Cited by 657Emotion and Mood RecognitionFace recognition and analysisDomain Adaptation and Few-Shot Learning

The DOI matches its Crossref record; 31 of the 32 references it cites were found in a registry or an index.

Deep Learning for Emotion Recognition on Small Datasets using Transfer Learning

Ng, Hong-Wei, Nguyen, Viet Dung, Vonikakis, Vassilios, Winkler, Stefan·2015·Proceedings of the 2015 ACM on International Conference on Multimodal Interaction

DOI 10.1145/2818346.2830593

Open this paper in CoChat — free account

Abstract

This paper presents the techniques employed in our team's submissions to the 2015 Emotion Recognition in the Wild contest, for the sub-challenge of Static Facial Expression Recognition in the Wild. The objective of this sub-challenge is to classify the emotions expressed by the primary human subject in static images extracted from movies. We follow a transfer learning approach for deep Convolutional Neural Network (CNN) architectures. Starting from a network pre-trained on the generic ImageNet dataset, we perform supervised fine-tuning on the network in a two-stage process, first on datasets relevant to facial expressions, followed by the contest's dataset. Experimental results show that this cascading fine-tuning approach achieves better results, compared to a single stage fine-tuning with the combined datasets. Our best submission exhibited an overall accuracy of 48.5% in the validation set and 55.6% in the test set, which compares favorably to the respective 35.96% and 39.13% of the challenge baseline.

Integrity signals

Registry

Crossref · 10.1145/2818346.2830593

Cites

31 of 31 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
Robust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097
Advances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019
Return of the Devil in the Details: Delving Deep into Convolutional Nets
Chatfield, K., Simonyan, K., Vedaldi, A., & Zisserman, A. (2014) · Proceedings of the British Machine Vision Conference 2014 · doi:10.5244/c.28.6 · Cited by 3,335
Recognizing action units for facial expression analysis
Tian, Y.-I., Kanade, T., & Cohn, J. F. (2001) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.908962 · Cited by 1,745

Flagged first, then by citations

Show all 32 references

1 of the 32 references couldn’t be matched to a known paper.

Research works printed but not linked: 1

J. R. S. Widen and A. Brooks . Anger and disgust: Discrete or overlapping categories ? In Proceedings of the 2004 APS Annual Convention , 2004 . J. R. S. Widen and A. Brooks. Anger and disgust: Discrete or overlapping categories? In Proceedings of the 2004 APS Annual Convention, 2004.

