainable with respect to L1-loss defined on the extracted features. We chose Adam as the optimization algorithm. Measurements were initialized from standard normal distributions. |