Representation Learning is a significant and challenging task in multimodal learning. Effective modality representations should contain two parts of characteristics: the consistency and the difference. Due to the unified multimodal annotation, existing methods are restricted in capturing differentiated information. However, additional uni-modal annotations are high time- and labor-cost. In this paper, we design a label generation module based on the self-supervised learning strategy to acquire independent unimodal supervisions. Then, joint training the multi-modal and uni-modal tasks to learn the consistency and difference, respectively. Moreover, during the training stage, we design a weight-adjustment strategy to balance the learning progress among different subtasks. That is to guide the subtasks to focus on samples with a larger difference between modality supervisions. Last, we conduct extensive experiments on three public multimodal baseline datasets. The experimental results validate the reliability and stability of auto-generated unimodal supervisions. On MOSI and MOSEI datasets, our method surpasses the current state-of-the-art methods. On the SIMS dataset, our method achieves comparable performance than human-annotated unimodal labels. The full codes are available at https://github.com/thuiar/Self-MM.
Nowadays, with the explosive growth of multimodal reviews on social media platforms, multimodal sentiment analysis has recently gained popularity because of its high relevance to these social media posts. Although most previous studies design various fusion frameworks for learning an interactive representation of multiple modalities, they fail to incorporate sentimental knowledge into inter-modality learning. This paper proposes a Multi-channel Attentive Graph Convolutional Network (MAGCN), consisting of two main components: cross-modality interactive learning and sentimental feature fusion. F…
Harbin Institute of Technology（哈尔滨工业大学）；AI Lab of China Merchants Bank（招商银行人工智能实验室）
Multimodal sentiment analysis has attracted increasing attention and lots of models have been proposed. However, the performance of the state-of-the-art models decreases sharply when they are deployed in the real world. We find that the main reason is that real-world applications can only access the text outputs by the automatic speech recognition (ASR) models, which may be with errors because of the limitation of model capacity. Through further analysis of the ASR outputs, we find that in some cases the sentiment words, the key sentiment elements in the textual modality, are recognized as oth…
Compared with unimodal data, multimodal data can provide more features to help the model analyze the sentiment of data. Previous research works rarely consider token-level feature fusion, and few works explore learning the common features related to sentiment in multimodal data to help the model fuse multimodal features. In this paper, we propose a Contrastive Learning and Multi-Layer Fusion (CLMLF) method for multimodal sentiment detection. Specifically, we first encode text and image to obtain hidden representations, and then use a multi-layer fusion module to align and fuse the token-level …
Language Technologies Institute（语言技术研究所）；Carnegie Mellon University（卡内基梅隆大学）；Temasek Laboratories（淡马锡实验室）；NTU, Singapore（新加坡南洋理工大学）
Multimodal sentiment analysis is an increasingly popular research area, which extends the conventional language-based definition of sentiment analysis to a multimodal setup where other relevant modalities accompany language. In this paper, we pose the problem of multimodal sentiment analysis as modeling intra-modality and inter-modality dynamics. We introduce a novel model, termed Tensor Fusion Network, which learns both such dynamics end-to-end. The proposed approach is tailored for the volatile nature of spoken language in online videos as well as accompanying gestures and voice. In the expe…
Enhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University（航天信息安全部门与可信计算教育部重点实验室，网络安全科学与工程学院，武汉大学）
National University of Singapore（新加坡国立大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Building robust multimodal models are crucial for achieving reliable deployment in the wild. Despite its importance, less attention has been paid to identifying and improving the robustness of Multimodal Sentiment Analysis (MSA) models. In this work, we hope to address that by (i) Proposing simple diagnostic checks for modality robustness in a trained multimodal model. Using these checks, we find MSA models to be highly sensitive to a single modality, which creates issues in their robustness; (ii) We analyze well-known robust training strategies to alleviate the issues. Critically, we observe …
LLaVAC: Fine-tuning LLaVA as a Multimodal Sentiment Classifier
iApp Technology Co., Ltd.（iApp科技有限公司）；Panasonic Research and Development on Artificial Intelligence (AI)（松下人工智能研发中心）；Sirindhorn International Institute of Technology, Thammasat University（泰国法政大学诗琳通国际理工学院）