Sorted by citations

Items 501–600 of 655

Detecting Children Emotion through Facial Expression Recognition
Chinta, U., & Atyabi, A. (2023) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53992.2023.10394090 · Cited by 2
“[17] utilized transfer learning with a pre-trained CNN model on the FER-2013 dataset, achieving an accuracy of 83.5%.”
MethodInfluential
Relevant Musical Schema-based Human Emotion Controller using Deep Learning Techniques
Nagaraj, P., Sudar, K. M., Krishna, G. V., Yeswanth, G. S., Charan, G., & Charan, N. (2024) · IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS) · doi:10.1109/incos59338.2024.10527687 · Cited by 2
“Some criticisms of existing research include low feature extraction quality, a single assessment measure, and a shortage of systematic studies on user behaviors and demands[13].”
Background
Enhancing Face Emotion Recognition with FACS-Based Synthetic Dataset Using Deep Learning Models
Mishra, S., Shalu, P., & Singh, R. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-58181-6_44 · Cited by 2
Robust Facial Emotion Detection in Low-Light Conditions: A Novel Approach Using Real-Time WebSocket Data Transfer
Patel, D. M., Qurashi, A. W., & Johnson, A. P. (2024) · International Conference on Intelligent Computing in Data Sciences (ICDS) · doi:10.1109/icds62089.2024.10756352 · Cited by 3
Multi-Modal Emotion and Gesture Recognition System for Humans and Animals Using Computer Vision and Deep Learning
Nair, R. R., Babu, T., Kishore, S. P., Shivaswamy, S., Aruna, S., & Bhargavi, M. (2024) · International Conference on IoT Based Control Networks and Intelligent Systems (ICICNIS) · doi:10.1109/icicnis64247.2024.10823314 · Cited by 3
“Transfer learning approaches, which fine-tune pre-trained models on emotion recognition tasks, have proven particularly effective [20].”
Mal Class: A Deep Learning Approach for Automatic Classification of Malware Images
Divya, S. (2025) · International Conference on Sentiment Analysis and Deep Learning (ICSADL) · doi:10.1109/icsadl65848.2025.10933410 · Cited by 3
“These general traits were successfully extracted from smaller datasets by Ng et al. [14] in a various classification investigations.”
Transfer learning-based facial emotion detection for enhanced driver safety: a hybrid approach
Slimi, S., Kallel, I. F., Kallel, M., Fakhfakh, M., Ouhmida, A., & Raihani, A. (2025) · Engineering Research Express · doi:10.1088/2631-8695/adfa6b · Cited by 2
Singular Learning of Deep Multilayer Perceptrons for EEG-Based Emotion Recognition
Guo, W., Li, G., Lu, J., & Yang, J. J. (2021) · Frontiers in Computer Science · doi:10.3389/fcomp.2021.786964 · Cited by 2
“…in Computer Science | www.frontiersin.org December 2021 | Volume 3 | Article 7869641 ORIGINAL RESEARCH published: 21 December 2021 doi: 10.3389/fcomp.2021.786964 learning also show significant superiority of conventional methods (Ng et al., 2015; Tzirakis et al., 2017; Hassan et al., 2019).”
BackgroundMethodInfluential
A Review on Forensic Science and Criminal Investigation Through a Deep Learning Framework
Acharjya, P. P., Koley, S., & Barman, S. (2022) · Advances in digital crime, forensics, and cyber terrorism book series · doi:10.4018/978-1-6684-4558-7.ch001 · Cited by 2
How Good Is Your Model ‘Really’? On ‘Wildness’ of the In-the-Wild Speech-Based Affect Recognisers
Pandit, V., Schmitt, M., Cummins, N., Graf, F., Paletta, L., & Schuller, B. W. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-99579-3_51 · Cited by 2
Comparison of Facial Emotion Recognition Based on Image Visual Features and EEG Features
Long, Y., Kong, W., Ling, W., Yang, C., & Zhu, J. (2019) · Communications in computer and information science · doi:10.1007/978-981-13-7986-4_15 · Cited by 2
Emotional Detection of Patients Major Depressive Disorder in Medical Diagnosis
Ketcham, M., Piyaneeranart, M., & Ganokratanaa, T. (2018) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis.2018.00058 · Cited by 2
“At the international level [9-14], activities are organized for multimedia processing and computer-based learning.”
Background
Cross-Domain Knowledge Transfer for Incremental Deep Learning in Facial Expression Recognition
