Recognizing Emotions in Video Using Multimodal DNN Feature Fusion
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
We present our system description of input-level multimodal fusion of audio, video, and text for recognition of emotions and their intensities for the 2018 First Grand Challenge on Computational Modeling of Human Multimodal Language.Our proposed approach is based on input-level feature fusion with sequence learning from Bidirectional Long-Short Term Memory (BLSTM) deep neural networks (DNNs).We show that our fusion approach outperforms unimodal predictors.Our system performs 6-way simultaneous classification and regression, allowing for overlapping emotion labels in a video segment.This leads to an overall binary accuracy of 90%, overall 4-class accuracy of 89.2% and an overall mean-absolute-error (MAE) of 0.12.Our work shows that an early fusion technique can effectively predict the presence of multi-label emotions as well as their coarsegrained intensities.The presented multimodal approach creates a simple and robust baseline on this new Grand Challenge dataset.Furthermore, we provide a detailed analysis of emotion intensity distributions as output from our DNN, as well as a related discussion concerning the inherent difficulty of this task.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“They constructed a multimodal fusion system that discerns emotions and their intensities. By carrying out feature fusion at the input level and employing a Bidirectional Long Short-Term Memory (BLSTM) model for sequence learning, they underscored that early fusion can effectively predict the presence of multi-label emotions and their coarse-grained intensities.”
From A Survey of Deep Learning-Based Multimodal Emotion Recognition: Speech, Text, and Face (2023) · cites this paper as [84]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 2×
“The learning rule was Adam (Kingma and Ba, 2014) with default Tensorflow parameters.”
MethodGlove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 1×
“Text features consist of word vectors obtained from the Global Vectors for Word Representation (GloVe) software (Pennington et al., 2014) as well as one-hot word representations.”
Method(2014) · Cited by 33,419
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“sizes set to 64 (Ioffe and Szegedy, 2015).”
Convolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831 · cited 1×
“CNN: Convolutional Neural Networks are often used in NLP for various prediction tasks, including sentiment analysis (Kim, 2014).”
Method(2010) · International Conference on Machine Learning · Cited by 13,995
TensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
Multimodal Machine Learning: A Survey and Taxonomy
Baltrusaitis, T., Ahuja, C., & Morency, L.-P. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2798607 · Cited by 5,018
IEMOCAP: Interactive emotional dyadic motion capture database
Busso, C., Bulut, M., Lee, C.-C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J. N., Lee, S., & Narayanan, S. S. (2008) · Language Resources and Evaluation · doi:10.1007/s10579-008-9076-6 · Cited by 3,869 · cited 2×
“The subjects functioned as emotional actors and were asked to perform scripts that were designed to elicit specific emotions: happy, angry, sad, frustrated and neutral (Busso et al., 2008).”
BackgroundFace recognition: a convolutional neural-network approach
Lawrence, S., Giles, C. L., Tsoi, A. C., & Back, A. D. (1997) · IEEE Transactions on Neural Networks · doi:10.1109/72.554195 · Cited by 3,092 · cited 2×
“From the first time that convolutional neural networks (CNNs) were employed for face recognition (Lawrence et al., 1997) to the present times when sentiment analysis revolves around using CNNs (Tripathi et al.”
MethodA Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous Expressions
Zeng, Z., Pantic, M., Roisman, G. I., & Huang, T. S. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.52 · Cited by 2,797
Tensor Fusion Network for Multimodal Sentiment Analysis
Zadeh, A., Chen, M., Poria, S., Cambria, E., & Morency, L.-P. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1115 · Cited by 2,102 · cited 2×
“In light of recent successes with deep learning approaches to multimodal classification problems (Zadeh et al., 2017), emotion analysis remains truly challenging.”
BackgroundA review of affective computing: From unimodal analysis to multimodal fusion
Poria, S., Cambria, E., Bajpai, R., & Hussain, A. (2017) · Information Fusion · doi:10.1016/j.inffus.2017.02.003 · Cited by 1,644 · cited 1×
“However, it remains a difficult task due to the ambiguity of language and the use of slang and sarcasm (Baltrušaitis et al., 2018; Poria et al., 2017; Soleymani et al., 2017).”
BackgroundMultimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
Bagher Zadeh, A., Liang, P. P., Poria, S., Cambria, E., & Morency, L.-P. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1208 · Cited by 1,433 · cited 7×
“First, we created our own custom data split from the CMU-MOSEI challenge data so that we could utilize a held-out test set.”
MethodInfluentialConvolutional Neural Networks for Sentence ClassificationPreprint
Kim, Y. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1408.5882 · Cited by 1,112 · cited 1×
“CNN: Convolutional Neural Networks are often used in NLP for various prediction tasks, including sentiment analysis (Kim, 2014).”
MethodMultimodal Sentiment Intensity Analysis in Videos: Facial Gestures and Verbal Messages
Zadeh, A., Zellers, R., Pincus, E., & Morency, L.-P. (2016) · IEEE Intelligent Systems · doi:10.1109/mis.2016.94 · Cited by 852 · cited 4×
“this notion is applicable across many fields and tasks, in this work we focus on emotion analysis from video data — a very active research area that is beaming with interesting results and methodologies (Pérez-Rosas et al., 2013; Wöllmer et al., 2013; Poria et al., 2015; Brady et al., 2016; Zadeh et al., 2016b).”
BackgroundMethodInfluentialSpeech emotion recognition using deep neural network and extreme learning machine
Han, K., Yu, D., & Tashev, I. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-57 · Cited by 794 · cited 2×
“work on emotion recognition using Bidirectional LSTMs, which we also use for developing our best system (e.g. Ghosh et al., 2016; Lee and Tashev, 2015; Han et al., 2014; Chernykh et al., 2017).”
MethodCOVAREP — A collaborative voice analysis repository for speech technologies
Degottex, G., Kane, J., Drugman, T., Raitio, T., & Scherer, S. (2014) · 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2014.6853739 · Cited by 695 · cited 4×
“These low-level descriptors can be extracted from the audio signal using a standard speech toolbox such as the COVAREP software (Degottex et al., 2014).”
BackgroundMethodInfluentialMulti-Label Classification Of Music Into Emotions.
Trohidis, K., Tsoumakas, G., Kalliris, G. M., & Vlahavas, I. P. (2008) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.1414899 · Cited by 607
A survey of multimodal sentiment analysis
Soleymani, M., Garcia, D., Jou, B., Schuller, B., Chang, S.-F., & Pantic, M. (2017) · Image and Vision Computing · doi:10.1016/j.imavis.2017.08.003 · Cited by 601 · cited 2×
“However, it remains a difficult task due to the ambiguity of language and the use of slang and sarcasm (Baltruˇsaitis et al., 2018; Poria et al., 2017; Soleymani et al., 2017).”
BackgroundThe computer expression recognition toolbox (CERT)
Littlewort, G., Whitehill, J., Wu, T., Fasel, I., Frank, M., Movellan, J., & Bartlett, M. (2011) · Face and Gesture 2011 · doi:10.1109/fg.2011.5771414 · Cited by 539 · cited 2×
“Video features were extracted using the Emotient FACET software (Littlewort et al., 2011).”
MethodPoria, S., Cambria, E., & Gelbukh, A. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1303 · Cited by 533 · cited 2×
“this notion is applicable across many fields and tasks, in this work we focus on emotion analysis from video data — a very active research area that is beaming with interesting results and methodologies (Pérez-Rosas et al., 2013; Wöllmer et al., 2013; Poria et al., 2015; Brady et al., 2016; Zadeh et al., 2016b).”
BackgroundSpeech emotion recognition using convolutional and Recurrent Neural Networks
Lim, W., Jang, D., & Lee, T. (2016) · 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA) · doi:10.1109/apsipa.2016.7820699 · Cited by 405 · cited 1×
“Many approaches to detecting emotion in speech use recurrent neural network (RNN) approaches to sequential learning, such as Long-Short Term Memory (LSTM) (Lim et al., 2016).”