Multimodal sentiment analysis is an important research area that predicts speaker's sentiment tendency through features extracted from textual, visual and acoustic modalities. The central challenge is the fusion method of the multimodal information. A variety of fusion methods have been proposed, but few of them adopt end-to-end translation models to mine the subtle correlation between modalities. Enlightened by recent success of Transformer in the area of machine translation, we propose a new fusion method, TransModality, to address the task of multimodal sentiment analysis. We assume that tr…
Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors. From a psychological perspective, emotions are the expression of affect or feelings during a short period, while sentiments are formed and held for a longer period. However, most existing works study sentiment and emotion separately and do not fully exploit the complementary knowledge behind the two. In this paper, we propose a multimodal sentiment knowledge-sharing framework (UniMSE) that unifies MSA and ERC tasks from features, labels, and mod…
SentiMM: A Multimodal Multi-Agent Framework for Sentiment Analysis in Social Media
College of Information and Electrical Engineering, China Agricultural University（信息与电气工程学院，中国农业大学）；College of Software, Jilin University（软件学院，吉林大学）；College of Communication Engineering, Jilin University（通信工程学院，吉林大学）
Multimodal sentiment analysis is an important research task to predict the sentiment score based on the different modality data from a specific opinion video. Many previous pieces of research have proved the significance of utilizing the shared and unique information across different modalities. However, the high-order combined signals from multimodal data would also help extract satisfied representations. In this paper, we propose CMGA, a Cross-Modality Gated Attention fusion model for MSA that tends to make adequate interaction across different modality pairs. CMGA also adds a forget gate to…
Current multimodal sentiment analysis frames sentiment score prediction as a general Machine Learning task. However, what the sentiment score actually represents has often been overlooked. As a measurement of opinions and affective states, a sentiment score generally consists of two aspects: polarity and intensity. We decompose sentiment scores into these two aspects and study how they are conveyed through individual modalities and combined multimodal models in a naturalistic monologue setting. In particular, we build unimodal and multimodal multi-task learning models with sentiment score pred…
National University of Ireland Galway（爱尔兰国立高威大学）；Amrita Vishwa Vidyapeetham（阿姆里塔大学）；Indian Institute of Information Technology and Management-Kerala（喀拉拉邦印度信息技术与管理学院）；Universiti Pendidikan Sultan Idris（苏丹依德理斯教育大学）
Human communication is inherently multimodal and asynchronous. Analyzing human emotions and sentiment is an emerging field of artificial intelligence. We are witnessing an increasing amount of multimodal content in local languages on social media about products and other topics. However, there are not many multimodal resources available for under-resourced Dravidian languages. Our study aims to create a multimodal sentiment analysis dataset for the under-resourced Tamil and Malayalam languages. First, we downloaded product or movies review videos from YouTube for Tamil and Malayalam. Next, we …
National University of Singapore（新加坡国立大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Multimodal Sentiment Analysis is an active area of research that leverages multimodal signals for affective understanding of user-generated videos. The predominant approach, addressing this task, has been to develop sophisticated fusion techniques. However, the heterogeneous nature of the signals creates distributional modality gaps that pose significant challenges. In this paper, we aim to learn effective modality representations to aid the process of fusion. We propose a novel framework, MISA, which projects each modality to two distinct subspaces. The first subspace is modality-invariant, w…
Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）；Institute of Artificial Intelligence, Huazhong University of Science and Technology（华中科技大学人工智能研究院）；Hubei Key Laboratory of Brain-Inspired Intelligent Systems, Huazhong University of Science and Technology（华中科技大学脑启发智能系统省重点实验室）；Key Laboratory of Image Processing and Intelligent Control (Huazhong University of Science and Technology), Ministry of Education（图像处理与智能控制重点实验室（华中科技大学））
University of Stirling（斯特林大学）；Edinburgh Napier University（爱丁堡龙比亚大学）；Nanyang Technological University（南洋理工大学）
Most recent works on sentiment analysis have exploited the text modality. However, millions of hours of video recordings posted on social media platforms everyday hold vital unstructured information that can be exploited to more effectively gauge public perception. Multimodal sentiment analysis offers an innovative solution to computationally understand and harvest sentiments from videos by contextually exploiting audio, visual and textual cues. In this paper, we, firstly, present a first of its kind Persian multimodal dataset comprising more than 800 utterances, as a benchmark resource for re…
Multimodal Sentiment Analysis with Missing Modality: A Knowledge-Transfer Approach
College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算机与数据科学学院）；Singapore University of Social Sciences, Singapore（新加坡社会科学研究大学）