Sugianto, N., & Tjondronegoro, D. (2019) · International Conference on Robot Intelligence Technology and Applications (RiTA) · doi:10.1109/ritapp.2019.8932731 · Cited by 2
“In [6], a mixed homogenous and heterogeneous transfer training is used for spontaneous facial expression recognition tasks.”
Background
TRANSFER:- DEEP INDUCTIVE NETWORK FOR FACIAL EMOTION RECOGNITION
Gupta, A. (2020) · JOURNAL OF MECHANICS OF CONTINUA AND MATHEMATICAL SCIENCES · doi:10.26782/jmcms.2020.07.00029 · Cited by 2
Self-Learning System for Child Development Using Conversational AI and Natural Language Processing (NLP)
Mishra, A. K. (2020) · Advances in educational technologies and instructional design book series · doi:10.4018/978-1-7998-4763-2.ch007 · Cited by 2
Recursive Identification Based on OS-ELM for Emotion Recognition and Prediction of Difficulties in Video Game
Blaiech, H., & Liouane, N. (2020) · Studies in Informatics and Control · doi:10.24846/v29i3y202007 · Cited by 2
“Another example is the work of (Ng et al. 2015), which classifies the emotions expressed by the primary human subject in static images extracted from movies.”
Background
Electroencephalography Signal Analysis and Classification Based on Deep Learning
Li, Z. (2020) · International Conference on Information Science, Computer Technology and Transportation (ISCTT) · doi:10.1109/isctt51595.2020.00029 · Cited by 2
Solution to OCT Diagnosis Using Simple Baseline CNN Models and Hyperparameter Tuning
Kushwaha, A. K., & Rastogi, S. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-3071-2_30 · Cited by 2
Transfer Learning for Handwritten Character Recognition
Inunganbi, S. C., & Katariya, R. S. (2021) · Lecture notes in networks and systems · doi:10.1007/978-981-16-6369-7_63 · Cited by 3
A hybrid approach based on transfer and ensemble learning for improving performances of deep learning models on small datasets
Gültekin, T., & Uğur, A. (2021) · TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES · doi:10.3906/elk-2102-101 · Cited by 2
“For an emotion prediction task, transfer learning was applied by using two-staged fine-tuning [13].”
Method
Emotion Recognition in Music Using Deep Neural Networks
Geroulanos, A., & Γιαννακόπουλος, Θ. (2022) · Signals and communication technology · doi:10.1007/978-3-031-18444-4_10 · Cited by 2
Face Emotion Pattern Analysis of Korean Depending on Persons and Environments Using DCGAN
Kim, D. H. (2023) · IARJSET · doi:10.17148/iarjset.2023.10932 · Cited by 2
Deep Learning for Human Visual Attention Recognition Using Transfer Learning
Hoai, N. V., Mai, H. N., & Pham, C. (2018) · International Conference on Advanced Technologies for Communications · doi:10.1109/atc.2018.8587576 · Cited by 2
“[18] proposed a system which utilizing transfer learning approach for emotion recognition on small datasets.”
Background
Patient Stress Estimation for Using Deep Learning with RRI Data Sensed by WBAN
Kinjo, Y., Sakuma, Y., Kobayashi, T., Sugimoto, C., & Kohno, R. (2019) · International Symposium on Medical Information and Communication Technology · doi:10.1109/ismict.2019.8743842 · Cited by 2
“Therefore, we adopt the method of transfer learning [7].”
Method
Facial Expression Recognition: Residue Learning Using SVM
Wang, F., & Shen, L. (2019) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai.2019.00246 · Cited by 2
“[21] proposed a CNN architecture from a network pre-trained on the generic ImageNet dataset first, and fine-tuning approach is used to expression datasets.”
Background
Behaviour Based Data Dispatcher
(2019) · International Journal of Recent Technology and Engineering (IJRTE) · doi:10.35940/ijrte.d8428.118419 · Cited by 2
Deep Learning of Human Apparent Age for the Detection of Sexually Exploitative Imagery of Children
Rondeau, J. (2019) · doi:10.23860/thesis-rondeau-jared-2019 · Cited by 2
The Contextual Dynamics of Multimodal Emotion Recognition in VideosPreprint
Bhattacharya, P., Gupta, R. K., & Yang, Y. (2020) · arXiv (Cornell University) · Cited by 2
Abordagem computacional para aprimoramento das habilidades com as emoções em indivíduos com autismo
Dantas, A. C. (2022) · doi:10.14393/ufu.te.2022.211 · Cited by 2