MethodYoutube movie reviews: Sentiment analysis in an audio-visual context
Wollmer, M., Weninger, F., Knaup, T., Schuller, B., Sun, C., Sagae, K., & Morency, L.-P. (2013) · IEEE Intelligent Systems · doi:10.1109/mis.2013.34 · Cited by 403 · cited 2×
“this notion is applicable across many fields and tasks, in this work we focus on emotion analysis from video data — a very active research area that is beaming with interesting results and methodologies (Pérez-Rosas et al., 2013; Wöllmer et al., 2013; Poria et al., 2015; Brady et al., 2016; Zadeh et al., 2016b).”
BackgroundHigh-level feature representation using recurrent neural network for speech emotion recognition
Lee, J., & Tashev, I. (2015) · Interspeech 2015 · doi:10.21437/interspeech.2015-336 · Cited by 388 · cited 1×
“work on emotion recognition using Bidirectional LSTMs, which we also use for developing our best system (e.g. Ghosh et al., 2016; Lee and Tashev, 2015; Han et al., 2014; Chernykh et al., 2017).”
MethodMOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos
Zadeh, A., Zellers, R., Pincus, E., & Morency, L.-P. (2016) · arXiv · doi:10.48550/arxiv.1606.06259 · Cited by 350 · cited 3×
“…applicable across many fields and tasks, in this work we focus on emotion analysis from video data — a very active research area that is beaming with interesting results and methodologies (P´erez-Rosas et al., 2013; W¨ollmer et al., 2013; Poria et al., 2015; Brady et al., 2016; Zadeh et al., 2016b).”
BackgroundMethodRendering of Eyes for Eye-Shape Registration and Gaze Estimation
Wood, E., Baltruaitis, T., Zhang, X., Sugano, Y., Robinson, P., & Bulling, A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.428 · Cited by 308 · cited 2×
“(2016a), the visual features include 16 Facial Action Units, 68 Facial Landmarks, Head Pose and Orientation, 6 Basic Emotions and Eye Gaze (Wood et al., 2015; Baltrusaitis et al., 2014).”
Background(2013) · Cited by 236
Representation Learning for Speech Emotion Recognition
Ghosh, S., Laksana, E., Morency, L.-P., & Scherer, S. (2016) · Interspeech 2016 · doi:10.21437/interspeech.2016-692 · Cited by 123 · cited 1×
“There has been work on emotion recognition using Bidirectional LSTMs, which we also use for developing our best system (e.g. Ghosh et al., 2016; Lee and Tashev, 2015; Han et al., 2014; Chernykh et al., 2017).”
MethodEmotion Recognition From Speech With Recurrent Neural Networks
Chernykh, V., & Prikhodko, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.08071 · Cited by 122 · cited 2×
“work on emotion recognition using Bidirectional LSTMs, which we also use for developing our best system (e.g. Ghosh et al., 2016; Lee and Tashev, 2015; Han et al., 2014; Chernykh et al., 2017).”
MethodMulti-Modal Audio, Video and Physiological Sensor Learning for Continuous Emotion Prediction
Brady, K., Gwon, Y., Khorrami, P., Godoy, E., Campbell, W., Dagli, C., & Huang, T. S. (2016) · Proceedings of the 6th International Workshop on Audio/Visual Emotion Challenge · doi:10.1145/2988257.2988264 · Cited by 110 · cited 4×
“edu/acl2018multimodalchallenge/ ing as well as a state space estimation approach to multimodal fusion (Brady et al., 2016).”
BackgroundMethodInfluentialVisual Sentiment Prediction with Deep Convolutional Neural Networks
Xu, C., Cetintas, S., Lee, K.-C., & Li, L.-J. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1411.5731 · Cited by 109 · cited 4×
“, 1997) to the present times when sentiment analysis revolves around using CNNs (Tripathi et al., 2017; Xu et al., 2014; Pereira et al., November 2016), CNNs appear promising for multimodal sentiment analysis and emotion recognition.”
BackgroundMethodInfluentialContinuous Conditional Neural Fields for Structured Regression
Baltrušaitis, T., Robinson, P., & Morency, L.-P. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10593-2_39 · Cited by 101 · cited 2×
“(2016a), the visual features include 16 Facial Action Units, 68 Facial Landmarks, Head Pose and Orientation, 6 Basic Emotions and Eye Gaze (Wood et al., 2015; Baltrusaitis et al., 2014).”
