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
VideoAdviser: Video Knowledge Distillation for Multimodal Transfer Learning.
Yanan Wang,Donghuo Zeng,Shinya Wada,Satoshi Kurihara +3 more
TL;DR: This paper proposes VideoAdviser, a video knowledge distillation method for multimodal transfer learning, achieving high efficiency-performance by transferring multimodal knowledge from a CLIP-based teacher to a RoBERTa-based student, improving performance by up to 12.3% in sentiment analysis and 3.4% in audio-visual retrieval.
Cross-modal context-gated convolution for multi-modal sentiment analysis
Huanglu Wen,Shaodi You,Ying Fu +2 more
TL;DR: This work proposes cross-modal context-gated convolution for unaligned sequences, which captures the local cross- modal interactions, dealing with the misalignment while reducing the effect of unrelated information.
MUSER: MUltimodal Stress detection using Emotion Recognition as an Auxiliary Task
Yiqun Yao,Michalis Papakostas,Mihai Burzo,Mohamed Abouelenien,Rada Mihalcea +4 more
- 01 Jun 2021
TL;DR: This work proposes MUSER – a transformer-based model architecture and a novel multi-task learning algorithm with speed-based dynamic sampling strategy that is effective for stress detection with both internal and external auxiliary tasks, and achieves state-of-the-art results.
Linking emotions to behaviors through deep transfer learning.
TL;DR: Through the analysis, it is found that emotion-related information is an important cue for behavior recognition and the importance of emotional-context in the expression of behavior is investigated by constraining (or not) the neural networks’ contextual view of the data.
A Novel Multimodal Sentiment Analysis Model Based on Gated Fusion and Multi-Task Learning
Xin Sun,Xiangyu Ren,Xiaohao Xie +2 more
- 14 Apr 2024
TL;DR: This work proposes a novel model for multimodal sentiment analysis based on gated fusion and multi-task learning that outperforms the existing methods and achieves the state-of-the art performance.
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.