Face Emotion Detection Using Convolutional Neural Network (CNN) and OpenCVPreprint
Pandey, U., Janahan, S. K., Kumar, S., Kumar, U., Maurya, H., & Divyansh, K. S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4490240 · Cited by 2
Separation of the Latent Representations into "Identity" and "Expression" without Emotional Labels
Kanou, Y., & Nagao, T. (2020) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc42975.2020.9283482 · Cited by 1
“In recent years, many authors reported successful facial expression recognition using a deep learning model like convolutional neural networks (CNNs) [11], [14], [17]–[19].”
Background
Exploring Multi-Modality in Animal-Centered Computing
Oren, A. (2021) · International Conference on Animal-Computer Interaction (ACI) · doi:10.1145/3493842.3493900 · Cited by 1
“The use of CNN (convolutional neural network) and RNN (recurrent neural network) in human emotion recognition has great results as shown in [18], more problems similar to those presented in our video datasets [27, 28].”
Result
Fused Architecture with Enhanced Bag of Visual Words for Efficient Drowsiness Detection
Vijayan, V., & Pushpalatha, K. P. (2023) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2023.p0182 · Cited by 1
Foundations on transfer learning in machine fault diagnosis and prognosis
Yan, R., & Shen, F. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-99989-2.00011-6 · Cited by 1
Facial Emotion Recognition for Virtual Customer Service Agents
Gupta, S., Saxena, S., Verma, V., & Nishad, D. K. (2024) · International Conference on Communication, Computer Sciences and Engineering (IC3SE) · doi:10.1109/ic3se62002.2024.10593310 · Cited by 1
“Variants like Inception [17] and ResNet [18], with very deep architectures, have published the results of state-of-the-art data analysis.”
Background
VATE: A Large Scale Multimodal Spontaneous Dataset for Affective Evaluation
Agnelli, F., Grossi, G., D’Amelio, A., Paoli, M. D., & Lanzarotti, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91575-8_13 · Cited by 1
Identify user features impacting keystroke, mouse and touchscreen dynamics
Yang, L., & Qin, S. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-21043-2 · Cited by 1
Deep Learning-Based Speech Emotion Recognition for IoT Edge Devices: A Comparative Study
İşler, B. (2025) · Journal of Polytechnic · doi:10.2339/politeknik.1729678 · Cited by 1
Emotion Recognition in Multi-speaker Scenarios for Social Robots
García‐Rodríguez, J., Begazo, R., Cárdenas, P., Dongo, I., Cardinale, Y., & Aguilera, A. (2025) · International Journal of Social Robotics · doi:10.1007/s12369-025-01312-8 · Cited by 1
Automatic speech emotion recognition for arabic dialects: a new dataset and machine learning framework
Kahhoul, Z. S., Terki, N., Dahmani, H., Athamena, B., Houhamdi, Z., Hamiane, M., & Bourennane, M. (2025) · Cluster Computing · doi:10.1007/s10586-025-05830-y · Cited by 2
A Systematic Literature Review on Emotion Recognition and Classification in Online Learning
Zhang, X., & Liu, C. (2025) · Concurrency and Computation · doi:10.1002/cpe.70428 · Cited by 1
An improved transfer learning for surface defect detection in edge-cloud continuum environments
Tang, B. T., Lin, Y., Cao, Y., Zhang, L., Ma, X., & Yang, Q. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-025-07993-2 · Cited by 1
“Ng et al. [18] pre-trained a deep CNN on the large-scale ImageNet dataset and transferred the learned knowledge to a small facial expression dataset, significantly improving the accuracy of emotion feature detection.”
Transferring Multi-Channel Convolutional Neural Network Model for Cross-Domain Sentiment Analysis
Rozie, A. F., Arisal, A., & Munandar, D. (2019) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti48646.2019.9034599 · Cited by 1
FSE: a Powerful Feature Augmentation Technique for Classification Task
Liu, Y., Yang, Y., & Hossain, M. Z. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-92270-2_55 · Cited by 1
An Emotion Recognition Model Augmented a Small Amount of Individual EEG by Domain Adaptation
Furukawa, S., Sakuma, T., & Kato, S. (2022) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.142.771 · Cited by 1