School of Computer Science and Engineering, NTU（南洋理工大学计算机科学与工程学院）；School of Natural Sciences, University of Stirling（斯特灵大学自然科学学院）；Temasek Laboratories, NTU（南洋理工大学淡马锡实验室）；National Institute of Technology, Warangal（瓦朗加尔国立理工学院）
We propose a framework for multimodal sentiment analysis and emotion recognition using convolutional neural network-based feature extraction from text and visual modalities. We obtain a performance improvement of 10% over the state of the art by combining visual, text and audio features. We also discuss some major issues frequently ignored in multimodal sentiment analysis research: the role of speaker-independent models, importance of the modalities and generalizability. The paper thus serve as a new benchmark for further research in multimodal sentiment analysis and also demonstrates the diff…
Cooperative Sentiment Agents for Multimodal Sentiment Analysis
College of Computer Science and Technology in Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；School of Computer Science in Nanjing University of Posts and Telecommunications（南京邮电大学计算机学院）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Functional Brain Imaging Institute（功能脑成像研究所）；Nanjing Medical University（南京医科大学）
Multimodal sentiment analysis has recently gained popularity because of its relevance to social media posts, customer service calls and video blogs. In this paper, we address three aspects of multimodal sentiment analysis; 1. Cross modal interaction learning, i.e. how multiple modalities contribute to the sentiment, 2. Learning long-term dependencies in multimodal interactions and 3. Fusion of unimodal and cross modal cues. Out of these three, we find that learning cross modal interactions is beneficial for this problem. We perform experiments on two benchmark datasets, CMU Multimodal Opinion …
Instituto Politécnico Nacional（国立理工学院）；National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）
Multimodal sentiment analysis is a very actively growing field of research. A promising area of opportunity in this field is to improve the multimodal fusion mechanism. We present a novel feature fusion strategy that proceeds in a hierarchical fashion, first fusing the modalities two in two and only then fusing all three modalities. On multimodal sentiment analysis of individual utterances, our strategy outperforms conventional concatenation of features by 1%, which amounts to 5% reduction in error rate. On utterance-level multimodal sentiment analysis of multi-utterance video clips, for which…
Multimodal sentiment analysis is drawing an increasing amount of attention these days. It enables mining of opinions in video reviews which are now available aplenty on online platforms. However, multimodal sentiment analysis has only a few high-quality data sets annotated for training machine learning algorithms. These limited resources restrict the generalizability of models, where, for example, the unique characteristics of a few speakers (e.g., wearing glasses) may become a confounding factor for the sentiment classification task. In this paper, we propose a Select-Additive Learning (SAL) …
Multimodal sentiment analysis has currently identified its significance in a variety of domains. For the purpose of sentiment analysis, different aspects of distinguishing modalities, which correspond to one target, are processed and analyzed. In this work, we propose the targeted aspect-based multimodal sentiment analysis (TABMSA) for the first time. Furthermore, an attention capsule extraction and multi-head fusion network (EF-Net) on the task of TABMSA is devised. The multi-head attention (MHA) based network and the ResNet-152 are employed to deal with texts and images, respectively. The in…
Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning
Academy for Engineering and Technology, Fudan University（复旦大学工程与技术学院）；Cognition and Intelligent Technology Laboratory（认知与智能技术实验室）；Institute of Metaverse & Intelligent Medicine, Fudan University（复旦大学元宇宙与智能医学研究院）；Jilin Provincial Key Laboratory of Intelligence Science and Engineering（吉林省智能科学与工程重点实验室）；Engineering Research Center of AI and Robotics, Ministry of Education（教育部人工智能与机器人工程研究中心）
This paper investigates the effectiveness and implementation of modality-specific large-scale pre-trained encoders for multimodal sentiment analysis~(MSA). Although the effectiveness of pre-trained encoders in various fields has been reported, conventional MSA methods employ them for only linguistic modality, and their application has not been investigated. This paper compares the features yielded by large-scale pre-trained encoders with conventional heuristic features. One each of the largest pre-trained encoders publicly available for each modality are used; CLIP-ViT, WavLM, and BERT for vis…
CIC, Instituto Politécnico Nacional（国家理工学院CIC（CIC））；SCSE, Nanyang Technological Institute（南洋理工学院计算机学院（SCSE））；SOC, National University of Singapore（新加坡国立大学SOC（SOC））；Edinburgh Napier University（爱丁堡龙比亚大学）
We compile baselines, along with dataset split, for multimodal sentiment analysis. In this paper, we explore three different deep-learning based architectures for multimodal sentiment classification, each improving upon the previous. Further, we evaluate these architectures with multiple datasets with fixed train/test partition. We also discuss some major issues, frequently ignored in multimodal sentiment analysis research, e.g., role of speaker-exclusive models, importance of different modalities, and generalizability. This framework illustrates the different facets of analysis to be consider…