BackgroundFusing Audio, Textual, and Visual Features for Sentiment Analysis of News Videos
Pereira, M. H. R., Pádua, F. L. C., Pereira, A. C. M., Benevenuto, F., & Dalip, D. H. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v10i1.14810 · Cited by 27
Tensor Fusion Network for Multimodal Sentiment Analysis
Zadeh, A., Chen, M., Poria, S., Cambria, E., & Morency, L.-P. (2017) · arXiv · doi:10.48550/arxiv.1707.07250 · cited 2×
“In light of recent successes with deep learning approaches to multimodal classification problems (Zadeh et al., 2017), emotion analysis remains truly challenging.”
Background
Research works printed but not linked: 2
- Keng-hao Chang, Drew Fisher, and John Canny. 2011. AMMON: A Speech Analysis Library For Analyz- ing Affect, Stress, and Mental Health on Mobile Phones. Proceedings of PhoneSense.
- Samarth Tripathi, Shrinivas Acharya, Ranti Dev Sharma, Sudhanshu Mittal, and Samit Bhattacharya. 2017. Using Deep and Convolutional Neural Net- works for Accurate emotion classification on DEAP Dataset. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, USA., pages 4746- 4752.
Cited by
CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotation of Modality
Yu, W., Xu, H., Meng, F., Zhu, Y., Ma, Y., Wu, J., Zou, J., & Yang, K. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.343 · Cited by 482
“The Early Fusion LSTM (EF-LSTM) (Williams et al., 2018) concatenates initial inputs of three modalities first and then use LSTM to capture long-distance dependencies in a sequence.”
MethodTransformer-based Feature Reconstruction Network for Robust Multimodal Sentiment Analysis
Yuan, Z., Li, W., Xu, H., & Yu, W. (2021) · Proceedings of the 29th ACM International Conference on Multimedia · doi:10.1145/3474085.3475585 · Cited by 211
“The models like MFN [30] and EF-LSTM [27] can work on aligned multimodal data, which means the frames of audio and vision have explicit correspondence with the words in the text modality.”
MethodA Survey of Deep Learning-Based Multimodal Emotion Recognition: Speech, Text, and Face
Lian, H., Lu, C., Li, S., Zhao, Y., Tang, C., & Zong, Y. (2023) · Entropy · doi:10.3390/e25101440 · Cited by 224
“Further progress in early fusion was seen in the work of Williams et al. [84].”
MethodAutomated emotion recognition: Current trends and future perspectives
Maithri, M., Raghavendra, U., Gudigar, A., Samanth, J., Barua, P. D., Murugappan, M., Chakole, Y., & Acharya, U. R. (2022) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2022.106646 · Cited by 172
Ho, N.-H., Yang, H.-J., Kim, S.-H., & Lee, G. (2020) · IEEE Access · doi:10.1109/access.2020.2984368 · Cited by 167
Metadata
- Authors
- Williams, J., Kleinegesse, S., Comanescu, R., & Radu, O.
- Affiliations
- University of Edinburgh (GB)
- Corresponding author
- Williams, Jennifer
- Venue
- Proceedings of Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML)
- Published
- 2018
- Pages
- 11-19
- OpenAlex
- W2924126491
- Cited by
- 132
- References
- 35
- Citations by year
- 2026: 16 · 2025: 31 · 2024: 30 · 2023: 26 · 2022: 9 · 2021: 11 · 2020: 7 · 2019: 1 · 2018: 1
- FWCI
- 6.11
- Type
- conference paper
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- ePrints Soton (University of Southampton) (submittedVersion)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, cc-by)
- Funders
- University of Edinburgh
- Engineering and Physical Sciences Research Council (EP/L016427/1)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- emotion recognition, video, multimodal fusion, feature-level fusion, emotion intensity estimation, multi-label emotion classification, bidirectional LSTM, deep neural network
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.

![Figure 2 Distribution of predicted intensity targets for each emotion: [ Anger, Disgust, Fear, Happy, Sad, Surprised ]](https://figures.cochat.ai/paper-figures/91bf147507154938a79b7e6ab2b85a49/recognizing-emotions-in-video-using-multimodal-dnn-feature-fusion-figure-2.png)