Communication Analysis through Visual Analytics: Current Practices, Challenges, and New Frontiers
Fischer, M. T., Dennig, F. L., Seebacher, D., Keim, D. A., & El‐Assady, M. (2022) · IEEE Visualization in Data Science (VDS) · doi:10.1109/vds57266.2022.00006 · Cited by 2
“Implication: Using such models can potentially support the analysis [12, 35], through measures as active learning [10, 66], intelligent filtering [23], or confidence-based predictions [75].”
EMPATÍA-CM: protEcción integral de las víctimas de violencia de género Mediante comPutación AfecTIva multimodal
Manuel, R. S. S., & López-Ongil, C. (2022) · Sociología y Tecnociencia · doi:10.24197/st.1.2022.1-33 · Cited by 1
Recognition and Classification of Facial Expressions Using Artificial Neural Networks
Tuama, B. A., Shawkat‎‎, S. A., & Askar, N. A. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-3148-2_20 · Cited by 1
Multi-level feature fusion capsule network with self-attention for facial expression recognition
Huang, Z., Yu, S., & Liang, J. (2023) · Journal of Electronic Imaging · doi:10.1117/1.jei.32.2.023038 · Cited by 1
Anterior Segment Eye Abnormality Detection
Corbaci, T. (2023) · International Conference on Intelligent Information Technology (ICIIT) · doi:10.1145/3591569.3591590 · Cited by 1
“A study in 2015 utilized a pre-trained algorithm to classify emotions from a small dataset of facial images [26].”
Method
Automated Emotion Recognition Through Graphical Cues on Comics at Character Scale
Théodose, R., Burie, J.-C., & Revel, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-37742-6_5 · Cited by 1
A simplified U-net model for Covid-19 CT image segmentation
Zhan, H. (2023) · Applied and Computational Engineering · doi:10.54254/2755-2721/19/20231011 · Cited by 1
Transfer Learning-Based Effective Facial Emotion Recognition Using Contrast Limited Adaptive Histogram Equalization (CLAHE)
Devi, D. A. S., Rekha, D. S., Kumar, M. K., Rao, P. R. M., & Vallika, G. N. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-6690-5_20 · Cited by 1
Real-Time Facial Emotion Recognition Using Haar-Cascade Classifier and MobileNet in Smart Cities
El‐Shekheby, S. (2024) · Earth and environmental sciences library · doi:10.1007/978-3-031-46491-1_33 · Cited by 1
A Deep Learning Model for Automatic Recognition of Facial Expressions Using Haar Cascade Images
Johri, P., Gangwar, L. K., Sharma, P., Rajesh, E., Baghela, V. S., & Johri, M. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-99-7862-5_14 · Cited by 1
Deep Transfer Learning Method Using Self-Pixel and Global Channel Attentive Regularization
Kang, C., & Kang, S.-U. (2024) · Sensors · doi:10.3390/s24113522 · Cited by 1
“For example, Ng et al. [15] showed about 16% higher emotion recognition accuracy, Zhao [16] achieved 7.2% better classification results, and Mohammadian et al. [17] attained about 12.1% improvement over the conventional approach [18] in diabetes diagnosis.”
ResultInfluential
Steel Plate Fault Detection Using the Fitness-Dependent Optimizer and Neural Networks
Farahmand‐Tabar, S., & Rashid, T. A. (2024) · Springer eBooks · doi:10.1007/978-981-97-3820-5_41 · Cited by 2
From Image to Emotion: Exploring CNN Architectures for Facial Emotion Recognition
Rafi, M., Alam, T., Chowdhury, L., & Chowdhury, B. R. (2024) · IEEE International Conference on Computing, Applications and Systems (COMPAS) · doi:10.1109/compas60761.2024.10795991 · Cited by 1
“Ng et al.(2015) [5] found that it was beneficial to use pre-trained models off the shelf and adjust them according to course-tailored data, even when doing so meant a significant increase in difficulty.”
ComFace: Facial Representation Learning with Synthetic Data for Comparing Faces
Akamatsu, Y., Umematsu, T., Imaoka, H., Gomi, S., & Tsurushima, H. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00514 · Cited by 2
“Facial Representation Learning: Transfer learning in face analysis tasks commonly depends on pre-training us-ing ImageNet [2, 15, 38, 45] and large face recognition datasets [33, 47, 51, 53, 54].”
Feature Pruned and Weighted Convolutional Neural Network for Micro-Expression Recognition
