Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
AmirAli Bagher Zadeh,Paul Pu Liang,Soujanya Poria,Erik Cambria,Louis-Philippe Morency +4 more
- 01 Jul 2018
- Vol. 1, pp 2236-2246
TL;DR: This paper introduces CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI), the largest dataset of sentiment analysis and emotion recognition to date and uses a novel multimodal fusion technique called the Dynamic Fusion Graph (DFG), which is highly interpretable and achieves competative performance when compared to the previous state of the art.
read more
Abstract: Analyzing human multimodal language is an emerging area of research in NLP Intrinsically this language is multimodal (heterogeneous), sequential and asynchronous; it consists of the language (words), visual (expressions) and acoustic (paralinguistic) modalities all in the form of asynchronous coordinated sequences From a resource perspective, there is a genuine need for large scale datasets that allow for in-depth studies of this form of language In this paper we introduce CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI), the largest dataset of sentiment analysis and emotion recognition to date Using data from CMU-MOSEI and a novel multimodal fusion technique called the Dynamic Fusion Graph (DFG), we conduct experimentation to exploit how modalities interact with each other in human multimodal language Unlike previously proposed fusion techniques, DFG is highly interpretable and achieves competative performance when compared to the previous state of the art
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Capturing High-Level Semantic Correlations via Graph for Multimodal Sentiment Analysis
Fan Qian,Jiqing Han,Yadong Guan,Wenjie Song,Yongjun He +4 more
TL;DR: C capsule networks are introduced to construct high-level semantic nodes in a graph, uncovering deep sentimental structures in multimodal sentiment analysis and the learnable adjacency matrices are employed to construct edges of graph, thus adaptively learning the relations between nodes.
4
OSAN: A One-Stage Alignment Network to Unify Multimodal Alignment and Unsupervised Domain Adaptation
Ye Liu,Lingfeng Qiao,Changsheng Liu,Di Yin,Chen Lin,Haoyuan Peng,Bo Ren +6 more
- 01 Jun 2023
TL;DR: A tensor-based alignment module (TAL) is presented and a dynamic domain generator (DDG) module is proposed to build transitional samples by mixing the shared information of two domains in a self-supervised manner, which helps the model learn a domain-invariant common representation space.
4
•Posted Content
Multimodal Embeddings from Language Models
TL;DR: This work integrates acoustic information into contextualized lexical embeddings through the addition of multimodal inputs to a pretrained bidirectional language model that contains paralinguistic information which can modify word meanings and provide affective information.
4
Sparse Fusion for Multimodal Transformers
16 Apr 2022
TL;DR: Sparse Fusion Transformers (SFT) as mentioned in this paper is a multimodal fusion method for transformers that performs comparably to existing state-of-the-art methods while having greatly reduced memory footprint and computation cost.
4
Adapted Multimodal BERT with Layer-wise Fusion for Sentiment Analysis
Odysseas S. Chlapanis,Georgios Paraskevopoulos,Alexandros Potamianos +2 more
- 01 Dec 2022
TL;DR: Adapted Multimodal BERT (AMB) as discussed by the authors is a BERT-based architecture for multimodal tasks that uses a combination of adapter modules and intermediate fusion layers.
References
Random Forests
Leo Breiman
- 01 Oct 2001
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
99K
Support-Vector Networks
Corinna Cortes,Vladimir Vapnik +1 more
TL;DR: High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Glove: Global Vectors for Word Representation
Jeffrey Pennington,Richard Socher,Christopher D. Manning +2 more
- 01 Oct 2014
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
•Posted Content
TensorFlow: A system for large-scale machine learning
Martín Abadi,Paul Barham,Jianmin Chen,Zhifeng Chen,Andy Davis,Jeffrey Dean,Matthieu Devin,Sanjay Ghemawat,Geoffrey Irving,Michael Isard,Manjunath Kudlur,Josh Levenberg,Rajat Monga,Sherry Moore,Derek G. Murray,Benoit Steiner,Paul A. Tucker,Vijay K. Vasudevan,Pete Warden,Martin Wicke,Yuan Yu,Xiaoqiang Zheng +21 more
TL;DR: The TensorFlow dataflow model is described and the compelling performance that Tensor Flow achieves for several real-world applications is demonstrated.