Shandong University（山东大学）；National University of Singapore（新加坡国立大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Existing studies on multimodal sentiment analysis heavily rely on textual modality and unavoidably induce the spurious correlations between textual words and sentiment labels. This greatly hinders the model generalization ability. To address this problem, we define the task of out-of-distribution (OOD) multimodal sentiment analysis. This task aims to estimate and mitigate the bad effect of textual modality for strong OOD generalization. To this end, we embrace causal inference, which inspects the causal relationships via a causal graph. From the graph, we find that the spurious correlations ar…
Enhancing Cryptocurrency Sentiment Analysis with Multimodal Features
Department of Computer Science, The University of Auckland（计算机科学系，奥克兰大学）；School of Information Systems, Queensland University of Technology（信息系统学院，昆士兰技术大学）；Department of Economics, The University of Auckland（经济学系，奥克兰大学）
PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis
National University of Singapore（新加坡国立大学）；Wuhan University（武汉大学）；The University of Auckland（奥克兰大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Nanyang Technological University（南洋理工大学）
With the increasing popularity of video sharing websites such as YouTube and Facebook, multimodal sentiment analysis has received increasing attention from the scientific community. Contrary to previous works in multimodal sentiment analysis which focus on holistic information in speech segments such as bag of words representations and average facial expression intensity, we develop a novel deep architecture for multimodal sentiment analysis that performs modality fusion at the word level. In this paper, we propose the Gated Multimodal Embedding LSTM with Temporal Attention (GME-LSTM(A)) model…
Sentiment analysis, mostly based on text, has been rapidly developing in the last decade and has attracted widespread attention in both academia and industry. However, the information in the real world usually comes from multiple modalities, such as audio and text. Therefore, in this paper, based on audio and text, we consider the task of multimodal sentiment analysis and propose a novel fusion strategy including both multi-feature fusion and multi-modality fusion to improve the accuracy of audio-text sentiment analysis. We call it the DFF-ATMF (Deep Feature Fusion - Audio and Text Modality Fu…
Multimodal machine learning is a core research area spanning the language, visual and acoustic modalities. The central challenge in multimodal learning involves learning representations that can process and relate information from multiple modalities. In this paper, we propose two methods for unsupervised learning of joint multimodal representations using sequence to sequence (Seq2Seq) methods: a \textit{Seq2Seq Modality Translation Model} and a \textit{Hierarchical Seq2Seq Modality Translation Model}. We also explore multiple different variations on the multimodal inputs and outputs of these …
Identifying and understanding underlying sentiment or emotions in text is a key component of multiple natural language processing applications. While simple polarity sentiment analysis is a well-studied subject, fewer advances have been made in identifying more complex, finer-grained emotions using only textual data. In this paper, we present a Transformer-based model with a Fusion of Adapter layers which leverages knowledge from more simple sentiment analysis tasks to improve the emotion detection task on large scale dataset, such as CMU-MOSEI, using the textual modality only. Results show th…
University of São Paulo（圣保罗大学）；Institute of Mathematics and Computer Sciences (ICMC)（数学与计算机科学学院（ICMC））
Most existing methods focus on sentiment analysis of textual data. However, recently there has been a massive use of images and videos on social platforms, motivating sentiment analysis from other modalities. Current studies show that exploring other modalities (e.g., images) increases sentiment analysis performance. State-of-the-art multimodal models, such as CLIP and VisualBERT, are pre-trained on datasets with the text paired with images. Although the results obtained by these models are promising, pre-training and sentiment analysis fine-tuning tasks of these models are computationally exp…
Singapore University of Technology and Design（新加坡科技设计大学）
In multimodal sentiment analysis (MSA), the performance of a model highly depends on the quality of synthesized embeddings. These embeddings are generated from the upstream process called multimodal fusion, which aims to extract and combine the input unimodal raw data to produce a richer multimodal representation. Previous work either back-propagates the task loss or manipulates the geometric property of feature spaces to produce favorable fusion results, which neglects the preservation of critical task-related information that flows from input to the fusion results. In this work, we propose a…