Mohideen, A. K. (2025) · International Journal of Software Science and Computational Intelligence · doi:10.4018/ijssci.389197 · Cited by 1
Approach to semi-automatic labeling of video sequences for affective computing-enabling the comprehensive assessment of emotion detection software from mimics
Böhm, T., Engel, F., Bzdok, D., Schneider, F. W., & Hemmje, M. (2017) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2017.8217967 · Cited by 3
“The main motivation for this process relies on evidence that the required training data set for this stage can be relatively small [9] [7] [6].”
Background
AVEID: Automatic Video System for Measuring Engagement In Dementia
Parekh, V., Foong, P. S., Zhao, S., & Subramanian, R. (2017) · ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam) · doi:10.48550/arxiv.1712.08084 · Cited by 1
“The Emotion Detection module implements the deep network for emotion recognition described in [12].”
BackgroundMethod
Meta Transfer Learning for Facial Emotion Recognition
Nguyen, D., Nguyen, K., Sridharan, S., Abbasnejad, I., Dean, D., & Fookes, C. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545411 · Cited by 1
Semantic analisis on faces using deep neural networks
Pellejero, N. (2018) · INTELIGENCIA ARTIFICIAL · doi:10.4114/intartif.vol21iss61pp14-29 · Cited by 1
Emotion Detection using Facial expressions with Transfer Learning
Geetanand, S., Basha, S. N., Rao, S. N., & Srinivas, R. (2019) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit195150 · Cited by 1
The Application of Using Convolutional Neural Network to Classify MRI Brain Tumor
Liu, Q. (2021) · 2021 2nd International Conference on Computing and Data Science (CDS) · doi:10.1109/cds52072.2021.00075 · Cited by 1
Customer Feedback Through Facial Expression Recognition System Using Neural Network
Dandgawhal, T. P., & Momin, B. F. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-1249-7_16 · Cited by 1
Recognition and Classification of Facial Expressions using Artificial Neural Networks
Tuama, B. A., Shawkat‎‎, S. A., & Askar, N. A. (2022) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/hora55278.2022.9800021 · Cited by 1
On Computational Complexity of Transfer Learning Approaches in Facial Analysis
Moloiu, A.-Ş., Albeanu, G., & Popențiu-Vlădicescu, F. (2022) · Smart innovation, systems and technologies · doi:10.1007/978-981-16-9447-9_27 · Cited by 1
Contextualizing Lung Nodule Malignancy Predictions with Easy vs. Hard Image Classification
Xu, E., Ramaraj, T., Tchoua, R., Furst, J. D., & Raicu, D. S. (2022) · International Conference on Transdisciplinary AI (TransAI) · doi:10.1109/transai54797.2022.00028 · Cited by 1
“Transfer learning has previously been demonstrated to improve performance of image classi-ﬁcation tasks on small datasets [16]–[18].”
Background
Self-Cure Networks with Latent Distribution Mining for Facial Expression Recognition
Zhao, G., Chen, Y., Wu, D., Liu, Y., Jing, S., & Wang, D. (2022) · International Conference on Algorithms, High Performance Computing and Artificial Intelligence (AHPCAI) · doi:10.1109/ahpcai57455.2022.10087623 · Cited by 1
Book Review and Future Work
Zhang, D. D., Guo, Z., & Gong, Y. (2015) · Springer eBooks · doi:10.1007/978-3-319-22485-5_12 · Cited by 1
A Global Alignment Kernel based Approach for Group-level Happiness Intensity EstimationPreprint
Huang, X., Dhall, A., Goecke, R., Pietikäinen, M., & Zhao, G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.03313 · Cited by 1
Confidence Trigger Detection: An Approach to Build Real-time Tracking-by-detection SystemPreprint
Ding, Z., & Wong, E. K. (2019) · arXiv (Cornell University) · Cited by 1
Group Affect Prediction Using Multimodal DistributionsPreprint
Shamsi, S., Rawat, B. P. S., & Wadhwa, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.01216 · Cited by 1
“It is interesting to see that all the three winners of the 3 rd EmotiW challenge utilized deep learning networks in their techniques [21][18][13].”
BackgroundMethod
Deep Multi-Facial patches Aggregation Network for Expression Classification from Face ImagesPreprint
Djerghri, A., Hazourli, A. R., & Othmani, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.10305 · Cited by 1
“Several works have been proposed for facial emotions classiﬁcation from static images [24, 7, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38] or from continuous video input [39, 40, 41].”
BackgroundMethod
Facial Expression Representation Learning by Synthesizing Expression ImagesPreprint
Ali, K., & Hughes, C. E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.01456 · Cited by 1
“he subjects with constant illumination and stable head pose. However, these features fail on spontaneous data with varying head position and illumination. Recently, deep CNN based methods [11], [12], [13] [14] have been employed to increase the robustness of FER to real-world scenarios. However, the learned deep repre…”
Sim-to-Real Domain Adaptation For High Energy PhysicsPreprint
Baalouch, M., Defurne, M., Poli, J.-P., & Cherrier, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.08001 · Cited by 8
“It has been carried out successfully in several ﬁelds as image recognition [4, 5, 6], sentiment classiﬁcation [7, 8] or robotics [9, 10, 11].”
Detecting Escalation Level from Speech with Transfer Learning and Acoustic-Lexical Information FusionPreprint
Zhou, Z., Xu, Y., & Li, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.06004 · Cited by 1
“[3] 2.”
Landmark-Aware and Part-based Ensemble Transfer Learning Network for Facial Expression Recognition from Static imagesPreprint
Wadhawan, R., & Gandhi, T. K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.11274 · Cited by 1
“Some researchers proposed multi-stage fine-tuning techniques over the direct use of these pre-trained models and fine-tuned models [10].”
BackgroundMethod
Multi-modal Residual Perceptron Network for Audio-Video Emotion RecognitionPreprint
Chang, X., & Skarbek, W. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.10742 · Cited by 1
“Moreover, for video frames, HW. Ng et al. [28] got 47.3% validation accuracy and 53.8% testing accuracy on EmotiW dataset [29] using transfer learning and averaged temporal deep features.”
MethodInfluential
Communication Analysis through Visual Analytics: Current Practices, Challenges, and New FrontiersPreprint
Fischer, M. T., Dennig, F. L., Seebacher, D., Keim, D. A., & El‐Assady, M. (2021) · doi:10.36227/techrxiv.15022791 · Cited by 2
Book Review and Future Work
Zhang, D. D., & Wu, K. (2020) · Springer eBooks · doi:10.1007/978-981-32-9196-6_8 · Cited by 1
Leveraging One-Class Classification with Resnet18 and Cbam for Enhanced Facial Expression RecognitionPreprint
Yang, W., Chen, H., Peng, H. J., Guo, J., & Liu, Z. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4505113 · Cited by 1
Facial expression recognition under harsh lighting using high dynamic range imaging.
Ige, E. O. (2026) · Warwick Research Archive Portal (University of Warwick) · doi:10.82444/warw.33741808
Separation of Water and Fat Magnetic Resonance Imaging Signals Using Deep Learning with Convolutional Neural NetworksPreprint
Goldfarb, J. W. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.00107
“ac MR trained ConvNets would perform well in other anatomical areas. Adaption to flexible MR protocols (number and positions of echo times) was not explored, but it is expected that transfer learning (19,39) could be used to minimize future ConvNet training for these applications. Computation time was not compared bet…”
Method
Expression recognition in the wild with transfer learning
Xia, T., Zhang, Y., Liu, Y., & Sun, Y. (2017) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2017.8170910
“Ng [29] employed a transfer learning method that contained two stages: A network pre-trained on ImageNet dataset is firstly fine-tuned on a dataset that relate to facial expression, then fine-tuned on target dataset.”
MethodInfluential
DEVELOPMENT OF THE METHOD OF UNSUPERVISED TRAINING OF CONVOLUTIONAL NEURAL NETWORKS BASED ON NEURAL GAS MODIFICATION
Москаленко, В. В. (2017) · Technology Transfer fundamental principles and innovative technical solutions · doi:10.21303/2585-6847.2017.00469
“2, a), the effectiveness of unsupervised training of a hierarchical feature extractor constructed on the first ten layers of the neural network VGG-16 by using a modification of the neural gas algorithm aimed to sparse coding of observations is proved.”
MethodInfluential
Semi-supervised Clustering of Facial Expressions
Jalal, A. (2017) · DSpace at AUS (American University of Sharjah) · doi:10.82366/574
Fast Learning for Accurate Object Recognition Using a Pre-trained Deep Neural Network
Ríos, V. L., Tenorio-González, A. C., & Morales, E. F. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-02837-4_4
“Fine-tuning have been successfully used classifying images from completely different domains such as land segmentation [16][18], emotion recognition [19] or medical images [20].”
Background
Deep Neural Networks for Human Behavior Understanding
Singh, R. K., & Nigam, S. (2019) · Springer eBooks · doi:10.1007/978-3-030-15887-3_32
Exploring Low-level and High-level Transfer Learning for Multi-task Facial Recognition with a Semi-supervised Neural Network
Barros, P. V. A., Fließwasser, E., Kerzel, M., & Wermter, S. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8968243
“Pre-training a network on a domain for which data is highly available and fine-tuning it for another domain where data is scarce is a paradigm that has become popular in recent years [17], [18], [19].”
Background
Training Approaches for Deep Learning Based Fault Diagnosis of Rotating Machinery Overcoming Fault Data Insufficiency
김현재 (2020) · Seoul National University Open Repository (Seoul National University)
DCNNs: A Transfer Learning comparison of Full Weapon Family threat detection for Dual-Energy X-Ray Baggage ImageryPreprint
Williamson, A., Dickinson, P., Lambrou, T., & Murray, J. C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.13065
“This technique has become popular across difﬁcult training domains, and has been shown to work within detection scenarios [21, 27].”
Conclusion and further research directions
Harrou, F., Sun, Y., Hering, A. S., Madakyaru, M., & Dairi, A. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-819365-5.00015-2
Addressing Variability in Speech when Recognizing Emotion and Mood In-the-Wild
Gideon, J. (2019) · Deep Blue (University of Michigan)
Performance Analysis of GAN Architecture for Effective Facial Expression Synthesis
Karthik, R., Nandana, B., Patil, M., Basu, C., & Rajangam, V. (2020) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-7998-6690-9.ch015
A Development Framework for Automated Facial Expression Recognition Systems
Rehman, B., Ong, W.-H., & Ngo, T. D. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-68133-3_16
“However, the CNN model can be made more robust by adding more data or using transfer learning [21].”
Method
Understanding, Quantifying, and Reducing Bias in Fisheries-independent Visual Surveys
Kilfoil, J. P. (2020) · doi:10.25148/etd.fidc008896
Bias-Free Yuragi Learning
Otoshi, T. (2020) · Springer eBooks · doi:10.1007/978-981-33-4976-6_10

Authors: Ng, H.-W., Nguyen, V. D., Vonikakis, V., & Winkler, S.
Affiliations: University of Illinois at Urbana-Champaign (Singapore), Singapore, Singapore
University of Illinois Urbana-Champaign (US)
ORCID: Vonikakis, Vassilios
Winkler, Stefan
Venue: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction
Publisher: ACM
Published: 2015-11-09
Pages: 443-449
DOI: 10.1145/2818346.2830593
OpenAlex: W2253728219
Cited by: 657
References: 32
Citations by year: 2026: 13 · 2025: 29 · 2024: 37 · 2023: 70 · 2022: 69 · 2021: 106 · 2020: 106 · 2019: 106 · 2018: 63 · 2017: 44 · 2016: 13 · 2015: 1
FWCI: 53.84
Type: conference paper
Language: en
Open access: closed
Licence: www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION (publishedVersion)
Funders: Agency for Science Technology and Research
Topics: Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords: emotion recognition, facial expression recognition, still images, transfer learning, convolutional neural networks, fine-tuning, ImageNet pre-training, small datasets

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

Deep Learning for Emotion Recognition on Small Datasets using Transfer Learning

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Citations

Cites

Cited by

Related

Metadata

Record

About these checks